🔹 Title:
Solving Inequality Proofs with Large Language Models
🔹 Publication Date: Published on Jun 9
🔹 Abstract:
The investigation into inequality proving using large language models uncovers significant challenges in constructing rigorous proofs, revealing gaps between finding answers and generating valid step-wise solutions. AI-generated summary Inequality proving, crucial across diverse scientific and mathematical fields, tests advanced reasoning skills such as discovering tight bounds and strategic theorem application. This makes it a distinct, demanding frontier for large language models ( LLMs ), offering insights beyond general mathematical problem-solving. Progress in this area is hampered by existing datasets that are often scarce, synthetic, or rigidly formal. We address this by proposing an informal yet verifiable task formulation, recasting inequality proving into two automatically checkable subtasks: bound estimation and relation prediction . Building on this, we release IneqMath , an expert-curated dataset of Olympiad-level inequalities, including a test set and training corpus enriched with step-wise solutions and theorem annotations. We also develop a novel LLM-as-judge evaluation framework, combining a final-answer judge with four step-wise judges designed to detect common reasoning flaws. A systematic evaluation of 29 leading LLMs on IneqMath reveals a surprising reality: even top models like o1 achieve less than 10% overall accuracy under step-wise scrutiny; this is a drop of up to 65.5% from their accuracy considering only final answer equivalence. This discrepancy exposes fragile deductive chains and a critical gap for current LLMs between merely finding an answer and constructing a rigorous proof. Scaling model size and increasing test-time computation yield limited gains in overall proof correctness. Instead, our findings highlight promising research directions such as theorem-guided reasoning and self-refinement . Code and data are available at https:// ineqmath .github.io/.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.07927
• PDF: https://arxiv.org/pdf/2506.07927
• Github: https://ineqmath.github.io/#visualization
🔹 Datasets citing this paper:
• https://huggingface.co/datasets/AI4Math/IneqMath
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Solving Inequality Proofs with Large Language Models
🔹 Publication Date: Published on Jun 9
🔹 Abstract:
The investigation into inequality proving using large language models uncovers significant challenges in constructing rigorous proofs, revealing gaps between finding answers and generating valid step-wise solutions. AI-generated summary Inequality proving, crucial across diverse scientific and mathematical fields, tests advanced reasoning skills such as discovering tight bounds and strategic theorem application. This makes it a distinct, demanding frontier for large language models ( LLMs ), offering insights beyond general mathematical problem-solving. Progress in this area is hampered by existing datasets that are often scarce, synthetic, or rigidly formal. We address this by proposing an informal yet verifiable task formulation, recasting inequality proving into two automatically checkable subtasks: bound estimation and relation prediction . Building on this, we release IneqMath , an expert-curated dataset of Olympiad-level inequalities, including a test set and training corpus enriched with step-wise solutions and theorem annotations. We also develop a novel LLM-as-judge evaluation framework, combining a final-answer judge with four step-wise judges designed to detect common reasoning flaws. A systematic evaluation of 29 leading LLMs on IneqMath reveals a surprising reality: even top models like o1 achieve less than 10% overall accuracy under step-wise scrutiny; this is a drop of up to 65.5% from their accuracy considering only final answer equivalence. This discrepancy exposes fragile deductive chains and a critical gap for current LLMs between merely finding an answer and constructing a rigorous proof. Scaling model size and increasing test-time computation yield limited gains in overall proof correctness. Instead, our findings highlight promising research directions such as theorem-guided reasoning and self-refinement . Code and data are available at https:// ineqmath .github.io/.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.07927
• PDF: https://arxiv.org/pdf/2506.07927
• Github: https://ineqmath.github.io/#visualization
🔹 Datasets citing this paper:
• https://huggingface.co/datasets/AI4Math/IneqMath
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤4
🙏💸 500$ FOR THE FIRST 500 WHO JOIN THE CHANNEL! 🙏💸
Join our channel today for free! Tomorrow it will cost 500$!
https://t.iss.one/+Cl8uwGkD0l5lMGNl
You can join at this link! 👆👇
https://t.iss.one/+Cl8uwGkD0l5lMGNl
Join our channel today for free! Tomorrow it will cost 500$!
https://t.iss.one/+Cl8uwGkD0l5lMGNl
You can join at this link! 👆👇
https://t.iss.one/+Cl8uwGkD0l5lMGNl
❤1
Article Title:
TradingAgents: Multi-Agents LLM Financial Trading Framework
Article Date: 28 Dec 2024
Article Description:
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have largely focused on single-agent systems handling specific tasks or multi-agent frameworks independently gathering data. However, the multi-agent systems' potential to replicate real-world trading firms' collaborative dynamics remains underexplored. TradingAgents proposes a novel stock trading framework inspired by trading firms, featuring LLM-powered agents in specialized roles such as fundamental analysts, sentiment analysts, technical analysts, and traders with varied risk profiles. The framework includes Bull and Bear researcher agents assessing market conditions, a risk management team monitoring exposure, and traders synthesizing insights from debates and historical data to make informed decisions. By simulating a dynamic, collaborative trading environment, this framework aims to improve trading performance. Detailed architecture and extensive experiments reveal its superiority over baseline models, with notable improvements in cumulative returns, Sharpe ratio, and maximum drawdown, highlighting the potential of multi-agent LLM frameworks in financial trading. TradingAgents is available at https://github.com/TauricResearch/TradingAgents.PDFAbstract
PDF Download Link:
https://arxiv.org/pdf/2412.20138v7.pdf
GitHub:
• https://github.com/tauricresearch/tradingagents
Datasets:
• No datasets information available
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
TradingAgents: Multi-Agents LLM Financial Trading Framework
Article Date: 28 Dec 2024
Article Description:
Significant progress has been made in automated problem-solving using societies of agents powered by large language models (LLMs). In finance, efforts have largely focused on single-agent systems handling specific tasks or multi-agent frameworks independently gathering data. However, the multi-agent systems' potential to replicate real-world trading firms' collaborative dynamics remains underexplored. TradingAgents proposes a novel stock trading framework inspired by trading firms, featuring LLM-powered agents in specialized roles such as fundamental analysts, sentiment analysts, technical analysts, and traders with varied risk profiles. The framework includes Bull and Bear researcher agents assessing market conditions, a risk management team monitoring exposure, and traders synthesizing insights from debates and historical data to make informed decisions. By simulating a dynamic, collaborative trading environment, this framework aims to improve trading performance. Detailed architecture and extensive experiments reveal its superiority over baseline models, with notable improvements in cumulative returns, Sharpe ratio, and maximum drawdown, highlighting the potential of multi-agent LLM frameworks in financial trading. TradingAgents is available at https://github.com/TauricResearch/TradingAgents.PDFAbstract
PDF Download Link:
https://arxiv.org/pdf/2412.20138v7.pdf
GitHub:
• https://github.com/tauricresearch/tradingagents
Datasets:
• No datasets information available
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤4
🔹 Title:
Configurable Preference Tuning with Rubric-Guided Synthetic Data
🔹 Publication Date: Published on Jun 13
🔹 Abstract:
Configurable Preference Tuning enables language models to dynamically adjust their behavior based on human-interprettable directives, using rubric-guided preference data for fine-tuning and inference-time modulation. AI-generated summary Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic preferences by introducing Configurable Preference Tuning (CPT), a novel framework for endowing language models with the ability to dynamically adjust their behavior based on explicit, human-interpretable directives. CPT leverages synthetically generated preference data, conditioned on system prompts derived from structured, fine-grained rubrics that define desired attributes like writing style. By fine-tuning with these rubric-guided preferences, the LLM learns to modulate its outputs at inference time in response to the system prompt, without retraining. This approach not only offers fine-grained control but also provides a mechanism for modeling more nuanced and context-dependent human feedback. Several experimental artifacts, such as training code, generated datasets and fine-tuned models are released at https://github.com/vicgalle/configurable-preference-tuning
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.11702
• PDF: https://arxiv.org/pdf/2506.11702
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Configurable Preference Tuning with Rubric-Guided Synthetic Data
🔹 Publication Date: Published on Jun 13
🔹 Abstract:
Configurable Preference Tuning enables language models to dynamically adjust their behavior based on human-interprettable directives, using rubric-guided preference data for fine-tuning and inference-time modulation. AI-generated summary Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic preferences by introducing Configurable Preference Tuning (CPT), a novel framework for endowing language models with the ability to dynamically adjust their behavior based on explicit, human-interpretable directives. CPT leverages synthetically generated preference data, conditioned on system prompts derived from structured, fine-grained rubrics that define desired attributes like writing style. By fine-tuning with these rubric-guided preferences, the LLM learns to modulate its outputs at inference time in response to the system prompt, without retraining. This approach not only offers fine-grained control but also provides a mechanism for modeling more nuanced and context-dependent human feedback. Several experimental artifacts, such as training code, generated datasets and fine-tuned models are released at https://github.com/vicgalle/configurable-preference-tuning
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.11702
• PDF: https://arxiv.org/pdf/2506.11702
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
Configurable Preference Tuning with Rubric-Guided Synthetic Data
Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper...
