Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model

We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded using two bilingual text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames. A video-based DPO approach, Video-DPO, is applied to reduce artifacts and improve the visual quality of the generated videos. We also detail our training strategies and share key observations and insights. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, Step-Video-T2V-Eval, demonstrating its state-of-the-art text-to-video quality when compared with both open-source and commercial engines. Additionally, we discuss the limitations of current diffusion-based model paradigm and outline future directions for video foundation models. We make both Step-Video-T2V and Step-Video-T2V-Eval available at https://github.com/stepfun-ai/Step-Video-T2V. The online version can be accessed from https://yuewen.cn/videos as well. Our goal is to accelerate the innovation of video foundation models and empower video content creators.

Paper: https://arxiv.org/pdf/2502.10248v1.pdf

Codes:
https://github.com/phixion/phixion
https://github.com/stepfun-ai/step-video-t2v

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek

https://t.iss.one/DataScienceT

KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG

13 Feb 2025 · Yiqian Huang, Shiqi Zhang, Xiaokui Xiao ·

Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful in domains such as biomedicine, law, and political science, where retrieval often requires multi-hop reasoning over proprietary documents. Some existing Graph-RAG systems construct #KNN graphs based on text chunk relevance, but this coarse-grained approach fails to capture entity relationships within texts, leading to sub-par retrieval and generation quality. To address this, recent solutions leverage LLMs to extract entities and relationships from text chunks, constructing triplet-based knowledge graphs. However, this approach incurs significant indexing costs, especially for large document collections. To ensure a good result accuracy while reducing the indexing cost, we propose KET-RAG, a multi-granular indexing framework. KET-RAG first identifies a small set of key text chunks and leverages an #LLM to construct a knowledge graph skeleton. It then builds a text-keyword bipartite graph from all text chunks, serving as a lightweight alternative to a full knowledge graph. During retrieval, KET-RAG searches both structures: it follows the local search strategy of existing Graph-RAG systems on the skeleton while mimicking this search on the bipartite graph to improve retrieval quality. We evaluate eight solutions on two real-world datasets, demonstrating that KET-RAG outperforms all competitors in indexing cost, retrieval effectiveness, and generation quality. Notably, it achieves comparable or superior retrieval quality to Microsoft's Graph-RAG while reducing indexing costs by over an order of magnitude. Additionally, it improves the generation quality by up to 32.4% while lowering indexing costs by around 20%.

Paper: https://arxiv.org/pdf/2502.09304v1.pdf

Code: https://github.com/waetr/KET-RAG

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek

https://t.iss.one/DataScienceT

OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia

Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable comprehensive speech-based interactions. However, most advanced SULMs are developed by the industry, leveraging large-scale datasets and computational resources that are not readily available to the academic community. Moreover, the lack of transparency in training details creates additional barriers to further innovation. In this study, we present OSUM, an Open Speech Understanding Model designed to explore the potential of training SLUMs under constrained academic resources. The OSUM model combines a Whisper encoder with a Qwen2 LLM and supports a wide range of speech tasks, including speech recognition (ASR), speech recognition with timestamps (SRWT), vocal event detection (VED), speech emotion recognition (SER), speaking style recognition (SSR), speaker gender classification (SGC), speaker age prediction (SAP), and speech-to-text chat (STTC). By employing an ASR+X training strategy, OSUM achieves efficient and stable multi-task training by simultaneously optimizing ASR alongside target tasks. Beyond delivering strong performance, OSUM emphasizes transparency by providing openly available data preparation and training methodologies, offering valuable insights and practical guidance for the academic community. By doing so, we aim to accelerate research and innovation in advanced SULM technologies.

