✨MME-CC: A Challenging Multi-Modal Evaluation Benchmark of Cognitive Capacity
📝 Summary:
MME-CC is a new vision-grounded benchmark to evaluate multimodal large language models cognitive capacity in spatial, geometric, and knowledge-based reasoning tasks. It reveals that while some models lead, spatial and geometric reasoning remain broadly weak. This highlights the need for better ev...
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03146
• PDF: https://arxiv.org/pdf/2511.03146
• Project Page: https://randomtutu.github.io/MME-CC/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MultimodalAI #LLMs #Benchmarking #CognitiveAI #ComputerVision
📝 Summary:
MME-CC is a new vision-grounded benchmark to evaluate multimodal large language models cognitive capacity in spatial, geometric, and knowledge-based reasoning tasks. It reveals that while some models lead, spatial and geometric reasoning remain broadly weak. This highlights the need for better ev...
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03146
• PDF: https://arxiv.org/pdf/2511.03146
• Project Page: https://randomtutu.github.io/MME-CC/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MultimodalAI #LLMs #Benchmarking #CognitiveAI #ComputerVision
✨LEGO-Eval: Towards Fine-Grained Evaluation on Synthesizing 3D Embodied Environments with Tool Augmentation
📝 Summary:
The paper introduces LEGO-Eval, a tool-augmented framework, and LEGO-Bench, a detailed instruction benchmark, to improve 3D scene evaluation. It shows LEGO-Eval accurately assesses scene-instruction alignment, outperforming VLMs, and current generation methods largely fail to create realistic sce...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03001
• PDF: https://arxiv.org/pdf/2511.03001
• Project Page: https://gyeomh.github.io/LEGO-Eval/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#EmbodiedAI #3DGeneration #EvaluationMetrics #VLMs #Benchmarking
📝 Summary:
The paper introduces LEGO-Eval, a tool-augmented framework, and LEGO-Bench, a detailed instruction benchmark, to improve 3D scene evaluation. It shows LEGO-Eval accurately assesses scene-instruction alignment, outperforming VLMs, and current generation methods largely fail to create realistic sce...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03001
• PDF: https://arxiv.org/pdf/2511.03001
• Project Page: https://gyeomh.github.io/LEGO-Eval/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#EmbodiedAI #3DGeneration #EvaluationMetrics #VLMs #Benchmarking
✨Let Multimodal Embedders Learn When to Augment Query via Adaptive Query Augmentation
📝 Summary:
M-Solomon is a multimodal embedder that adaptively decides when to augment queries. It uses a Multimodal LLM to generate augmentations for queries that require them, learning to augment only when necessary. This approach improves performance and significantly reduces embedding latency compared to...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02358
• PDF: https://arxiv.org/pdf/2511.02358
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MultimodalAI #LLM #Embeddings #MachineLearning #DeepLearning
📝 Summary:
M-Solomon is a multimodal embedder that adaptively decides when to augment queries. It uses a Multimodal LLM to generate augmentations for queries that require them, learning to augment only when necessary. This approach improves performance and significantly reduces embedding latency compared to...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02358
• PDF: https://arxiv.org/pdf/2511.02358
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MultimodalAI #LLM #Embeddings #MachineLearning #DeepLearning
✨LiveTradeBench: Seeking Real-World Alpha with Large Language Models
📝 Summary:
LiveTradeBench evaluates LLMs in live trading environments with real-time data, multi-asset portfolios, and multiple markets. It reveals that strong static benchmark scores dont predict trading success, and some LLMs can adapt to live market signals. This highlights a gap in current LLM evaluations.
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03628
• PDF: https://arxiv.org/pdf/2511.03628
• Project Page: https://trade-bench.live/
• Github: https://github.com/ulab-uiuc/live-trade-bench
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #AlgorithmicTrading #FinancialAI #QuantitativeFinance #AIResearch
📝 Summary:
LiveTradeBench evaluates LLMs in live trading environments with real-time data, multi-asset portfolios, and multiple markets. It reveals that strong static benchmark scores dont predict trading success, and some LLMs can adapt to live market signals. This highlights a gap in current LLM evaluations.