❤1
🔹 Title:
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
🔹 Publication Date: Published on Mar 10
🔹 Abstract:
PLADIS leverages sparse attention in cross-attention layers to enhance pre-trained text-to-image diffusion models, improving text alignment and human preference without additional training. AI-generated summary Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing methods often require additional training or neural function evaluations (NFEs), making them incompatible with guidance-distilled models. Also, they rely on heuristic approaches that need identifying target layers. In this work, we propose a novel and efficient method, termed PLADIS , which boosts pre-trained models ( U-Net / Transformer ) by leveraging sparse attention. Specifically, we extrapolate query-key correlations using softmax and its sparse counterpart in the cross-attention layer during inference, without requiring extra training or NFEs. By leveraging the noise robustness of sparse attention , our PLADIS unleashes the latent potential of text-to-image diffusion models , enabling them to excel in areas where they once struggled with newfound effectiveness. It integrates seamlessly with guidance techniques, including guidance-distilled models . Extensive experiments show notable improvements in text alignment and human preference, offering a highly efficient and universally applicable solution.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2503.07677
• PDF: https://arxiv.org/pdf/2503.07677
• Github: https://cubeyoung.github.io/pladis-proejct/
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
🔹 Publication Date: Published on Mar 10
🔹 Abstract:
PLADIS leverages sparse attention in cross-attention layers to enhance pre-trained text-to-image diffusion models, improving text alignment and human preference without additional training. AI-generated summary Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing methods often require additional training or neural function evaluations (NFEs), making them incompatible with guidance-distilled models. Also, they rely on heuristic approaches that need identifying target layers. In this work, we propose a novel and efficient method, termed PLADIS , which boosts pre-trained models ( U-Net / Transformer ) by leveraging sparse attention. Specifically, we extrapolate query-key correlations using softmax and its sparse counterpart in the cross-attention layer during inference, without requiring extra training or NFEs. By leveraging the noise robustness of sparse attention , our PLADIS unleashes the latent potential of text-to-image diffusion models , enabling them to excel in areas where they once struggled with newfound effectiveness. It integrates seamlessly with guidance techniques, including guidance-distilled models . Extensive experiments show notable improvements in text alignment and human preference, offering a highly efficient and universally applicable solution.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2503.07677
• PDF: https://arxiv.org/pdf/2503.07677
• Github: https://cubeyoung.github.io/pladis-proejct/
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
PLADIS: Pushing the Limits of Attention in Diffusion Models at...
Diffusion models have shown impressive results in generating high-quality conditional samples using guidance techniques such as Classifier-Free Guidance (CFG). However, existing methods often...
❤1
Article Title:
Urban1960SatSeg: Unsupervised Semantic Segmentation of Mid-20$^{th}$ century Urban Landscapes with Satellite Imageries
Article Date: 11 Jun 2025
Article Description:
Historical satellite imagery, such as mid-20$^{th}$ century Keyhole data, offers rare insights into understanding early urban development and long-term transformation. However, severe quality degradation (e.g., distortion, misalignment, and spectral scarcity) and annotation absence have long hindered semantic segmentation on such historical RS imagery. To bridge this gap and enhance understanding of urban development, we introduce $\textbf{Urban1960SatBench}$, an annotated segmentation dataset based on historical satellite imagery with the earliest observation time among all existing segmentation datasets, along with a benchmark framework for unsupervised segmentation tasks, $\textbf{Urban1960SatUSM}$. First, $\textbf{Urban1960SatBench}$ serves as a novel, expertly annotated semantic segmentation dataset built on mid-20$^{th}$ century Keyhole imagery, covering 1,240 km$^2$ and key urban classes (buildings, roads, farmland, water). As the earliest segmentation dataset of its kind, it provides a pioneering benchmark for historical urban understanding. Second, $\textbf{Urban1960SatUSM}$(Unsupervised Segmentation Model) is a novel unsupervised semantic segmentation framework for historical RS imagery. It employs a confidence-aware alignment mechanism and focal-confidence loss based on a self-supervised learning architecture, which generates robust pseudo-labels and adaptively prioritizes prediction difficulty and label reliability to improve unsupervised segmentation on noisy historical data without manual supervision. Experiments show Urban1960SatUSM significantly outperforms existing unsupervised segmentation methods on Urban1960SatSeg for segmenting historical urban scenes, promising in paving the way for quantitative studies of long-term urban change using modern computer vision. Our benchmark and supplementary material are available at https://github.com/Tianxiang-Hao/Urban1960SatSeg.PDFAbstract
PDF Download Link:
https://arxiv.org/pdf/2506.09476v1.pdf
GitHub:
• https://github.com/tianxiang-hao/urban1960satseg
Datasets:
• No datasets information available
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Urban1960SatSeg: Unsupervised Semantic Segmentation of Mid-20$^{th}$ century Urban Landscapes with Satellite Imageries
Article Date: 11 Jun 2025
Article Description:
Historical satellite imagery, such as mid-20$^{th}$ century Keyhole data, offers rare insights into understanding early urban development and long-term transformation. However, severe quality degradation (e.g., distortion, misalignment, and spectral scarcity) and annotation absence have long hindered semantic segmentation on such historical RS imagery. To bridge this gap and enhance understanding of urban development, we introduce $\textbf{Urban1960SatBench}$, an annotated segmentation dataset based on historical satellite imagery with the earliest observation time among all existing segmentation datasets, along with a benchmark framework for unsupervised segmentation tasks, $\textbf{Urban1960SatUSM}$. First, $\textbf{Urban1960SatBench}$ serves as a novel, expertly annotated semantic segmentation dataset built on mid-20$^{th}$ century Keyhole imagery, covering 1,240 km$^2$ and key urban classes (buildings, roads, farmland, water). As the earliest segmentation dataset of its kind, it provides a pioneering benchmark for historical urban understanding. Second, $\textbf{Urban1960SatUSM}$(Unsupervised Segmentation Model) is a novel unsupervised semantic segmentation framework for historical RS imagery. It employs a confidence-aware alignment mechanism and focal-confidence loss based on a self-supervised learning architecture, which generates robust pseudo-labels and adaptively prioritizes prediction difficulty and label reliability to improve unsupervised segmentation on noisy historical data without manual supervision. Experiments show Urban1960SatUSM significantly outperforms existing unsupervised segmentation methods on Urban1960SatSeg for segmenting historical urban scenes, promising in paving the way for quantitative studies of long-term urban change using modern computer vision. Our benchmark and supplementary material are available at https://github.com/Tianxiang-Hao/Urban1960SatSeg.PDFAbstract