Paper: https://arxiv.org/pdf/2501.13306v2.pdf

Code: https://github.com/aslp-lab/osum

Datasets: LibriSpeech - IEMOCAP

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek

https://t.iss.one/DataScienceT

Zep: A Temporal Knowledge Graph Architecture for Agent Memory

20 Jan 2025 · Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, Daniel Chalef ·

We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark. Additionally, Zep excels in more comprehensive and challenging evaluations than DMR that better reflect real-world enterprise use cases. While existing retrieval-augmented generation (#RAG) frameworks for large language model (LLM)-based agents are limited to static document retrieval, enterprise applications demand dynamic knowledge integration from diverse sources including ongoing conversations and business data. Zep addresses this fundamental limitation through its core component Graphiti -- a temporally-aware knowledge graph engine that dynamically synthesizes both unstructured conversational data and structured business data while maintaining historical relationships. In the #DMR benchmark, which the MemGPT team established as their primary evaluation metric, Zep demonstrates superior performance (94.8% vs 93.4%). Beyond DMR, Zep's capabilities are further validated through the more challenging LongMemEval benchmark, which better reflects enterprise use cases through complex temporal reasoning tasks. In this evaluation, #Zep achieves substantial results with accuracy improvements of up to 18.5% while simultaneously reducing response latency by 90% compared to baseline implementations. These results are particularly pronounced in enterprise-critical tasks such as cross-session information synthesis and long-term context maintenance, demonstrating Zep's effectiveness for deployment in real-world applications.

Paper: https://arxiv.org/pdf/2501.13956v1.pdf

Code: https://github.com/getzep/graphiti

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation

14 Feb 2025 · Tianwei Lin, Wenqiao Zhang, Sijing Li, Yuqian Yuan, Binhe Yu, Haoyuan Li, Wanggui He, Hao Jiang, Mengze Li, Xiaohui Song, Siliang Tang, Jun Xiao, Hui Lin, Yueting Zhuang, Beng Chin Ooi ·

We present #HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm. Our bootstrapping philosophy is to progressively adapt heterogeneous comprehension and generation knowledge to pre-trained large language models (#LLMs). This is achieved through a novel heterogeneous low-rank adaptation (H-LoRA) technique, which is complemented by a tailored hierarchical visual perception approach and a three-stage learning strategy. To effectively learn the HealthGPT, we devise a comprehensive medical domain-specific comprehension and generation dataset called VL-Health. Experimental results demonstrate exceptional performance and scalability of HealthGPT in medical visual unified tasks.

Paper: https://github.com/dcdmllm/healthgpt

Code: https://github.com/dcdmllm/healthgpt

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Fractal Generative Models

24 Feb 2025 · Tianhong Li, Qinyi Sun, Lijie Fan, Kaiming He ·

Modularization is a cornerstone of computer science, abstracting complex functions into atomic building blocks. In this paper, we introduce a new level of modularization by abstracting generative models into atomic generative modules. Analogous to fractals in mathematics, our method constructs a new type of generative model by recursively invoking atomic generative modules, resulting in self-similar fractal architectures that we call fractal generative models. As a running example, we instantiate our fractal framework using autoregressive models as the atomic generative modules and examine it on the challenging task of pixel-by-pixel image generation, demonstrating strong performance in both likelihood estimation and generation quality. We hope this work could open a new paradigm in generative modeling and provide a fertile ground for future research. Code is available at https://github.com/LTH14/fractalgen.

Paper: https://arxiv.org/pdf/2502.17437v1.pdf

Code: https://github.com/LTH14/fractalgen

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Slamming: Training a Speech Language Model on One GPU in a Day

19 Feb 2025 · Gallil Maimon, Avishai Elmakies, Yossi Adi ·

We introduce Slam, a recipe for training high-quality Speech Language Models (SLMs) on a single academic GPU in 24 hours. We do so through empirical analysis of model initialisation and architecture, synthetic training data, preference optimisation with synthetic data and tweaking all other components. We empirically demonstrate that this training recipe also scales well with more compute getting results on par with leading SLMs in a fraction of the compute cost. We hope these insights will make SLM training and research more accessible. In the context of SLM scaling laws, our results far outperform predicted compute optimal performance, giving an optimistic view to #SLM feasibility. See code, data, models, samples at - https://pages.cs.huji.ac.il/adiyoss-lab/slamming .

Paper: https://arxiv.org/pdf/2502.15814v1.pdf

Code: https://github.com/slp-rl/slamkit

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Magma: A Foundation Model for Multimodal AI Agents

18 Feb 2025 · Jianwei Yang, Reuben Tan, Qianhui Wu, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Lars Liden, Jianfeng Gao ·

We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to plan and act in the visual-spatial world (spatial-temporal intelligence) and complete agentic tasks ranging from UI navigation to robot manipulation. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data, where the actionable visual objects (e.g., clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and the object movements (e.g., the trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that SoM and ToM reach great synergy and facilitate the acquisition of spatial-temporal intelligence for our Magma model, which is fundamental to a wide range of tasks as shown in Fig.1. In particular, Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. On image and video-related multimodal tasks, Magma also compares favorably to popular large multimodal models that are trained on much larger datasets. We make our model and code public for reproducibility at https://microsoft.github.io/Magma.

