🔹 Title: PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts

🔹 Publication Date: Published on Aug 13

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.09848
• PDF: https://arxiv.org/pdf/2508.09848
• Project Page: https://gorov.github.io/prelude
• Github: https://gorov.github.io/prelude/leaderboard.html

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/ttchungc/PRELUDE

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: From Black Box to Transparency: Enhancing Automated Interpreting Assessment with Explainable AI in College Classrooms

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10860
• PDF: https://arxiv.org/pdf/2508.10860

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10576
• PDF: https://arxiv.org/pdf/2508.10576
• Project Page: https://digital-avatar.github.io/ai/HumanSense/
• Github: https://digital-avatar.github.io/ai/HumanSense/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: UI-Venus Technical Report: Building High-performance UI Agents with RFT

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10833
• PDF: https://arxiv.org/pdf/2508.10833
• Github: https://github.com/antgroup/UI-Venus

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10711
• PDF: https://arxiv.org/pdf/2508.10711
• Github: https://github.com/stepfun-ai/NextStep-1

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10751
• PDF: https://arxiv.org/pdf/2508.10751
• Project Page: https://github.com/RUCAIBox/Passk_Training
• Github: https://github.com/RUCAIBox/Passk_Training

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: AgroBench: Vision-Language Model Benchmark in Agriculture

🔹 Publication Date: Published on Jul 28

🔹 Abstract: AgroBench evaluates vision-language models across agricultural tasks, revealing areas for improvement in fine-grained identification, particularly weed identification, with expert-annotated categories. AI-generated summary Precise automated understanding of agricultural tasks such as disease identification is essential for sustainable crop production. Recent advances in vision-language models ( VLMs ) are expected to further expand the range of agricultural tasks by facilitating human-model interaction through easy, text-based communication. Here, we introduce AgroBench (Agronomist AI Benchmark), a benchmark for evaluating VLM models across seven agricultural topics, covering key areas in agricultural engineering and relevant to real-world farming. Unlike recent agricultural VLM benchmarks, AgroBench is annotated by expert agronomists. Our AgroBench covers a state-of-the-art range of categories, including 203 crop categories and 682 disease categories , to thoroughly evaluate VLM capabilities. In our evaluation on AgroBench , we reveal that VLMs have room for improvement in fine-grained identification tasks. Notably, in weed identification , most open-source VLMs perform close to random. With our wide range of topics and expert-annotated categories, we analyze the types of errors made by VLMs and suggest potential pathways for future VLM development. Our dataset and code are available at https://dahlian00.github.io/ AgroBench Page/ .

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2507.20519

• PDF: https://arxiv.org/pdf/2507.20519

• Project Page: https://dahlian00.github.io/AgroBenchPage/

• Github: https://dahlian00.github.io/AgroBenchPage/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10881
• PDF: https://arxiv.org/pdf/2508.10881
• Project Page: https://lg-li.github.io/project/tooncomposer
• Github: https://github.com/TencentARC/ToonComposer

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: A Survey on Diffusion Language Models

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10875
• PDF: https://arxiv.org/pdf/2508.10875

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10637
• PDF: https://arxiv.org/pdf/2508.10637
• Github: https://github.com/ryan-caesar-ramos/visual-encoder-traces

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10893
• PDF: https://arxiv.org/pdf/2508.10893
• Project Page: https://nirvanalan.github.io/projects/stream3r
• Github: https://github.com/NIRVANALAN/STream3R

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: When Explainability Meets Privacy: An Investigation at the Intersection of Post-hoc Explainability and Differential Privacy in the Context of Natural Language Processing

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10482
• PDF: https://arxiv.org/pdf/2508.10482
• Github: https://github.com/dmah10/xpnlp

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: Artificial Intelligence and Misinformation in Art: Can Vision Language Models Judge the Hand or the Machine Behind the Canvas?

🔹 Publication Date: Published on Aug 2

🔹 Abstract: State-of-the-art vision language models struggle with accurately attributing artists and distinguishing AI-generated images, highlighting the need for improvement to prevent misinformation. AI-generated summary The attribution of artworks in general and of paintings in particular has always been an issue in art. The advent of powerful artificial intelligence models that can generate and analyze images creates new challenges for painting attribution. On the one hand, AI models can create images that mimic the style of a painter, which can be incorrectly attributed, for example, by other AI models. On the other hand, AI models may not be able to correctly identify the artist for real paintings, inducing users to incorrectly attribute paintings. In this paper, both problems are experimentally studied using state-of-the-art AI models for image generation and analysis on a large dataset with close to 40,000 paintings from 128 artists. The results show that vision language models have limited capabilities to: 1) perform canvas attribution and 2) to identify AI generated images . As users increasingly rely on queries to AI models to get information, these results show the need to improve the capabilities of VLMs to reliably perform artist attribution and detection of AI generated images to prevent the spread of incorrect information.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01408

• PDF: https://arxiv.org/pdf/2508.01408

• Github: https://ama2210.github.io/WikiArt_VLM_Web/

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: Puppeteer: Rig and Animate Your 3D Models

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.10898
• PDF: https://arxiv.org/pdf/2508.10898
• Project Page: https://chaoyuesong.github.io/Puppeteer/
• Github: https://github.com/Seed3D/Puppeteer

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning

🔹 Publication Date: Published on Aug 14

🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/we-math-20-a-versatile-mathbook-system-for-incentivizing-visual-mathematical-reasoning
• PDF: https://arxiv.org/pdf/2508.10433
• Project Page: https://we-math2.github.io/
• Github: https://github.com/We-Math/We-Math2.0