PDF Download Link:
https://arxiv.org/pdf/2506.09476v1.pdf
GitHub:
• https://github.com/tianxiang-hao/urban1960satseg
Datasets:
• No datasets information available
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤2
🔹 Title:
MMSearch-R1: Incentivizing LMMs to Search
🔹 Publication Date: Published on Jun 25
🔹 Abstract:
MMSearch-R1, a reinforcement learning framework, enables large multimodal models to perform efficient, on-demand, multi-turn search in real-world environments, outperforming existing approaches. AI-generated summary Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented generation (RAG) and prompt engineered search agents rely on rigid pipelines, often leading to inefficient or excessive search behaviors. We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables LMMs to perform on-demand, multi-turn search in real-world Internet environments. Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty . To support training, We collect a multimodal search VQA dataset through a semi-automated pipeline that covers diverse visual and textual knowledge needs and curate a search-balanced subset with both search-required and search-free samples, which proves essential for shaping efficient and on-demand search behavior. Extensive experiments on knowledge-intensive and info-seeking VQA tasks show that our model not only outperforms RAG-based baselines of the same model size, but also matches the performance of a larger RAG-based model while reducing search calls by over 30%. We further analyze key empirical findings to offer actionable insights for advancing research in multimodal search.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.20670
• PDF: https://arxiv.org/pdf/2506.20670
• Github: https://github.com/EvolvingLMMs-Lab/multimodal-search-r1
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
MMSearch-R1: Incentivizing LMMs to Search
🔹 Publication Date: Published on Jun 25
🔹 Abstract:
MMSearch-R1, a reinforcement learning framework, enables large multimodal models to perform efficient, on-demand, multi-turn search in real-world environments, outperforming existing approaches. AI-generated summary Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information. Existing approaches such as retrieval-augmented generation (RAG) and prompt engineered search agents rely on rigid pipelines, often leading to inefficient or excessive search behaviors. We present MMSearch-R1, the first end-to-end reinforcement learning framework that enables LMMs to perform on-demand, multi-turn search in real-world Internet environments. Our framework integrates both image and text search tools, allowing the model to reason about when and how to invoke them guided by an outcome-based reward with a search penalty . To support training, We collect a multimodal search VQA dataset through a semi-automated pipeline that covers diverse visual and textual knowledge needs and curate a search-balanced subset with both search-required and search-free samples, which proves essential for shaping efficient and on-demand search behavior. Extensive experiments on knowledge-intensive and info-seeking VQA tasks show that our model not only outperforms RAG-based baselines of the same model size, but also matches the performance of a larger RAG-based model while reducing search calls by over 30%. We further analyze key empirical findings to offer actionable insights for advancing research in multimodal search.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.20670
• PDF: https://arxiv.org/pdf/2506.20670
• Github: https://github.com/EvolvingLMMs-Lab/multimodal-search-r1
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
MMSearch-R1: Incentivizing LMMs to Search
Robust deployment of large multimodal models (LMMs) in real-world scenarios requires access to external knowledge sources, given the complexity and dynamic nature of real-world information....
❤1
🔹 Title:
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
Mind2Web 2 benchmark evaluates agentic search systems with a suite of realistic, long-horizon tasks, introducing an Agent-as-a-Judge framework to assess accuracy and source attribution. AI-generated summary Agentic search such as Deep Research systems , where large language models autonomously browse the web, synthesize information, and return comprehensive citation-backed answers , represents a major shift in how users interact with web-scale information. While promising greater efficiency and cognitive offloading, the growing complexity and open-endedness of agentic search have outpaced existing evaluation benchmarks and methodologies, which largely assume short search horizons and static answers . In this paper, we introduce Mind2Web 2, a benchmark of 130 realistic, high-quality, and long-horizon tasks that require real-time web browsing and extensive information synthesis , constructed with over 1,000 hours of human labor. To address the challenge of evaluating time-varying and complex answers, we propose a novel Agent-as-a-Judge framework. Our method constructs task-specific judge agents based on a tree-structured rubric design to automatically assess both answer correctness and source attribution . We conduct a comprehensive evaluation of nine frontier agentic search systems and human performance , along with a detailed error analysis to draw insights for future development. The best-performing system, OpenAI Deep Research , can already achieve 50-70% of human performance while spending half the time, showing a great potential. Altogether, Mind2Web 2 provides a rigorous foundation for developing and benchmarking the next generation of agentic search systems .
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21506
• PDF: https://arxiv.org/pdf/2506.21506
• Project Page: https://osu-nlp-group.github.io/Mind2Web-2
• Github: https://github.com/OSU-NLP-Group/Mind2Web-2/
🔹 Datasets citing this paper:
• https://huggingface.co/datasets/osunlp/Mind2Web-2
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
Mind2Web 2 benchmark evaluates agentic search systems with a suite of realistic, long-horizon tasks, introducing an Agent-as-a-Judge framework to assess accuracy and source attribution. AI-generated summary Agentic search such as Deep Research systems , where large language models autonomously browse the web, synthesize information, and return comprehensive citation-backed answers , represents a major shift in how users interact with web-scale information. While promising greater efficiency and cognitive offloading, the growing complexity and open-endedness of agentic search have outpaced existing evaluation benchmarks and methodologies, which largely assume short search horizons and static answers . In this paper, we introduce Mind2Web 2, a benchmark of 130 realistic, high-quality, and long-horizon tasks that require real-time web browsing and extensive information synthesis , constructed with over 1,000 hours of human labor. To address the challenge of evaluating time-varying and complex answers, we propose a novel Agent-as-a-Judge framework. Our method constructs task-specific judge agents based on a tree-structured rubric design to automatically assess both answer correctness and source attribution . We conduct a comprehensive evaluation of nine frontier agentic search systems and human performance , along with a detailed error analysis to draw insights for future development. The best-performing system, OpenAI Deep Research , can already achieve 50-70% of human performance while spending half the time, showing a great potential. Altogether, Mind2Web 2 provides a rigorous foundation for developing and benchmarking the next generation of agentic search systems .