Paper: https://arxiv.org/pdf/2502.13130v1.pdf

Code: https://github.com/microsoft/Magma

Datasets: Something-Something V2 - EPIC-KITCHENS-100 - Open-X-Embodiment - Ego4D

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

From System 1 to System 2: A Survey of Reasoning Large Language Models

24 Feb 2025 · Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, Jiaxin Zhang, Zengyan Liu, Yuxuan Yao, Haotian Xu, Junhao Zheng, Pei-Jie Wang, Xiuyi Chen, Yingying Zhang, Fei Yin, Jiahua Dong, Zhijiang Guo, Le Song, Cheng-Lin Liu ·

Achieving human-level intelligence requires refining the transition from the fast, intuitive System 1 to the slower, more deliberate System 2 reasoning. While System 1 excels in quick, heuristic decisions, System 2 relies on logical reasoning for more accurate judgments and reduced biases. Foundational Large Language Models (LLMs) excel at fast decision-making but lack the depth for complex reasoning, as they have not yet fully embraced the step-by-step analysis characteristic of true System 2 thinking. Recently, reasoning LLMs like OpenAI's o1/o3 and DeepSeek's R1 have demonstrated expert-level performance in fields such as mathematics and coding, closely mimicking the deliberate reasoning of System 2 and showcasing human-like cognitive abilities. This survey begins with a brief overview of the progress in foundational LLMs and the early development of System 2 technologies, exploring how their combination has paved the way for reasoning LLMs. Next, we discuss how to construct reasoning #LLMs, analyzing their features, the core methods enabling advanced reasoning, and the evolution of various reasoning LLMs. Additionally, we provide an overview of reasoning benchmarks, offering an in-depth comparison of the performance of representative reasoning LLMs. Finally, we explore promising directions for advancing reasoning LLMs and maintain a real-time \href{https://github.com/zzli2022/Awesome-Slow-Reason-System}{GitHub Repository} to track the latest developments. We hope this survey will serve as a valuable resource to inspire innovation and drive progress in this rapidly evolving field.

Paper: https://arxiv.org/pdf/2502.17419v1.pdf

Code: https://github.com/zzli2022/awesome-slow-reason-system

Datasets: GSM8K - MedQA - MathVista - GPQA - MMLU-Pro - PGPS9K

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Magma: A Foundation Model for Multimodal AI Agents

18 Feb 2025 · Jianwei Yang, Reuben Tan, Qianhui Wu, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Lars Liden, Jianfeng Gao ·

We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to plan and act in the visual-spatial world (spatial-temporal intelligence) and complete agentic tasks ranging from UI navigation to robot manipulation. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data, where the actionable visual objects (e.g., clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and the object movements (e.g., the trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that #SoM and ToM reach great synergy and facilitate the acquisition of spatial-temporal intelligence for our Magma model, which is fundamental to a wide range of tasks as shown in Fig.1. In particular, #Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. On image and video-related multimodal tasks, Magma also compares favorably to popular large multimodal models that are trained on much larger datasets. We make our model and code public for reproducibility at https://microsoft.github.io/Magma.

Paper: https://arxiv.org/pdf/2502.13130v1.pdf

Code: https://github.com/microsoft/Magma

Datasets: Something-Something V2 - EPIC-KITCHENS-100 - Open-X-Embodiment - Ego4D

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Hawk: Learning to Understand Open-World Video Anomalies

27 May 2024 · Jiaqi Tang, Hao Lu, Ruizheng Wu, Xiaogang Xu, Ke Ma, Cheng Fang, Bin Guo, Jiangbo Lu, Qifeng Chen, Ying-Cong Chen ·

Video Anomaly Detection (#VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (#VLM) to interpret video anomalies precisely. Recognizing the difference in motion information between abnormal and normal videos, Hawk explicitly integrates motion modality to enhance anomaly identification. To reinforce motion attention, we construct an auxiliary consistency loss within the motion and video space, guiding the video branch to focus on the motion modality. Moreover, to improve the interpretation of motion-to-language, we establish a clear supervisory relationship between motion and its linguistic representation. Furthermore, we have annotated over 8,000 anomaly videos with language descriptions, enabling effective training across diverse open-world scenarios, and also created 8,000 question-answering pairs for users' open-world questions. The final results demonstrate that #Hawk achieves SOTA performance, surpassing existing baselines in both video description generation and question-answering. Our codes/dataset/demo will be released at https://github.com/jqtangust/hawk.