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03628
• PDF: https://arxiv.org/pdf/2511.03628
• Project Page: https://trade-bench.live/
• Github: https://github.com/ulab-uiuc/live-trade-bench
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #AlgorithmicTrading #FinancialAI #QuantitativeFinance #AIResearch
❤1
✨Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects
📝 Summary:
Kinematify is an automated framework that synthesizes high-DoF articulated objects from images or text. It infers kinematic topologies and estimates joint parameters, combining MCTS search with geometry-driven optimization for physically consistent models.
🔹 Publication Date: Published on Nov 3
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.01294
• PDF: https://arxiv.org/pdf/2511.01294
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#3DModeling #ComputerVision #Robotics #AIResearch #Kinematics
📝 Summary:
Kinematify is an automated framework that synthesizes high-DoF articulated objects from images or text. It infers kinematic topologies and estimates joint parameters, combining MCTS search with geometry-driven optimization for physically consistent models.
🔹 Publication Date: Published on Nov 3
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.01294
• PDF: https://arxiv.org/pdf/2511.01294
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#3DModeling #ComputerVision #Robotics #AIResearch #Kinematics
✨Diffusion Language Models are Super Data Learners
📝 Summary:
Diffusion Language Models DLMs consistently outperform autoregressive models, especially in low-data settings. This is due to any-order modeling, iterative bidirectional denoising, and Monte Carlo augmentation. DLMs maintain advantages at scale, achieving strong performance even by repeating limi...
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03276
• PDF: https://arxiv.org/pdf/2511.03276
• Project Page: https://github.com/JinjieNi/dlms-are-super-data-learners
• Github: https://github.com/JinjieNi/OpenMoE2
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#DiffusionModels #LanguageModels #MachineLearning #LowDataLearning #AI
📝 Summary:
Diffusion Language Models DLMs consistently outperform autoregressive models, especially in low-data settings. This is due to any-order modeling, iterative bidirectional denoising, and Monte Carlo augmentation. DLMs maintain advantages at scale, achieving strong performance even by repeating limi...
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03276
• PDF: https://arxiv.org/pdf/2511.03276
• Project Page: https://github.com/JinjieNi/dlms-are-super-data-learners
• Github: https://github.com/JinjieNi/OpenMoE2
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#DiffusionModels #LanguageModels #MachineLearning #LowDataLearning #AI
✨Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
📝 Summary:
Orion-MSP is a novel tabular in-context learning architecture addressing limitations in existing models. It incorporates multi-scale processing, block-sparse attention, and a Perceiver-style memory. Orion-MSP achieves state-of-the-art performance on various benchmarks while scaling effectively to...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02818
• PDF: https://arxiv.org/pdf/2511.02818
🔹 Models citing this paper:
• https://huggingface.co/Lexsi/Orion-MSP
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#TabularLearning #SparseAttention #MachineLearning #DeepLearning #AI
📝 Summary:
Orion-MSP is a novel tabular in-context learning architecture addressing limitations in existing models. It incorporates multi-scale processing, block-sparse attention, and a Perceiver-style memory. Orion-MSP achieves state-of-the-art performance on various benchmarks while scaling effectively to...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02818
• PDF: https://arxiv.org/pdf/2511.02818
🔹 Models citing this paper:
• https://huggingface.co/Lexsi/Orion-MSP
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#TabularLearning #SparseAttention #MachineLearning #DeepLearning #AI
✨TabTune: A Unified Library for Inference and Fine-Tuning Tabular Foundation Models
📝 Summary:
TabTune is a unified library that standardizes the workflow for tabular foundation models. It provides consistent access to state-of-the-art models, diverse adaptation strategies, and integrated evaluation for performance, calibration, and fairness.
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02802
• PDF: https://arxiv.org/pdf/2511.02802
• Github: https://github.com/Lexsi-Labs/TabTune
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#TabularData #FoundationModels #MachineLearning #DataScience #AIResearch
📝 Summary:
TabTune is a unified library that standardizes the workflow for tabular foundation models. It provides consistent access to state-of-the-art models, diverse adaptation strategies, and integrated evaluation for performance, calibration, and fairness.