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21506
• PDF: https://arxiv.org/pdf/2506.21506
• Project Page: https://osu-nlp-group.github.io/Mind2Web-2
• Github: https://github.com/OSU-NLP-Group/Mind2Web-2/
🔹 Datasets citing this paper:
• https://huggingface.co/datasets/osunlp/Mind2Web-2
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
Agentic search such as Deep Research systems-where agents autonomously browse the web, synthesize information, and return comprehensive citation-backed answers-represents a major shift in how...
❤1
🔹 Title:
Intelligent Operation and Maintenance and Prediction Model Optimization for Improving Wind Power Generation Efficiency
🔹 Publication Date: Published on Jun 19
🔹 Abstract:
This study explores the effectiveness of predictive maintenance models and the optimization of intelligent Operation and Maintenance (O&M) systems in improving wind power generation efficiency. Through qualitative research, structured interviews were conducted with five wind farm engineers and maintenance managers, each with extensive experience in turbine operations. Using thematic analysis, the study revealed that while predictive maintenance models effectively reduce downtime by identifying major faults, they often struggle with detecting smaller, gradual failures. Key challenges identified include false positives, sensor malfunctions, and difficulties in integrating new models with older turbine systems. Advanced technologies such as digital twins, SCADA systems, and condition monitoring have significantly enhanced turbine maintenance practices. However, these technologies still require improvements, particularly in AI refinement and real-time data integration. The findings emphasize the need for continuous development to fully optimize wind turbine performance and support the broader adoption of renewable energy.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.16095
• PDF: https://arxiv.org/pdf/2506.16095
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Intelligent Operation and Maintenance and Prediction Model Optimization for Improving Wind Power Generation Efficiency
🔹 Publication Date: Published on Jun 19
🔹 Abstract:
This study explores the effectiveness of predictive maintenance models and the optimization of intelligent Operation and Maintenance (O&M) systems in improving wind power generation efficiency. Through qualitative research, structured interviews were conducted with five wind farm engineers and maintenance managers, each with extensive experience in turbine operations. Using thematic analysis, the study revealed that while predictive maintenance models effectively reduce downtime by identifying major faults, they often struggle with detecting smaller, gradual failures. Key challenges identified include false positives, sensor malfunctions, and difficulties in integrating new models with older turbine systems. Advanced technologies such as digital twins, SCADA systems, and condition monitoring have significantly enhanced turbine maintenance practices. However, these technologies still require improvements, particularly in AI refinement and real-time data integration. The findings emphasize the need for continuous development to fully optimize wind turbine performance and support the broader adoption of renewable energy.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.16095
• PDF: https://arxiv.org/pdf/2506.16095
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤2
🔹 Title:
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
🔹 Publication Date: Published on Jun 25
🔹 Abstract:
HiWave enhances ultra-high-resolution image synthesis using pretrained diffusion models through a two-stage pipeline involving DDIM inversion and wavelet-based detail enhancement, improving visual fidelity and reducing artifacts. AI-generated summary Diffusion models have emerged as the leading approach for image synthesis , demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing zero-shot generation techniques for synthesizing images beyond training resolutions often produce artifacts , including object duplication and spatial incoherence . In this paper, we introduce HiWave, a training-free, zero-shot approach that substantially enhances visual fidelity and structural coherence in ultra-high-resolution image synthesis using pretrained diffusion models. Our method employs a two-stage pipeline : generating a base image from the pretrained model followed by a patch-wise DDIM inversion step and a novel wavelet-based detail enhancer module. Specifically, we first utilize inversion methods to derive initial noise vectors that preserve global coherence from the base image. Subsequently, during sampling, our wavelet-domain detail enhancer retains low-frequency components from the base image to ensure structural consistency, while selectively guiding high-frequency components to enrich fine details and textures . Extensive evaluations using Stable Diffusion XL demonstrate that HiWave effectively mitigates common visual artifacts seen in prior methods, achieving superior perceptual quality . A user study confirmed HiWave's performance, where it was preferred over the state-of-the-art alternative in more than 80% of comparisons, highlighting its effectiveness for high-quality, ultra-high-resolution image synthesis without requiring retraining or architectural modifications.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.20452
• PDF: https://arxiv.org/pdf/2506.20452
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
🔹 Publication Date: Published on Jun 25
🔹 Abstract:
HiWave enhances ultra-high-resolution image synthesis using pretrained diffusion models through a two-stage pipeline involving DDIM inversion and wavelet-based detail enhancement, improving visual fidelity and reducing artifacts. AI-generated summary Diffusion models have emerged as the leading approach for image synthesis , demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing zero-shot generation techniques for synthesizing images beyond training resolutions often produce artifacts , including object duplication and spatial incoherence . In this paper, we introduce HiWave, a training-free, zero-shot approach that substantially enhances visual fidelity and structural coherence in ultra-high-resolution image synthesis using pretrained diffusion models. Our method employs a two-stage pipeline : generating a base image from the pretrained model followed by a patch-wise DDIM inversion step and a novel wavelet-based detail enhancer module. Specifically, we first utilize inversion methods to derive initial noise vectors that preserve global coherence from the base image. Subsequently, during sampling, our wavelet-domain detail enhancer retains low-frequency components from the base image to ensure structural consistency, while selectively guiding high-frequency components to enrich fine details and textures . Extensive evaluations using Stable Diffusion XL demonstrate that HiWave effectively mitigates common visual artifacts seen in prior methods, achieving superior perceptual quality . A user study confirmed HiWave's performance, where it was preferred over the state-of-the-art alternative in more than 80% of comparisons, highlighting its effectiveness for high-quality, ultra-high-resolution image synthesis without requiring retraining or architectural modifications.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.20452
• PDF: https://arxiv.org/pdf/2506.20452
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤🔥1
🔹 Title:
Resa: Transparent Reasoning Models via SAEs
🔹 Publication Date: Published on Jun 11
🔹 Abstract:
SAE-Tuning efficiently elicits strong reasoning in language models by leveraging sparse autoencoders, enabling cost-effective performance gains without extensive retraining. AI-generated summary How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained via a novel and efficient sparse autoencoder tuning ( SAE-Tuning ) procedure. This method first trains an SAE to capture reasoning abilities from a source model, and then uses the trained SAE to guide a standard supervised fine-tuning process to elicit such abilities in a target model, all using verified question-answer data without any reasoning traces. Notably, when applied to certain base models before further RL post-training, SAE-Tuning retains >97% of its RL-trained counterpart's reasoning performance while reducing training costs by >2000x to roughly \1 and training time by >450x to around 20 minutes. Furthermore, when applied to lightly RL-trained models (e.g., within 1 hour on 2 GPUs), it enables reasoning performance such as 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23 for only around 1 additional cost. Surprisingly, the reasoning abilities extracted via SAEs are potentially both generalizable and modular. Generality means abilities extracted from one dataset still elevate performance on a larger and overlapping corpus. Modularity means abilities extracted from Qwen or Qwen-Math can be attached to the R1-Distill model at test time, without any retraining, and yield comparable gains. Extensive ablations validate these findings and all artifacts are fully open-sourced.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.09967
• PDF: https://arxiv.org/pdf/2506.09967
• Project Page: https://shangshangwang.notion.site/resa
• Github: https://github.com/shangshang-wang/Resa
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Resa: Transparent Reasoning Models via SAEs
🔹 Publication Date: Published on Jun 11
🔹 Abstract:
SAE-Tuning efficiently elicits strong reasoning in language models by leveraging sparse autoencoders, enabling cost-effective performance gains without extensive retraining. AI-generated summary How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained via a novel and efficient sparse autoencoder tuning ( SAE-Tuning ) procedure. This method first trains an SAE to capture reasoning abilities from a source model, and then uses the trained SAE to guide a standard supervised fine-tuning process to elicit such abilities in a target model, all using verified question-answer data without any reasoning traces. Notably, when applied to certain base models before further RL post-training, SAE-Tuning retains >97% of its RL-trained counterpart's reasoning performance while reducing training costs by >2000x to roughly \1 and training time by >450x to around 20 minutes. Furthermore, when applied to lightly RL-trained models (e.g., within 1 hour on 2 GPUs), it enables reasoning performance such as 43.33% Pass@1 on AIME24 and 90% Pass@1 on AMC23 for only around 1 additional cost. Surprisingly, the reasoning abilities extracted via SAEs are potentially both generalizable and modular. Generality means abilities extracted from one dataset still elevate performance on a larger and overlapping corpus. Modularity means abilities extracted from Qwen or Qwen-Math can be attached to the R1-Distill model at test time, without any retraining, and yield comparable gains. Extensive ablations validate these findings and all artifacts are fully open-sourced.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.09967
• PDF: https://arxiv.org/pdf/2506.09967
• Project Page: https://shangshangwang.notion.site/resa
• Github: https://github.com/shangshang-wang/Resa
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
Resa: Transparent Reasoning Models via SAEs
How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning models trained...