Paper: https://arxiv.org/pdf/2405.16886v1.pdf

Code: https://github.com/jqtangust/hawk

Dataset: Hawk Annotation Dataset

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data

20 Feb 2025 · Shijie Huang, Yiren Song, Yuxuan Zhang, Hailong Guo, Xueyin Wang, Mike Zheng Shou, Jiaming Liu ·

We introduce PhotoDoodle, a novel image editing framework designed to facilitate photo doodling by enabling artists to overlay decorative elements onto photographs. Photo doodling is challenging because the inserted elements must appear seamlessly integrated with the background, requiring realistic blending, perspective alignment, and contextual coherence. Additionally, the background must be preserved without distortion, and the artist's unique style must be captured efficiently from limited training data. These requirements are not addressed by previous methods that primarily focus on global style transfer or regional inpainting. The proposed method, PhotoDoodle, employs a two-stage training strategy. Initially, we train a general-purpose image editing model, OmniEditor, using large-scale data. Subsequently, we fine-tune this model with EditLoRA using a small, artist-curated dataset of before-and-after image pairs to capture distinct editing styles and techniques. To enhance consistency in the generated results, we introduce a positional encoding reuse mechanism. Additionally, we release a PhotoDoodle dataset featuring six high-quality styles. Extensive experiments demonstrate the advanced performance and robustness of our method in customized image editing, opening new possibilities for artistic creation.

Paper: https://arxiv.org/pdf/2502.14397v1.pdf

Code: https://github.com/showlab/PhotoDoodle

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator

26 Feb 2025 · Xiankang He, Dongyan Guo, Hongji Li, Ruibo Li, Ying Cui, Chi Zhang ·

Monocular depth estimation (#MDE) aims to predict scene depth from a single RGB image and plays a crucial role in 3D scene understanding. Recent advances in zero-shot MDE leverage normalized depth representations and distillation-based learning to improve generalization across diverse scenes. However, current depth normalization methods for distillation, relying on global normalization, can amplify noisy pseudo-labels, reducing distillation effectiveness. In this paper, we systematically analyze the impact of different depth normalization strategies on pseudo-label distillation. Based on our findings, we propose Cross-Context Distillation, which integrates global and local depth cues to enhance pseudo-label quality. Additionally, we introduce a multi-teacher distillation framework that leverages complementary strengths of different depth estimation models, leading to more robust and accurate depth predictions. Extensive experiments on benchmark datasets demonstrate that our approach significantly outperforms state-of-the-art methods, both quantitatively and qualitatively.

Paper: https://arxiv.org/pdf/2502.19204v1.pdf

Code: https://github.com/Westlake-AGI-Lab/Distill-Any-Depth

Datasets: ScanNet - NYUv2 - ETH3D

Note: Ranked #1 on Depth Estimation on ScanNetV2

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents

https://t.iss.one/DataScienceT

Escaping The Big Data Paradigm in Self-Supervised Representation Learning

25 Feb 2025 · Carlos Vélez García, Miguel Cazorla, Jorge Pomares ·

The reliance on large-scale datasets and extensive computational resources has become a major barrier to advancing representation learning in vision, especially in data-scarce domains. In this paper, we address the critical question: Can we escape the big data paradigm in self-supervised representation learning from images? We introduce #SCOTT (Sparse Convolutional Tokenizer for Transformers), a shallow tokenization architecture that is compatible with Masked Image Modeling (MIM) tasks. SCOTT injects convolutional inductive biases into Vision Transformers (ViTs), enhancing their efficacy in small-scale data regimes. Alongside, we propose to train on a Joint-Embedding Predictive Architecture within a MIM framework (MIM-JEPA), operating in latent representation space to capture more semantic features. Our approach enables ViTs to be trained from scratch on datasets orders of magnitude smaller than traditionally required --without relying on massive external datasets for pretraining. We validate our method on three small-size, standard-resoultion, fine-grained datasets: Oxford Flowers-102, Oxford IIIT Pets-37, and ImageNet-100. Despite the challenges of limited data and high intra-class similarity, frozen SCOTT models pretrained with MIM-JEPA significantly outperform fully supervised methods and achieve competitive results with SOTA approaches that rely on large-scale pretraining, complex image augmentations and bigger model sizes. By demonstrating that robust off-the-shelf representations can be learned with limited data, compute, and model sizes, our work paves the way for computer applications in resource constrained environments such as medical imaging or robotics. Our findings challenge the prevailing notion that vast amounts of data are indispensable for effective representation learning in vision, offering a new pathway toward more accessible and inclusive advancements in the field.

