René's URL Explorer Experiment


Title: Trending Papers - Hugging Face

Open Graph Title: Trending Papers - Hugging Face

Description: Your daily dose of AI research from AK

Open Graph Description: Your daily dose of AI research from AK

Opengraph URL: https://huggingface.co/papers/trending

X: @huggingface

direct link

Domain: paperswithcode.com

IPv4 address: 108.138.246.67

fb:app_id1321688464574422
twitter:cardsummary_large_image
twitter:imagehttps://huggingface.co/front/thumbnails/trending-papers.png
og:typewebsite
og:imagehttps://huggingface.co/front/thumbnails/trending-papers.png

Links:

Hugging Facehttps://paperswithcode.com/
Modelshttps://paperswithcode.com/models
Datasetshttps://paperswithcode.com/datasets
Spaceshttps://paperswithcode.com/spaces
Bucketshttps://paperswithcode.com/storage
Docshttps://paperswithcode.com/docs
Enterprisehttps://paperswithcode.com/enterprise
Pricinghttps://paperswithcode.com/pricing
Taskshttps://paperswithcode.com/tasks
HuggingChathttps://paperswithcode.com/chat
Collectionshttps://paperswithcode.com/collections
Languageshttps://paperswithcode.com/languages
Organizationshttps://paperswithcode.com/organizations
Bloghttps://paperswithcode.com/blog
Postshttps://paperswithcode.com/posts
Daily Papershttps://paperswithcode.com/papers
Hardwarehttps://paperswithcode.com/hardware
Learnhttps://paperswithcode.com/learn
Discordhttps://paperswithcode.com/join/discord
Forumhttps://discuss.huggingface.co/
GitHubhttps://github.com/huggingface
Team & Enterprisehttps://paperswithcode.com/enterprise
Hugging Face PROhttps://paperswithcode.com/pro
Enterprise Supporthttps://paperswithcode.com/support
Inference Providershttps://paperswithcode.com/inference/models
Inference Endpointshttps://paperswithcode.com/inference-endpoints
Storage Bucketshttps://paperswithcode.com/storage
Log Inhttps://paperswithcode.com/login
Sign Uphttps://paperswithcode.com/join
Subscribehttps://paperswithcode.com/login?next=%2Fpapers
AKhttps://paperswithcode.com/akhaliq
https://paperswithcode.com/papers
https://paperswithcode.com/papers/2604.05018
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writinghttps://paperswithcode.com/papers/2604.05018
Upvote 12 https://paperswithcode.com/login?next=%2Fpapers%2F2604.05018
GitHub 5.79khttps://github.com/google-research/paper-orchestra
arXiv Pagehttps://arxiv.org/abs/2604.05018
https://paperswithcode.com/papers/2604.05018
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writinghttps://paperswithcode.com/papers/2604.05018
Upvote 12 https://paperswithcode.com/login?next=%2Fpapers%2F2604.05018
GitHub 5.79khttps://github.com/google-research/paper-orchestra
arXiv Pagehttps://arxiv.org/abs/2604.05018
https://paperswithcode.com/papers/2611.26603
Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depthhttps://paperswithcode.com/papers/2611.26603
Applehttps://paperswithcode.com/apple
Upvote 33 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26603
GitHub 354https://github.com/apple-aiml-research/ml-depth-pro-2
arXiv Pagehttps://arxiv.org/abs/2611.26603
https://paperswithcode.com/papers/2611.26603
Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depthhttps://paperswithcode.com/papers/2611.26603
Applehttps://paperswithcode.com/apple
Upvote 33 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26603