❤1
🔹 Title:
WorldVLA: Towards Autoregressive Action World Model
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
WorldVLA, an autoregressive action world model integrating vision-language-action (VLA) and world models, enhances performance through mutual understanding and generation, improving action prediction and sequence generation with an attention mask strategy. AI-generated summary We present WorldVLA, an autoregressive action world model that unifies action and image understanding and generation. Our WorldVLA intergrates Vision-Language-Action (VLA) model and world model in one single framework. The world model predicts future images by leveraging both action and image understanding, with the purpose of learning the underlying physics of the environment to improve action generation . Meanwhile, the action model generates the subsequent actions based on image observations, aiding in visual understanding and in turn helps visual generation of the world model . We demonstrate that WorldVLA outperforms standalone action and world model s, highlighting the mutual enhancement between the world model and the action model. In addition, we find that the performance of the action model deteriorates when generating sequences of actions in an autoregressive manner. This phenomenon can be attributed to the model's limited generalization capability for action prediction , leading to the propagation of errors from earlier actions to subsequent ones. To address this issue, we propose an attention mask strategy that selectively masks prior actions during the generation of the current action, which shows significant performance improvement in the action chunk generation task.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21539
• PDF: https://arxiv.org/pdf/2506.21539
• Project Page: https://github.com/alibaba-damo-academy/WorldVLA
• Github: https://github.com/alibaba-damo-academy/WorldVLA
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
WorldVLA: Towards Autoregressive Action World Model
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
WorldVLA, an autoregressive action world model integrating vision-language-action (VLA) and world models, enhances performance through mutual understanding and generation, improving action prediction and sequence generation with an attention mask strategy. AI-generated summary We present WorldVLA, an autoregressive action world model that unifies action and image understanding and generation. Our WorldVLA intergrates Vision-Language-Action (VLA) model and world model in one single framework. The world model predicts future images by leveraging both action and image understanding, with the purpose of learning the underlying physics of the environment to improve action generation . Meanwhile, the action model generates the subsequent actions based on image observations, aiding in visual understanding and in turn helps visual generation of the world model . We demonstrate that WorldVLA outperforms standalone action and world model s, highlighting the mutual enhancement between the world model and the action model. In addition, we find that the performance of the action model deteriorates when generating sequences of actions in an autoregressive manner. This phenomenon can be attributed to the model's limited generalization capability for action prediction , leading to the propagation of errors from earlier actions to subsequent ones. To address this issue, we propose an attention mask strategy that selectively masks prior actions during the generation of the current action, which shows significant performance improvement in the action chunk generation task.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21539
• PDF: https://arxiv.org/pdf/2506.21539
• Project Page: https://github.com/alibaba-damo-academy/WorldVLA
• Github: https://github.com/alibaba-damo-academy/WorldVLA
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤2
🔹 Title:
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
🔹 Publication Date: Published on Jun 18
🔹 Abstract:
HeurAgenix, a two-stage hyper-heuristic framework using large language models, evolves and selects heuristics dynamically for combinatorial optimization problems, achieving performance on par with specialized solvers. AI-generated summary Heuristic algorithms play a vital role in solving combinatorial optimization (CO) problems, yet traditional designs depend heavily on manual expertise and struggle to generalize across diverse instances. We introduce HeurAgenix, a two-stage hyper-heuristic framework powered by large language models (LLMs) that first evolves heuristics and then selects among them automatically. In the heuristic evolution phase, HeurAgenix leverages an LLM to compare seed heuristic solutions with higher-quality solutions and extract reusable evolution strategies. During problem solving, it dynamically picks the most promising heuristic for each problem state, guided by the LLM's perception ability. For flexibility, this selector can be either a state-of-the-art LLM or a fine-tuned lightweight model with lower inference cost. To mitigate the scarcity of reliable supervision caused by CO complexity, we fine-tune the lightweight heuristic selector with a dual-reward mechanism that jointly exploits singals from selection preferences and state perception , enabling robust selection under noisy annotations. Extensive experiments on canonical benchmarks show that HeurAgenix not only outperforms existing LLM-based hyper-heuristics but also matches or exceeds specialized solvers. Code is available at https://github.com/microsoft/HeurAgenix.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.15196
• PDF: https://arxiv.org/pdf/2506.15196
• Project Page: https://github.com/microsoft/HeurAgenix
• Github: https://github.com/microsoft/HeurAgenix
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
🔹 Publication Date: Published on Jun 18
🔹 Abstract:
HeurAgenix, a two-stage hyper-heuristic framework using large language models, evolves and selects heuristics dynamically for combinatorial optimization problems, achieving performance on par with specialized solvers. AI-generated summary Heuristic algorithms play a vital role in solving combinatorial optimization (CO) problems, yet traditional designs depend heavily on manual expertise and struggle to generalize across diverse instances. We introduce HeurAgenix, a two-stage hyper-heuristic framework powered by large language models (LLMs) that first evolves heuristics and then selects among them automatically. In the heuristic evolution phase, HeurAgenix leverages an LLM to compare seed heuristic solutions with higher-quality solutions and extract reusable evolution strategies. During problem solving, it dynamically picks the most promising heuristic for each problem state, guided by the LLM's perception ability. For flexibility, this selector can be either a state-of-the-art LLM or a fine-tuned lightweight model with lower inference cost. To mitigate the scarcity of reliable supervision caused by CO complexity, we fine-tune the lightweight heuristic selector with a dual-reward mechanism that jointly exploits singals from selection preferences and state perception , enabling robust selection under noisy annotations. Extensive experiments on canonical benchmarks show that HeurAgenix not only outperforms existing LLM-based hyper-heuristics but also matches or exceeds specialized solvers. Code is available at https://github.com/microsoft/HeurAgenix.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.15196
• PDF: https://arxiv.org/pdf/2506.15196
• Project Page: https://github.com/microsoft/HeurAgenix
• Github: https://github.com/microsoft/HeurAgenix
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤2
🔹 Title:
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
🔹 Publication Date: Published on Jun 24
🔹 Abstract:
An automated data-curation pipeline for software engineering improves large language model performance on SWE tasks, achieving state-of-the-art results with and without test-time scaling techniques. AI-generated summary Software engineering (SWE) has recently emerged as a crucial testbed for next-generation LLM agents , demanding inherent capabilities in two critical dimensions: sustained iterative problem-solving (e.g., >50 interaction rounds) and long-context dependency resolution (e.g., >32k tokens). However, the data curation process in SWE remains notoriously time-consuming, as it heavily relies on manual annotation for code file filtering and the setup of dedicated runtime environments to execute and validate unit tests . Consequently, most existing datasets are limited to only a few thousand GitHub-sourced instances. To this end, we propose an incremental, automated data-curation pipeline that systematically scales both the volume and diversity of SWE datasets. Our dataset comprises 10,169 real-world Python task instances from 2,531 distinct GitHub repositories, each accompanied by a task specified in natural language and a dedicated runtime-environment image for automated unit-test validation. We have carefully curated over 8,000 successfully runtime-validated training trajectories from our proposed SWE dataset. When fine-tuning the Skywork-SWE model on these trajectories, we uncover a striking data scaling phenomenon: the trained model's performance for software engineering capabilities in LLMs continues to improve as the data size increases, showing no signs of saturation. Notably, our Skywork-SWE model achieves 38.0% pass@1 accuracy on the SWE-bench Verified benchmark without using verifiers or multiple rollouts, establishing a new state-of-the-art (SOTA) among the Qwen2.5-Coder-32B-based LLMs built on the OpenHands agent framework . Furthermore, with the incorporation of test-time scaling techniques , the performance further improves to 47.0% accuracy, surpassing the previous SOTA results for sub-32B parameter models. We release the Skywork-SWE-32B model checkpoint to accelerate future research.