Paper: https://arxiv.org/pdf/2502.18056v1.pdf

Code: https://github.com/inescopresearch/scott

Datasets: Oxford 102 Flower - Oxford-IIIT Pets - Imagenet100

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://t.iss.one/DataScienceT

A-MEM: Agentic Memory for LLM Agents

17 Feb 2025 · Wujiang Xu, Zujie Liang, Kai Mei, Hang Gao, Juntao Tan, Yongfeng Zhang ·

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack sophisticated memory organization, despite recent attempts to incorporate graph databases. Moreover, these systems' fixed operations and structures limit their adaptability across diverse tasks. To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. Following the basic principles of the Zettelkasten method, we designed our memory system to create interconnected knowledge networks through dynamic indexing and linking. When a new memory is added, we generate a comprehensive note containing multiple structured attributes, including contextual descriptions, keywords, and tags. The system then analyzes historical memories to identify relevant connections, establishing links where meaningful similarities exist. Additionally, this process enables memory evolution - as new memories are integrated, they can trigger updates to the contextual representations and attributes of existing historical memories, allowing the memory network to continuously refine its understanding. Our approach combines the structured organization principles of Zettelkasten with the flexibility of agent-driven decision making, allowing for more adaptive and context-aware memory management. Empirical experiments on six foundation models show superior improvement against existing SOTA baselines. The source code for evaluating performance is available at https://github.com/WujiangXu/AgenticMemory, while the source code of agentic memory system is available at https://github.com/agiresearch/A-mem.

Paper: https://arxiv.org/pdf/2502.12110v3.pdf

Code: https://github.com/wujiangxu/agenticmemory

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #RAG #Agents #GPT4

https://t.iss.one/DataScienceT

Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles

26 Feb 2025 · Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li ·

User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language models (LLMs). However, existing simulators often rely solely on text utterances, missing implicit user traits such as personality, speaking style, and goals. In contrast, persona-based methods lack generalizability, as they depend on predefined profiles of famous individuals or archetypes. To address these challenges, we propose User Simulator with implicit Profiles (#USP), a framework that infers implicit user profiles from human-machine conversations and uses them to generate more personalized and realistic dialogues. We first develop an LLM-driven extractor with a comprehensive profile schema. Then, we refine the simulation through conditional supervised fine-tuning and reinforcement learning with cycle consistency, optimizing it at both the utterance and conversation levels. Finally, we adopt a diverse profile sampler to capture the distribution of real-world user profiles. Experimental results demonstrate that USP outperforms strong baselines in terms of authenticity and diversity while achieving comparable performance in consistency. Furthermore, dynamic multi-turn evaluations based on USP strongly align with mainstream benchmarks, demonstrating its effectiveness in real-world applications

.
Paper: https://arxiv.org/pdf/2502.18968v1.pdf

Code: https://github.com/wangkevin02/USP

Dataset: LMSYS-USP

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://t.iss.one/DataScienceT

Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens

3 Mar 2025 · Xinsheng Wang, Mingqi Jiang, Ziyang Ma, Ziyu Zhang, Songxiang Liu, Linqin Li, Zheng Liang, Qixi Zheng, Rui Wang, Xiaoqin Feng, Weizhen Bian, Zhen Ye, Sitong Cheng, Ruibin Yuan, Zhixian Zhao, Xinfa Zhu, Jiahao Pan, Liumeng Xue, Pengcheng Zhu, Yunlin Chen, Zhifei Li, Xie Chen, Lei Xie, Yike Guo, Wei Xue ·

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Paper: https://arxiv.org/pdf/2503.01710v1.pdf