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02802
• PDF: https://arxiv.org/pdf/2511.02802
• Github: https://github.com/Lexsi-Labs/TabTune
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#TabularData #FoundationModels #MachineLearning #DataScience #AIResearch
❤1
✨UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
📝 Summary:
UniAVGen uses dual Diffusion Transformers and Asymmetric Cross-Modal Interaction for unified audio-video generation. This framework ensures precise spatiotemporal synchronization and semantic consistency. It outperforms existing methods in sync and consistency with far fewer training samples.
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03334
• PDF: https://arxiv.org/pdf/2511.03334
• Project Page: https://mcg-nju.github.io/UniAVGen/
• Github: https://mcg-nju.github.io/UniAVGen/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#GenerativeAI #AudioVideoGeneration #DiffusionModels #CrossModalAI #DeepLearning
📝 Summary:
UniAVGen uses dual Diffusion Transformers and Asymmetric Cross-Modal Interaction for unified audio-video generation. This framework ensures precise spatiotemporal synchronization and semantic consistency. It outperforms existing methods in sync and consistency with far fewer training samples.
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03334
• PDF: https://arxiv.org/pdf/2511.03334
• Project Page: https://mcg-nju.github.io/UniAVGen/
• Github: https://mcg-nju.github.io/UniAVGen/
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#GenerativeAI #AudioVideoGeneration #DiffusionModels #CrossModalAI #DeepLearning
✨MemOS: A Memory OS for AI System
📝 Summary:
MemOS is a memory operating system that unifies plaintext, activation-based, and parameter-level memories for LLMs. It manages memory as a system resource with MemCubes, enabling efficient storage, retrieval, continual learning, and personalized modeling.
🔹 Publication Date: Published on Jul 4
🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/memos-a-memory-os-for-ai-system
• PDF: https://arxiv.org/pdf/2507.03724
• Project Page: https://memos.openmem.net/
• Github: https://github.com/MemTensor/MemOS
🔹 Models citing this paper:
• https://huggingface.co/kagvi13/HMP
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MemOS #LLMs #MemoryManagement #OperatingSystems #AI
📝 Summary:
MemOS is a memory operating system that unifies plaintext, activation-based, and parameter-level memories for LLMs. It manages memory as a system resource with MemCubes, enabling efficient storage, retrieval, continual learning, and personalized modeling.
🔹 Publication Date: Published on Jul 4
🔹 Paper Links:
• arXiv Page: https://arxivexplained.com/papers/memos-a-memory-os-for-ai-system
• PDF: https://arxiv.org/pdf/2507.03724
• Project Page: https://memos.openmem.net/
• Github: https://github.com/MemTensor/MemOS
🔹 Models citing this paper:
• https://huggingface.co/kagvi13/HMP
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MemOS #LLMs #MemoryManagement #OperatingSystems #AI
✨FG-CLIP: Fine-Grained Visual and Textual Alignment
📝 Summary:
FG-CLIP enhances fine-grained multimodal understanding, overcoming CLIPs limitations with coarse captions. It uses large models for long captions, a high-quality dataset with region boxes and detailed captions, and hard negative samples. FG-CLIP outperforms existing methods on fine-grained and ge...
🔹 Publication Date: Published on May 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2505.05071
• PDF: https://arxiv.org/pdf/2505.05071
• Github: https://github.com/360CVGroup/FG-CLIP
🔹 Models citing this paper:
• https://huggingface.co/qihoo360/fg-clip2-base
• https://huggingface.co/qihoo360/fg-clip-large
• https://huggingface.co/qihoo360/fg-clip-base
✨ Datasets citing this paper:
• https://huggingface.co/datasets/qihoo360/FineHARD
• https://huggingface.co/datasets/qihoo360/DCI-CN
• https://huggingface.co/datasets/qihoo360/DOCCI-CN
✨ Spaces citing this paper:
• https://huggingface.co/spaces/qihoo360/FG-CLIP-Retrieval-demo
• https://huggingface.co/spaces/qihoo360/FG-CLIP-Densefeature-demo
• https://huggingface.co/spaces/qihoo360/FG-CLIP2-Retrieval-demo
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#FGCLIP #FineGrainedAI #MultimodalLearning #ComputerVision #DeepLearning
📝 Summary:
FG-CLIP enhances fine-grained multimodal understanding, overcoming CLIPs limitations with coarse captions. It uses large models for long captions, a high-quality dataset with region boxes and detailed captions, and hard negative samples. FG-CLIP outperforms existing methods on fine-grained and ge...