GitHub 354https://github.com/apple-aiml-research/ml-depth-pro-2
arXiv Pagehttps://arxiv.org/abs/2611.26603
https://paperswithcode.com/papers/2611.18397
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agenthttps://paperswithcode.com/papers/2611.18397
Upvote 150 https://paperswithcode.com/login?next=%2Fpapers%2F2611.18397
GitHub 1.24khttps://github.com/RainBowLuoCS/Gamer
arXiv Pagehttps://arxiv.org/abs/2611.18397
https://paperswithcode.com/papers/2611.18397
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agenthttps://paperswithcode.com/papers/2611.18397
Upvote 150 https://paperswithcode.com/login?next=%2Fpapers%2F2611.18397
GitHub 1.24khttps://github.com/RainBowLuoCS/Gamer
arXiv Pagehttps://arxiv.org/abs/2611.18397
https://paperswithcode.com/papers/2610.22732
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agentshttps://paperswithcode.com/papers/2610.22732
Microsoft Researchhttps://paperswithcode.com/MicrosoftResearch
Upvote 21 https://paperswithcode.com/login?next=%2Fpapers%2F2610.22732
GitHub 7.93khttps://github.com/microsoft/TokenEconomizer
arXiv Pagehttps://arxiv.org/abs/2610.22732
https://paperswithcode.com/papers/2610.22732
TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agentshttps://paperswithcode.com/papers/2610.22732
Microsoft Researchhttps://paperswithcode.com/MicrosoftResearch
Upvote 21 https://paperswithcode.com/login?next=%2Fpapers%2F2610.22732
GitHub 7.93khttps://github.com/microsoft/TokenEconomizer
arXiv Pagehttps://arxiv.org/abs/2610.22732
https://paperswithcode.com/papers/2611.23144
π^4: A Foundation Model for 4D Scene Geometry and Motionhttps://paperswithcode.com/papers/2611.23144
Shanghai AI Laboratoryhttps://paperswithcode.com/Shanghai-AI-Laboratory
Upvote 18 https://paperswithcode.com/login?next=%2Fpapers%2F2611.23144
GitHub 415https://github.com/yyfz/Pi4
arXiv Pagehttps://arxiv.org/abs/2611.23144
https://paperswithcode.com/papers/2611.23144
π^4: A Foundation Model for 4D Scene Geometry and Motionhttps://paperswithcode.com/papers/2611.23144
Shanghai AI Laboratoryhttps://paperswithcode.com/Shanghai-AI-Laboratory
Upvote 18 https://paperswithcode.com/login?next=%2Fpapers%2F2611.23144
GitHub 415https://github.com/yyfz/Pi4
arXiv Pagehttps://arxiv.org/abs/2611.23144
https://paperswithcode.com/papers/2412.20138
TradingAgents: Multi-Agents LLM Financial Trading Frameworkhttps://paperswithcode.com/papers/2412.20138
Upvote 169 https://paperswithcode.com/login?next=%2Fpapers%2F2412.20138
GitHub 123khttps://github.com/tauricresearch/tradingagents
arXiv Pagehttps://arxiv.org/abs/2412.20138
https://paperswithcode.com/papers/2412.20138
TradingAgents: Multi-Agents LLM Financial Trading Frameworkhttps://paperswithcode.com/papers/2412.20138
Upvote 169 https://paperswithcode.com/login?next=%2Fpapers%2F2412.20138
GitHub 123khttps://github.com/tauricresearch/tradingagents
arXiv Pagehttps://arxiv.org/abs/2412.20138
https://paperswithcode.com/papers/2610.14224
Harness^2: Recursive Agent Harnessing for an Open Worldhttps://paperswithcode.com/papers/2610.14224
Googlehttps://paperswithcode.com/google
Upvote 70 https://paperswithcode.com/login?next=%2Fpapers%2F2610.14224
GitHub 24.7khttps://github.com/google-research/harness2
arXiv Pagehttps://arxiv.org/abs/2610.14224
https://paperswithcode.com/papers/2610.14224