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/We-Math/We-Math2.0-Pro
• https://huggingface.co/datasets/We-Math/We-Math2.0-Standard

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: ChartCap: Mitigating Hallucination of Dense Chart Captioning

🔹 Publication Date: Published on Aug 5

🔹 Abstract: ChartCap, a large-scale dataset with dense, type-specific captions for real-world charts, improves caption accuracy and reduces hallucinations in vision language models. AI-generated summary Generating accurate, informative, and hallucination-free captions for charts remains challenging for vision language models , primarily due to the lack of large-scale, high-quality datasets of real-world charts . However, existing real-world chart datasets suffer from the inclusion of extraneous information that cannot be inferred from the chart and failure to sufficiently capture structural elements and key insights . Therefore, we introduce ChartCap, a large-scale dataset of 565K real-world chart images paired with type-specific, dense captions that exclude extraneous information and highlight both structural elements and key insights in detail. To build ChartCap, we design a four-stage pipeline that generates captions using only the discernible data from the chart and employ a cycle consistency-based human verification , which accelerates quality control without sacrificing accuracy. Additionally, we propose a novel metric, the Visual Consistency Score , which evaluates caption quality by measuring the similarity between the chart regenerated from a caption and the original chart, independent of reference captions. Extensive experiments confirms that models fine-tuned on ChartCap consistently generate more accurate and informative captions with reduced hallucinations , surpassing both open-source and proprietary models and even human-annotated captions.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.03164

• PDF: https://arxiv.org/pdf/2508.03164

• Project Page: https://junyoung-00.github.io/ChartCap/

• Github: https://junyoung-00.github.io/ChartCap/

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/junyoung-00/ChartCap

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization

🔹 Publication Date: Published on Aug 4

🔹 Abstract: AlignGuard-LoRA (AGL) is a framework that preserves alignment during fine-tuning of large language models by introducing regularization techniques and a diagnostic benchmark to mitigate alignment drift. AI-generated summary Low-rank adaptation ( LoRA ) has become a standard tool for efficiently fine-tuning large language models (LLMs). Yet, even minor LoRA updates can induce alignment drift , weakening safety and behavioral constraints through entangled parameter changes. To address this, we propose AlignGuard-LoRA (AGL), a principled framework for preserving alignment during finetuning. AGL introduces several key components: a primary task loss for supervision, Fisher Information Matrix-based regularization to restrict updates in alignment-sensitive subspaces, and task-specific regularization to stabilize the integration of new knowledge. We further introduce collision-aware regularization, blending Riemannian overlap -- which penalizes coordinate-wise interference -- and geodesic separation -- which encourages disjoint update geometry. We curate DriftCaps , a targeted diagnostic benchmark of safe and unsafe prompts designed to quantify alignment drift and safety degradation. Empirical evaluations show that AGL mitigates alignment drift by up to 50% on safety-critical benchmarks without degrading downstream task performance. Comprehensive ablation confirms that each component contributes distinctly to preserving latent safety behaviors. Finally, we derive and validate a scaling law for catastrophic forgetting , revealing that AGL flattens post-finetuning loss escalation while preserving adaptation dynamics . AGL is a structurally grounded refinement of LoRA , ensuring alignment preservation with minimal trade-offs. To encourage further exp lora tion and development, we open-source our implementation.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.02079

• PDF: https://arxiv.org/pdf/2508.02079

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning

🔹 Publication Date: Published on Aug 3

🔹 Abstract: An uncertainty-driven framework for automated process reward data construction and aggregation methods improves the effectiveness and efficiency of Process-Level Reward Models in mathematical reasoning tasks. AI-generated summary Large language models have demonstrated remarkable capabilities in complex math ematical reasoning tasks, but they inevitably generate errors throughout multi-step solutions. Process-level Reward Models ( PRMs ) have shown great promise by providing supervision and evaluation at each intermediate step, thereby effectively improving the models' reasoning abilities. However, training effective PRMs requires high-quality process reward data, yet existing methods for constructing such data are often labour-intensive or inefficient. In this paper, we propose an uncertainty-driven framework for automated process reward data construction, encompassing both data generation and annotation processes for PRMs . Additionally, we identify the limitations of both majority vote and PRMs , and introduce two generic uncertainty-aware output aggregation methods: Hybrid Majority Reward Vote and Weighted Reward Frequency Vote , which combine the strengths of majority vote with PRMs . Extensive experiments on ProcessBench , MATH , and GSMPlus show the effectiveness and efficiency of the proposed PRM data construction framework, and demonstrate that the two output aggregation methods further improve the math ematical reasoning abilities across diverse PRMs . The code and data will be publicly available at https://github.com/Jiuzhouh/UnPRM.

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.01773

• PDF: https://arxiv.org/pdf/2508.01773

• Github: https://github.com/Jiuzhouh/UnPRM

🔹 Datasets citing this paper:
No datasets found

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT

🔹 Title: Thyme: Think Beyond Images

🔹 Publication Date: Published on Aug 15

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2508.11630
• PDF: https://arxiv.org/pdf/2508.11630
• Project Page: https://thyme-vl.github.io/
• Github: https://github.com/yfzhang114/Thyme

🔹 Datasets citing this paper:
• https://huggingface.co/datasets/Kwai-Keye/Thyme-RL
• https://huggingface.co/datasets/Kwai-Keye/Thyme-SFT

🔹 Spaces citing this paper:
No spaces found
==================================

For more data science resources:
✓ https://t.iss.one/DataScienceT