🔹 Publication Date: Published on May 8
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2505.05071
• PDF: https://arxiv.org/pdf/2505.05071
• Github: https://github.com/360CVGroup/FG-CLIP
🔹 Models citing this paper:
• https://huggingface.co/qihoo360/fg-clip2-base
• https://huggingface.co/qihoo360/fg-clip-large
• https://huggingface.co/qihoo360/fg-clip-base
✨ Datasets citing this paper:
• https://huggingface.co/datasets/qihoo360/FineHARD
• https://huggingface.co/datasets/qihoo360/DCI-CN
• https://huggingface.co/datasets/qihoo360/DOCCI-CN
✨ Spaces citing this paper:
• https://huggingface.co/spaces/qihoo360/FG-CLIP-Retrieval-demo
• https://huggingface.co/spaces/qihoo360/FG-CLIP-Densefeature-demo
• https://huggingface.co/spaces/qihoo360/FG-CLIP2-Retrieval-demo
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#FGCLIP #FineGrainedAI #MultimodalLearning #ComputerVision #DeepLearning
arXiv.org
FG-CLIP: Fine-Grained Visual and Textual Alignment
Contrastive Language-Image Pre-training (CLIP) excels in multimodal tasks such as image-text retrieval and zero-shot classification but struggles with fine-grained understanding due to its focus...
✨The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute
📝 Summary:
Sequential scaling for language model reasoning consistently outperforms parallel self-consistency at matched compute, achieving significant accuracy gains. The paper introduces inverse-entropy weighted voting to further enhance sequential scaling, establishing it as the superior test-time strate...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02309
• PDF: https://arxiv.org/pdf/2511.02309
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #AIReasoning #SelfConsistency #SequentialScaling #InverseEntropy
📝 Summary:
Sequential scaling for language model reasoning consistently outperforms parallel self-consistency at matched compute, achieving significant accuracy gains. The paper introduces inverse-entropy weighted voting to further enhance sequential scaling, establishing it as the superior test-time strate...
🔹 Publication Date: Published on Nov 4
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.02309
• PDF: https://arxiv.org/pdf/2511.02309
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#LLM #AIReasoning #SelfConsistency #SequentialScaling #InverseEntropy
✨In-the-Flow Agentic System Optimization for Effective Planning and Tool Use
📝 Summary:
AgentFlow is a trainable agentic framework that optimizes its planner in-the-flow within multi-turn interactions. It uses Flow-GRPO to train its modules and significantly outperforms top baselines and GPT-4o on various reasoning and tool-use tasks.
🔹 Publication Date: Published on Oct 7
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.05592
• PDF: https://arxiv.org/pdf/2510.05592
• Project Page: https://agentflow.stanford.edu/
• Github: https://github.com/lupantech/AgentFlow
✨ Spaces citing this paper:
• https://huggingface.co/spaces/AgentFlow/agentflow
• https://huggingface.co/spaces/bioliveir4/agentflow2
• https://huggingface.co/spaces/bioliveir4/agentflow
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#AI #MachineLearning #AIagents #ToolUse #Planning
📝 Summary:
AgentFlow is a trainable agentic framework that optimizes its planner in-the-flow within multi-turn interactions. It uses Flow-GRPO to train its modules and significantly outperforms top baselines and GPT-4o on various reasoning and tool-use tasks.
🔹 Publication Date: Published on Oct 7
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2510.05592
• PDF: https://arxiv.org/pdf/2510.05592
• Project Page: https://agentflow.stanford.edu/
• Github: https://github.com/lupantech/AgentFlow
✨ Spaces citing this paper:
• https://huggingface.co/spaces/AgentFlow/agentflow
• https://huggingface.co/spaces/bioliveir4/agentflow2
• https://huggingface.co/spaces/bioliveir4/agentflow
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#AI #MachineLearning #AIagents #ToolUse #Planning
✨Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
📝 Summary:
PaperCoder is a multi-agent LLM framework that automates converting machine learning papers into functional code repositories. It uses planning, analysis, and generation stages with specialized agents. Evaluations show it effectively creates high-quality implementations, outperforming strong base...