Harness^2: Recursive Agent Harnessing for an Open Worldhttps://paperswithcode.com/papers/2610.14224
Googlehttps://paperswithcode.com/google
Upvote 70 https://paperswithcode.com/login?next=%2Fpapers%2F2610.14224
GitHub 24.7khttps://github.com/google-research/harness2
arXiv Pagehttps://arxiv.org/abs/2610.14224
https://paperswithcode.com/papers/2609.18063
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Predictionhttps://paperswithcode.com/papers/2609.18063
Edge0https://paperswithcode.com/Edge0
Upvote 37 https://paperswithcode.com/login?next=%2Fpapers%2F2609.18063
GitHub 12.2khttps://github.com/Edge0-AI/edge0
arXiv Pagehttps://arxiv.org/abs/2609.18063
https://paperswithcode.com/papers/2609.18063
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Predictionhttps://paperswithcode.com/papers/2609.18063
Edge0https://paperswithcode.com/Edge0
Upvote 37 https://paperswithcode.com/login?next=%2Fpapers%2F2609.18063
GitHub 12.2khttps://github.com/Edge0-AI/edge0
arXiv Pagehttps://arxiv.org/abs/2609.18063
https://paperswithcode.com/papers/2502.11880
Bitnet.cpp: Efficient Edge Inference for Ternary LLMshttps://paperswithcode.com/papers/2502.11880
Upvote 22 https://paperswithcode.com/login?next=%2Fpapers%2F2502.11880
GitHub 42.4khttps://github.com/microsoft/BitNet
arXiv Pagehttps://arxiv.org/abs/2502.11880
https://paperswithcode.com/papers/2502.11880
Bitnet.cpp: Efficient Edge Inference for Ternary LLMshttps://paperswithcode.com/papers/2502.11880
Upvote 22 https://paperswithcode.com/login?next=%2Fpapers%2F2502.11880
GitHub 42.4khttps://github.com/microsoft/BitNet
arXiv Pagehttps://arxiv.org/abs/2502.11880
https://paperswithcode.com/papers/2309.06180
Efficient Memory Management for Large Language Model Serving with PagedAttentionhttps://paperswithcode.com/papers/2309.06180
Upvote 78 https://paperswithcode.com/login?next=%2Fpapers%2F2309.06180
GitHub 86.1khttps://github.com/vllm-project/vllm
arXiv Pagehttps://arxiv.org/abs/2309.06180
https://paperswithcode.com/papers/2309.06180
Efficient Memory Management for Large Language Model Serving with PagedAttentionhttps://paperswithcode.com/papers/2309.06180
Upvote 78 https://paperswithcode.com/login?next=%2Fpapers%2F2309.06180
GitHub 86.1khttps://github.com/vllm-project/vllm
arXiv Pagehttps://arxiv.org/abs/2309.06180
https://paperswithcode.com/papers/2606.23050
Unlimited OCR Workshttps://paperswithcode.com/papers/2606.23050
BAIDUhttps://paperswithcode.com/baidu
Upvote 106 https://paperswithcode.com/login?next=%2Fpapers%2F2606.23050
GitHub 31.6khttps://github.com/baidu/Unlimited-OCR
arXiv Pagehttps://arxiv.org/abs/2606.23050
https://paperswithcode.com/papers/2606.23050
Unlimited OCR Workshttps://paperswithcode.com/papers/2606.23050
BAIDUhttps://paperswithcode.com/baidu
Upvote 106 https://paperswithcode.com/login?next=%2Fpapers%2F2606.23050
GitHub 31.6khttps://github.com/baidu/Unlimited-OCR
arXiv Pagehttps://arxiv.org/abs/2606.23050
https://paperswithcode.com/papers/2608.16157
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Executionhttps://paperswithcode.com/papers/2608.16157
University of California, Berkeleyhttps://paperswithcode.com/UCBerkeley
Upvote 110 https://paperswithcode.com/login?next=%2Fpapers%2F2608.16157
GitHub 17.6khttps://github.com/FlashML-org/FreeToken