🔹 Links:
• arXiv Page: https://arxiv.org/pdf/2506.19290
• PDF: https://arxiv.org/pdf/2506.19290
• Project Page: https://quixotic-sting-239.notion.site/eb17f379610040ceb54da5d5d24065bd
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
🔹 Publication Date: Published on Jun 24
🔹 Abstract:
An automated data-curation pipeline for software engineering improves large language model performance on SWE tasks, achieving state-of-the-art results with and without test-time scaling techniques. AI-generated summary Software engineering (SWE) has recently emerged as a crucial testbed for next-generation LLM agents , demanding inherent capabilities in two critical dimensions: sustained iterative problem-solving (e.g., >50 interaction rounds) and long-context dependency resolution (e.g., >32k tokens). However, the data curation process in SWE remains notoriously time-consuming, as it heavily relies on manual annotation for code file filtering and the setup of dedicated runtime environments to execute and validate unit tests . Consequently, most existing datasets are limited to only a few thousand GitHub-sourced instances. To this end, we propose an incremental, automated data-curation pipeline that systematically scales both the volume and diversity of SWE datasets. Our dataset comprises 10,169 real-world Python task instances from 2,531 distinct GitHub repositories, each accompanied by a task specified in natural language and a dedicated runtime-environment image for automated unit-test validation. We have carefully curated over 8,000 successfully runtime-validated training trajectories from our proposed SWE dataset. When fine-tuning the Skywork-SWE model on these trajectories, we uncover a striking data scaling phenomenon: the trained model's performance for software engineering capabilities in LLMs continues to improve as the data size increases, showing no signs of saturation. Notably, our Skywork-SWE model achieves 38.0% pass@1 accuracy on the SWE-bench Verified benchmark without using verifiers or multiple rollouts, establishing a new state-of-the-art (SOTA) among the Qwen2.5-Coder-32B-based LLMs built on the OpenHands agent framework . Furthermore, with the incorporation of test-time scaling techniques , the performance further improves to 47.0% accuracy, surpassing the previous SOTA results for sub-32B parameter models. We release the Skywork-SWE-32B model checkpoint to accelerate future research.
🔹 Links:
• arXiv Page: https://arxiv.org/pdf/2506.19290
• PDF: https://arxiv.org/pdf/2506.19290
• Project Page: https://quixotic-sting-239.notion.site/eb17f379610040ceb54da5d5d24065bd
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤2
🔹 Title:
MADrive: Memory-Augmented Driving Scene Modeling
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
MADrive enhances scene reconstruction for autonomous driving by integrating visually similar 3D car assets from an external memory bank to achieve photorealistic synthesis of altered scenarios. AI-generated summary Recent advances in scene reconstruction have pushed toward highly realistic modeling of autonomous driving (AD) environments using 3D Gaussian splatting . However, the resulting reconstructions remain closely tied to the original observations and struggle to support photorealistic synthesis of significantly altered or novel driving scenarios. This work introduces MADrive , a memory-augmented reconstruction framework designed to extend the capabilities of existing scene reconstruction methods by replacing observed vehicles with visually similar 3D assets retrieved from a large-scale external memory bank. Specifically, we release MAD-Cars , a curated dataset of {sim}70K 360{\deg} car videos captured in the wild and present a retrieval module that finds the most similar car instances in the memory bank, reconstructs the corresponding 3D assets from video, and integrates them into the target scene through orientation alignment and relighting . The resulting replacements provide complete multi-view representations of vehicles in the scene, enabling photorealistic synthesis of substantially altered configurations, as demonstrated in our experiments. Project page: https://yandex-research.github.io/ madrive /
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21520
• PDF: https://arxiv.org/pdf/2506.21520
• Project Page: https://yandex-research.github.io/madrive/
🔹 Datasets citing this paper:
• https://huggingface.co/datasets/yandex/mad-cars
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
MADrive: Memory-Augmented Driving Scene Modeling
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
MADrive enhances scene reconstruction for autonomous driving by integrating visually similar 3D car assets from an external memory bank to achieve photorealistic synthesis of altered scenarios. AI-generated summary Recent advances in scene reconstruction have pushed toward highly realistic modeling of autonomous driving (AD) environments using 3D Gaussian splatting . However, the resulting reconstructions remain closely tied to the original observations and struggle to support photorealistic synthesis of significantly altered or novel driving scenarios. This work introduces MADrive , a memory-augmented reconstruction framework designed to extend the capabilities of existing scene reconstruction methods by replacing observed vehicles with visually similar 3D assets retrieved from a large-scale external memory bank. Specifically, we release MAD-Cars , a curated dataset of {sim}70K 360{\deg} car videos captured in the wild and present a retrieval module that finds the most similar car instances in the memory bank, reconstructs the corresponding 3D assets from video, and integrates them into the target scene through orientation alignment and relighting . The resulting replacements provide complete multi-view representations of vehicles in the scene, enabling photorealistic synthesis of substantially altered configurations, as demonstrated in our experiments. Project page: https://yandex-research.github.io/ madrive /
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21520
• PDF: https://arxiv.org/pdf/2506.21520
• Project Page: https://yandex-research.github.io/madrive/
🔹 Datasets citing this paper:
• https://huggingface.co/datasets/yandex/mad-cars
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
MADrive: Memory-Augmented Driving Scene Modeling
Recent advances in scene reconstruction have pushed toward highly realistic modeling of autonomous driving (AD) environments using 3D Gaussian splatting. However, the resulting reconstructions...