🔹 Publication Date: Published on Apr 24
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.17192
• PDF: https://arxiv.org/pdf/2504.17192
• Project Page: https://huggingface.co/papers/2504.15080
• Github: https://github.com/going-doer/Paper2Code
✨ Datasets citing this paper:
• https://huggingface.co/datasets/iaminju/paper2code
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#CodeGeneration #MachineLearning #LLM #AI #Automation
📝 Summary:
PaperCoder is a multi-agent LLM framework that automates converting machine learning papers into functional code repositories. It uses planning, analysis, and generation stages with specialized agents. Evaluations show it effectively creates high-quality implementations, outperforming strong base...
🔹 Publication Date: Published on Apr 24
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2504.17192
• PDF: https://arxiv.org/pdf/2504.17192
• Project Page: https://huggingface.co/papers/2504.15080
• Github: https://github.com/going-doer/Paper2Code
✨ Datasets citing this paper:
• https://huggingface.co/datasets/iaminju/paper2code
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#CodeGeneration #MachineLearning #LLM #AI #Automation
✨Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask
📝 Summary:
This paper introduces a perspectivist annotation scheme for the MapTask corpus. It separately tracks speaker and addressee interpretations to reveal how understanding emerges and diverges. Findings show subtle discrepancies cause referential misalignment despite apparent agreement.
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03718
• PDF: https://arxiv.org/pdf/2511.03718
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#Dialogue #NLP #Communication #Pragmatics #CorpusLinguistics
📝 Summary:
This paper introduces a perspectivist annotation scheme for the MapTask corpus. It separately tracks speaker and addressee interpretations to reveal how understanding emerges and diverges. Findings show subtle discrepancies cause referential misalignment despite apparent agreement.
🔹 Publication Date: Published on Nov 5
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.03718
• PDF: https://arxiv.org/pdf/2511.03718
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#Dialogue #NLP #Communication #Pragmatics #CorpusLinguistics
❤1
✨DINOv3
📝 Summary:
DINOv3 is a self-supervised vision model excelling across tasks. It scales datasets, prevents dense feature degradation via Gram anchoring, and uses post-hoc strategies for flexibility. This versatile foundation model outperforms specialized state of the art without fine-tuning.
🔹 Publication Date: Published on Aug 13
🔹 Paper Links:
• arXiv Page: https://huggingface.co/collections/facebook/dinov3
• PDF: https://arxiv.org/pdf/2508.10104
• Project Page: https://ai.meta.com/blog/dinov3-self-supervised-vision-model/
• Github: https://github.com/facebookresearch/dinov3
🔹 Models citing this paper:
• https://huggingface.co/facebook/dinov3-vit7b16-pretrain-lvd1689m
• https://huggingface.co/facebook/dinov3-vitb16-pretrain-lvd1689m
• https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m
✨ Datasets citing this paper:
• https://huggingface.co/datasets/zhuangzhe1229/test_dataset
• https://huggingface.co/datasets/simon123905/vitl
✨ Spaces citing this paper:
• https://huggingface.co/spaces/atalaydenknalbant/DINOv3
• https://huggingface.co/spaces/manu02/DINOv3-Interactive-Patch-Cosine-Similarity
• https://huggingface.co/spaces/merve/dinov3-viz
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#DINOv3 #SelfSupervisedLearning #ComputerVision #FoundationModels #AI
📝 Summary:
DINOv3 is a self-supervised vision model excelling across tasks. It scales datasets, prevents dense feature degradation via Gram anchoring, and uses post-hoc strategies for flexibility. This versatile foundation model outperforms specialized state of the art without fine-tuning.