Code: https://github.com/sparkaudio/spark-tts

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://t.iss.one/DataScienceT

Open Deep Search: Democratizing Search with Open-source Reasoning Agents

26 Mar 2025 · Salaheddin Alzubi, Creston Brooks, Purva Chiniya, Edoardo Contente, Chiara von Gerlach, Lucas Irwin, Yihan Jiang, Arda Kaz, Windsor Nguyen, Sewoong Oh, Himanshu Tyagi, Pramod Viswanath ·

We introduce Open Deep Search (ODS) to close the increasing gap between the proprietary search AI solutions, such as Perplexity's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview, and their open-source counterparts. The main innovation introduced in ODS is to augment the reasoning capabilities of the latest open-source LLMs with reasoning agents that can judiciously use web search tools to answer queries. Concretely, ODS consists of two components that work with a base LLM chosen by the user: Open Search Tool and Open Reasoning Agent. Open Reasoning Agent interprets the given task and completes it by orchestrating a sequence of actions that includes calling tools, one of which is the Open Search Tool. Open Search Tool is a novel web search tool that outperforms proprietary counterparts. Together with powerful open-source reasoning LLMs, such as DeepSeek-R1, ODS nearly matches and sometimes surpasses the existing state-of-the-art baselines on two benchmarks: SimpleQA and FRAMES. For example, on the FRAMES evaluation benchmark, ODS improves the best existing baseline of the recently released GPT-4o Search Preview by 9.7% in accuracy. ODS is a general framework for seamlessly augmenting any LLMs -- for example, DeepSeek-R1 that achieves 82.4% on SimpleQA and 30.1% on FRAMES -- with search and reasoning capabilities to achieve state-of-the-art performance: 88.3% on SimpleQA and 75.3% on FRAMES.

Paper: https://arxiv.org/pdf/2503.20201v1.pdf

Code: https://github.com/sentient-agi/opendeepsearch

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://t.iss.one/DataScienceT

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

10 Feb 2025 · Yangguang Li, Zi-Xin Zou, Zexiang Liu, Dehu Wang, Yuan Liang, Zhipeng Yu, Xingchao Liu, Yuan-Chen Guo, Ding Liang, Wanli Ouyang, Yan-Pei Cao ·

Recent advancements in diffusion techniques have propelled image and video generation to unprecedented levels of quality, significantly accelerating the deployment and application of generative AI. However, 3D shape generation technology has so far lagged behind, constrained by limitations in 3D data scale, complexity of 3D data processing, and insufficient exploration of advanced techniques in the 3D domain. Current approaches to 3D shape generation face substantial challenges in terms of output quality, generalization capability, and alignment with input conditions. We present TripoSG, a new streamlined shape diffusion paradigm capable of generating high-fidelity 3D meshes with precise correspondence to input images. Specifically, we propose: 1) A large-scale rectified flow transformer for 3D shape generation, achieving state-of-the-art fidelity through training on extensive, high-quality data. 2) A hybrid supervised training strategy combining SDF, normal, and eikonal losses for 3D VAE, achieving high-quality 3D reconstruction performance. 3) A data processing pipeline to generate 2 million high-quality 3D samples, highlighting the crucial rules for data quality and quantity in training 3D generative models. Through comprehensive experiments, we have validated the effectiveness of each component in our new framework. The seamless integration of these parts has enabled TripoSG to achieve state-of-the-art performance in 3D shape generation. The resulting 3D shapes exhibit enhanced detail due to high-resolution capabilities and demonstrate exceptional fidelity to input images. Moreover, TripoSG demonstrates improved versatility in generating 3D models from diverse image styles and contents, showcasing strong generalization capabilities. To foster progress and innovation in the field of 3D generation, we will make our model publicly available.

Paper: https://arxiv.org/pdf/2502.06608v3.pdf

Codes:
https://github.com/VAST-AI-Research/TripoSG
https://github.com/tencent/flashvdm

Dataset: 100poisonMpts

#DataScience #ArtificialIntelligence #MachineLearning #PythonProgramming #DeepLearning #LLM #AIResearch #BigData #NeuralNetworks #DataAnalytics #NLP #AutoML #DataVisualization #ScikitLearn #Pandas #NumPy #TensorFlow #AIethics #PredictiveModeling #GPUComputing #OpenSourceAI #DeepSeek #RAG #Agents #GPT4

https://t.iss.one/DataScienceT