❤3
🔹 Title:
Generative Blocks World: Moving Things Around in Pictures
🔹 Publication Date: Published on Jun 25
🔹 Abstract:
A generative method that edits 3D scenes using convex primitives and regenerates images with enhanced texture consistency and visual fidelity. AI-generated summary We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of convex 3D primitives , and the same scene can be represented by different numbers of primitives, allowing an editor to move either whole structures or small details. Once the scene geometry has been edited, the image is generated by a flow-based method which is conditioned on depth and a texture hint . Our texture hint takes into account the modified 3D primitives, exceeding texture-consistency provided by existing key-value caching techniques. These texture hint s (a) allow accurate object and camera moves and (b) largely preserve the identity of objects depicted. Quantitative and qualitative experiments demonstrate that our approach outperforms prior works in visual fidelity , editability , and compositional generalization .
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.20703
• PDF: https://arxiv.org/pdf/2506.20703
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Generative Blocks World: Moving Things Around in Pictures
🔹 Publication Date: Published on Jun 25
🔹 Abstract:
A generative method that edits 3D scenes using convex primitives and regenerates images with enhanced texture consistency and visual fidelity. AI-generated summary We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of convex 3D primitives , and the same scene can be represented by different numbers of primitives, allowing an editor to move either whole structures or small details. Once the scene geometry has been edited, the image is generated by a flow-based method which is conditioned on depth and a texture hint . Our texture hint takes into account the modified 3D primitives, exceeding texture-consistency provided by existing key-value caching techniques. These texture hint s (a) allow accurate object and camera moves and (b) largely preserve the identity of objects depicted. Quantitative and qualitative experiments demonstrate that our approach outperforms prior works in visual fidelity , editability , and compositional generalization .
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.20703
• PDF: https://arxiv.org/pdf/2506.20703
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤3
🔹 Title:
SAM4D: Segment Anything in Camera and LiDAR Streams
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
SAM4D is a multi-modal and temporal foundation model for segmentation in autonomous driving using Unified Multi-modal Positional Encoding and Motion-aware Cross-modal Memory Attention, with a multi-modal automated data engine generating pseudo-labels. AI-generated summary We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space , enabling seamless cross-modal prompting and interaction. Additionally, we propose Motion-aware Cross-modal Memory Attention (MCMA), which leverages ego-motion compensation to enhance temporal consistency and long-horizon feature retrieval, ensuring robust segmentation across dynamically changing autonomous driving scenes. To avoid annotation bottlenecks, we develop a multi-modal automated data engine that synergizes VFM-driven video masklets, spatiotemporal 4D reconstruction , and cross-modal masklet fusion . This framework generates camera - LiDAR aligned pseudo-labels at a speed orders of magnitude faster than human annotation while preserving VFM-derived semantic fidelity in point cloud representations. We conduct extensive experiments on the constructed Waymo-4DSeg , which demonstrate the powerful cross-modal segmentation ability and great potential in data annotation of proposed SAM4D.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21547
• PDF: https://arxiv.org/pdf/2506.21547
• Project Page: https://SAM4D-Project.github.io
• Github: https://github.com/CN-ADLab/SAM4D
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
SAM4D: Segment Anything in Camera and LiDAR Streams
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
SAM4D is a multi-modal and temporal foundation model for segmentation in autonomous driving using Unified Multi-modal Positional Encoding and Motion-aware Cross-modal Memory Attention, with a multi-modal automated data engine generating pseudo-labels. AI-generated summary We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space , enabling seamless cross-modal prompting and interaction. Additionally, we propose Motion-aware Cross-modal Memory Attention (MCMA), which leverages ego-motion compensation to enhance temporal consistency and long-horizon feature retrieval, ensuring robust segmentation across dynamically changing autonomous driving scenes. To avoid annotation bottlenecks, we develop a multi-modal automated data engine that synergizes VFM-driven video masklets, spatiotemporal 4D reconstruction , and cross-modal masklet fusion . This framework generates camera - LiDAR aligned pseudo-labels at a speed orders of magnitude faster than human annotation while preserving VFM-derived semantic fidelity in point cloud representations. We conduct extensive experiments on the constructed Waymo-4DSeg , which demonstrate the powerful cross-modal segmentation ability and great potential in data annotation of proposed SAM4D.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21547
• PDF: https://arxiv.org/pdf/2506.21547
• Project Page: https://SAM4D-Project.github.io
• Github: https://github.com/CN-ADLab/SAM4D
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
SAM4D: Segment Anything in Camera and LiDAR Streams
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to...
❤2
🔹 Title:
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
🔹 Publication Date: Published on Jun 13
🔹 Abstract:
A diffusion-based framework generates aligned novel views of images and geometry using warping-and-inpainting with cross-modal attention distillation and proximity-based mesh conditioning, achieving high-fidelity synthesis and 3D completion. AI-generated summary We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models limited to in-domain views, our method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images, and formulates novel-view synthesis as an inpainting task for both image and geometry. To ensure accurate alignment between generated images and geometry, we propose cross-modal attention distillation , where attention maps from the image diffusion branch are injected into a parallel geometry diffusion branch during both training and inference. This multi-task approach achieves synergistic effects, facilitating geometrically robust image synthesis as well as well-defined geometry prediction . We further introduce proximity-based mesh conditioning to integrate depth and normal cues, interpolating between point cloud and filtering erroneously predicted geometry from influencing the generation process. Empirically, our method achieves high-fidelity extrapolative view synthesis on both image and geometry across a range of unseen scenes, delivers competitive reconstruction quality under interpolation settings, and produces geometrically aligned colored point clouds for comprehensive 3D completion . Project page is available at https://cvlab-kaist.github.io/MoAI.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.11924
• PDF: https://arxiv.org/pdf/2506.11924
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
🔹 Publication Date: Published on Jun 13
🔹 Abstract:
A diffusion-based framework generates aligned novel views of images and geometry using warping-and-inpainting with cross-modal attention distillation and proximity-based mesh conditioning, achieving high-fidelity synthesis and 3D completion. AI-generated summary We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models limited to in-domain views, our method leverages off-the-shelf geometry predictors to predict partial geometries viewed from reference images, and formulates novel-view synthesis as an inpainting task for both image and geometry. To ensure accurate alignment between generated images and geometry, we propose cross-modal attention distillation , where attention maps from the image diffusion branch are injected into a parallel geometry diffusion branch during both training and inference. This multi-task approach achieves synergistic effects, facilitating geometrically robust image synthesis as well as well-defined geometry prediction . We further introduce proximity-based mesh conditioning to integrate depth and normal cues, interpolating between point cloud and filtering erroneously predicted geometry from influencing the generation process. Empirically, our method achieves high-fidelity extrapolative view synthesis on both image and geometry across a range of unseen scenes, delivers competitive reconstruction quality under interpolation settings, and produces geometrically aligned colored point clouds for comprehensive 3D completion . Project page is available at https://cvlab-kaist.github.io/MoAI.