🔹 Publication Date: Published on Aug 13
🔹 Paper Links:
• arXiv Page: https://huggingface.co/collections/facebook/dinov3
• PDF: https://arxiv.org/pdf/2508.10104
• Project Page: https://ai.meta.com/blog/dinov3-self-supervised-vision-model/
• Github: https://github.com/facebookresearch/dinov3
🔹 Models citing this paper:
• https://huggingface.co/facebook/dinov3-vit7b16-pretrain-lvd1689m
• https://huggingface.co/facebook/dinov3-vitb16-pretrain-lvd1689m
• https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m
✨ Datasets citing this paper:
• https://huggingface.co/datasets/zhuangzhe1229/test_dataset
• https://huggingface.co/datasets/simon123905/vitl
✨ Spaces citing this paper:
• https://huggingface.co/spaces/atalaydenknalbant/DINOv3
• https://huggingface.co/spaces/manu02/DINOv3-Interactive-Patch-Cosine-Similarity
• https://huggingface.co/spaces/merve/dinov3-viz
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#DINOv3 #SelfSupervisedLearning #ComputerVision #FoundationModels #AI
huggingface.co
DINOv3 - a facebook Collection
DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104
✨MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
📝 Summary:
MarS is a financial market simulation engine using LMM, an order-level generative model. It creates realistic, interactive market scenarios for risk-free strategy training and analysis. This offers scalability and strong realism.
🔹 Publication Date: Published on Sep 4, 2024
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2409.07486
• PDF: https://arxiv.org/pdf/2409.07486
• Github: https://github.com/microsoft/mars
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#FinancialMarkets #GenerativeAI #Simulation #LLM #FinTech
📝 Summary:
MarS is a financial market simulation engine using LMM, an order-level generative model. It creates realistic, interactive market scenarios for risk-free strategy training and analysis. This offers scalability and strong realism.
🔹 Publication Date: Published on Sep 4, 2024
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2409.07486
• PDF: https://arxiv.org/pdf/2409.07486
• Github: https://github.com/microsoft/mars
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#FinancialMarkets #GenerativeAI #Simulation #LLM #FinTech
✨V-Thinker: Interactive Thinking with Images
📝 Summary:
V-Thinker is a multimodal reasoning assistant that enables interactive thinking with images using end-to-end reinforcement learning. It synthesizes datasets and aligns perception to enhance performance in vision-centric tasks, outperforming existing models.
🔹 Publication Date: Published on Nov 6
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.04460
• PDF: https://arxiv.org/pdf/2511.04460
• Github: https://github.com/We-Math/V-Thinker
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MultimodalAI #ComputerVision #ReinforcementLearning #AIResearch #DeepLearning
📝 Summary:
V-Thinker is a multimodal reasoning assistant that enables interactive thinking with images using end-to-end reinforcement learning. It synthesizes datasets and aligns perception to enhance performance in vision-centric tasks, outperforming existing models.
🔹 Publication Date: Published on Nov 6
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.04460
• PDF: https://arxiv.org/pdf/2511.04460
• Github: https://github.com/We-Math/V-Thinker
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#MultimodalAI #ComputerVision #ReinforcementLearning #AIResearch #DeepLearning
✨Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm
📝 Summary:
The 'Thinking with Video' paradigm uses video generation models to unify multimodal reasoning, addressing limitations of static image or text-only approaches. Evaluated on VideoThinkBench, models like Sora-2 show strong performance on vision and text tasks, suggesting a promising unified reasonin...
🔹 Publication Date: Published on Nov 6
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.04570
• PDF: https://arxiv.org/pdf/2511.04570
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#VideoGeneration #MultimodalAI #AIResearch #ComputerVision #DeepLearning
📝 Summary:
The 'Thinking with Video' paradigm uses video generation models to unify multimodal reasoning, addressing limitations of static image or text-only approaches. Evaluated on VideoThinkBench, models like Sora-2 show strong performance on vision and text tasks, suggesting a promising unified reasonin...
🔹 Publication Date: Published on Nov 6
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2511.04570
• PDF: https://arxiv.org/pdf/2511.04570
==================================
For more data science resources:
✓ https://news.1rj.ru/str/DataScienceT
#VideoGeneration #MultimodalAI #AIResearch #ComputerVision #DeepLearning