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.11924
• PDF: https://arxiv.org/pdf/2506.11924
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤1
🔹 Title:
FairyGen: Storied Cartoon Video from a Single Child-Drawn Character
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
FairyGen generates story-driven cartoon videos from a single drawing by disentangling character modeling and background styling, employing MLLM for storyboards, style propagation for consistency, and MMDiT-based diffusion models for motion. AI-generated summary We propose FairyGen, an automatic system for generating story-driven cartoon videos from a single child's drawing, while faithfully preserving its unique artistic style. Unlike previous storytelling methods that primarily focus on character consistency and basic motion, FairyGen explicitly disentangles character modeling from stylized background generation and incorporates cinematic shot design to support expressive and coherent storytelling. Given a single character sketch, we first employ an MLLM to generate a structured storyboard with shot-level descriptions that specify environment settings, character actions, and camera perspectives. To ensure visual consistency, we introduce a style propagation adapter that captures the character's visual style and applies it to the background, faithfully retaining the character's full visual identity while synthesizing style-consistent scenes. A shot design module further enhances visual diversity and cinematic quality through frame cropping and multi-view synthesis based on the storyboard . To animate the story, we reconstruct a 3D proxy of the character to derive physically plausible motion sequences, which are then used to fine-tune an MMDiT-based image-to-video diffusion model. We further propose a two-stage motion customization adapter: the first stage learns appearance features from temporally unordered frames, disentangling identity from motion; the second stage models temporal dynamics using a timestep-shift strategy with frozen identity weights. Once trained, FairyGen directly renders diverse and coherent video scenes aligned with the storyboard . Extensive experiments demonstrate that our system produces animations that are stylistically faithful, narratively structured natural motion, highlighting its potential for personalized and engaging story animation. The code will be available at https://github.com/GVCLab/FairyGen
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21272
• PDF: https://arxiv.org/pdf/2506.21272
• Project Page: https://jayleejia.github.io/FairyGen/
• Github: https://github.com/GVCLab/FairyGen
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
FairyGen: Storied Cartoon Video from a Single Child-Drawn Character
🔹 Publication Date: Published on Jun 26
🔹 Abstract:
FairyGen generates story-driven cartoon videos from a single drawing by disentangling character modeling and background styling, employing MLLM for storyboards, style propagation for consistency, and MMDiT-based diffusion models for motion. AI-generated summary We propose FairyGen, an automatic system for generating story-driven cartoon videos from a single child's drawing, while faithfully preserving its unique artistic style. Unlike previous storytelling methods that primarily focus on character consistency and basic motion, FairyGen explicitly disentangles character modeling from stylized background generation and incorporates cinematic shot design to support expressive and coherent storytelling. Given a single character sketch, we first employ an MLLM to generate a structured storyboard with shot-level descriptions that specify environment settings, character actions, and camera perspectives. To ensure visual consistency, we introduce a style propagation adapter that captures the character's visual style and applies it to the background, faithfully retaining the character's full visual identity while synthesizing style-consistent scenes. A shot design module further enhances visual diversity and cinematic quality through frame cropping and multi-view synthesis based on the storyboard . To animate the story, we reconstruct a 3D proxy of the character to derive physically plausible motion sequences, which are then used to fine-tune an MMDiT-based image-to-video diffusion model. We further propose a two-stage motion customization adapter: the first stage learns appearance features from temporally unordered frames, disentangling identity from motion; the second stage models temporal dynamics using a timestep-shift strategy with frozen identity weights. Once trained, FairyGen directly renders diverse and coherent video scenes aligned with the storyboard . Extensive experiments demonstrate that our system produces animations that are stylistically faithful, narratively structured natural motion, highlighting its potential for personalized and engaging story animation. The code will be available at https://github.com/GVCLab/FairyGen
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.21272
• PDF: https://arxiv.org/pdf/2506.21272
• Project Page: https://jayleejia.github.io/FairyGen/
• Github: https://github.com/GVCLab/FairyGen
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
❤2
🔹 Title:
Seedance 1.0: Exploring the Boundaries of Video Generation Models
🔹 Publication Date: Published on Jun 10
🔹 Abstract:
Seedance 1.0 offers high-performance video generation by integrating advanced data curation, efficient architecture, post-training optimization, and model acceleration, resulting in superior quality and speed. AI-generated summary Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously balancing prompt following, motion plausibility, and visual quality. In this report, we introduce Seedance 1.0, a high-performance and inference-efficient video foundation generation model that integrates several core technical improvements: (i) multi-source data curation augmented with precision and meaningful video captioning , enabling comprehensive learning across diverse scenarios; (ii) an efficient architecture design with proposed training paradigm , which allows for natively supporting multi-shot generation and jointly learning of both text-to-video and image-to-video tasks. (iii) carefully-optimized post-training approaches leveraging fine-grained supervised fine-tuning , and video-specific RLHF with multi-dimensional reward mechanisms for comprehensive performance improvements; (iv) excellent model acceleration achieving ~10x inference speedup through multi-stage distillation strategies and system-level optimizations. Seedance 1.0 can generate a 5-second video at 1080p resolution only with 41.4 seconds (NVIDIA-L20). Compared to state-of-the-art video generation models, Seedance 1.0 stands out with high-quality and fast video generation having superior spatiotemporal fluidity with structural stability , precise instruction adherence in complex multi-subject contexts, native multi-shot narrative coherence with consistent subject representation .
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.09113
• PDF: https://arxiv.org/pdf/2506.09113
• Project Page: https://seed.bytedance.com/seedance
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
Seedance 1.0: Exploring the Boundaries of Video Generation Models
🔹 Publication Date: Published on Jun 10
🔹 Abstract:
Seedance 1.0 offers high-performance video generation by integrating advanced data curation, efficient architecture, post-training optimization, and model acceleration, resulting in superior quality and speed. AI-generated summary Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously balancing prompt following, motion plausibility, and visual quality. In this report, we introduce Seedance 1.0, a high-performance and inference-efficient video foundation generation model that integrates several core technical improvements: (i) multi-source data curation augmented with precision and meaningful video captioning , enabling comprehensive learning across diverse scenarios; (ii) an efficient architecture design with proposed training paradigm , which allows for natively supporting multi-shot generation and jointly learning of both text-to-video and image-to-video tasks. (iii) carefully-optimized post-training approaches leveraging fine-grained supervised fine-tuning , and video-specific RLHF with multi-dimensional reward mechanisms for comprehensive performance improvements; (iv) excellent model acceleration achieving ~10x inference speedup through multi-stage distillation strategies and system-level optimizations. Seedance 1.0 can generate a 5-second video at 1080p resolution only with 41.4 seconds (NVIDIA-L20). Compared to state-of-the-art video generation models, Seedance 1.0 stands out with high-quality and fast video generation having superior spatiotemporal fluidity with structural stability , precise instruction adherence in complex multi-subject contexts, native multi-shot narrative coherence with consistent subject representation .
🔹 Links:
• arXiv Page: https://arxiv.org/abs/2506.09113
• PDF: https://arxiv.org/pdf/2506.09113
• Project Page: https://seed.bytedance.com/seedance
🔹 Datasets citing this paper:
No datasets found
🔹 Spaces citing this paper:
No spaces found
==================================
For more data science resources:
✓ https://t.iss.one/DataScienceT
arXiv.org
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously balancing prompt...
❤2