arXiv Pagehttps://arxiv.org/abs/2608.16157
https://paperswithcode.com/papers/2608.16157
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Executionhttps://paperswithcode.com/papers/2608.16157
University of California, Berkeleyhttps://paperswithcode.com/UCBerkeley
Upvote 110 https://paperswithcode.com/login?next=%2Fpapers%2F2608.16157
GitHub 17.6khttps://github.com/FlashML-org/FreeToken
arXiv Pagehttps://arxiv.org/abs/2608.16157
https://paperswithcode.com/papers/2407.16741
OpenDevin: An Open Platform for AI Software Developers as Generalist Agentshttps://paperswithcode.com/papers/2407.16741
Upvote 87 https://paperswithcode.com/login?next=%2Fpapers%2F2407.16741
GitHub 94khttps://github.com/opendevin/opendevin
arXiv Pagehttps://arxiv.org/abs/2407.16741
https://paperswithcode.com/papers/2407.16741
OpenDevin: An Open Platform for AI Software Developers as Generalist Agentshttps://paperswithcode.com/papers/2407.16741
Upvote 87 https://paperswithcode.com/login?next=%2Fpapers%2F2407.16741
GitHub 94khttps://github.com/opendevin/opendevin
arXiv Pagehttps://arxiv.org/abs/2407.16741
https://paperswithcode.com/papers/2506.13771
LittleBit: Ultra Low-Bit Quantization via Latent Factorizationhttps://paperswithcode.com/papers/2506.13771
Upvote 2 https://paperswithcode.com/login?next=%2Fpapers%2F2506.13771
GitHub 758https://github.com/SamsungLabs/LittleBit
arXiv Pagehttps://arxiv.org/abs/2506.13771
https://paperswithcode.com/papers/2506.13771
LittleBit: Ultra Low-Bit Quantization via Latent Factorizationhttps://paperswithcode.com/papers/2506.13771
Upvote 2 https://paperswithcode.com/login?next=%2Fpapers%2F2506.13771
GitHub 758https://github.com/SamsungLabs/LittleBit
arXiv Pagehttps://arxiv.org/abs/2506.13771
https://paperswithcode.com/papers/2508.16279
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applicationshttps://paperswithcode.com/papers/2508.16279
Upvote 73 https://paperswithcode.com/login?next=%2Fpapers%2F2508.16279
GitHub 36.5khttps://github.com/agentscope-ai/agentscope
arXiv Pagehttps://arxiv.org/abs/2508.16279
https://paperswithcode.com/papers/2508.16279
AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applicationshttps://paperswithcode.com/papers/2508.16279
Upvote 73 https://paperswithcode.com/login?next=%2Fpapers%2F2508.16279
GitHub 36.5khttps://github.com/agentscope-ai/agentscope
arXiv Pagehttps://arxiv.org/abs/2508.16279
https://paperswithcode.com/papers/2407.17789
Very Large-Scale Multi-Agent Simulation in AgentScopehttps://paperswithcode.com/papers/2407.17789
Upvote 39 https://paperswithcode.com/login?next=%2Fpapers%2F2407.17789
GitHub 36.5khttps://github.com/modelscope/agentscope
arXiv Pagehttps://arxiv.org/abs/2407.17789
https://paperswithcode.com/papers/2407.17789
Very Large-Scale Multi-Agent Simulation in AgentScopehttps://paperswithcode.com/papers/2407.17789
Upvote 39 https://paperswithcode.com/login?next=%2Fpapers%2F2407.17789
GitHub 36.5khttps://github.com/modelscope/agentscope
arXiv Pagehttps://arxiv.org/abs/2407.17789
https://paperswithcode.com/papers/2508.19205
VibeVoice Technical Reporthttps://paperswithcode.com/papers/2508.19205
Microsoft Researchhttps://paperswithcode.com/MicrosoftResearch
Upvote 187 https://paperswithcode.com/login?next=%2Fpapers%2F2508.19205
GitHub 57.5khttps://github.com/microsoft/VibeVoice
arXiv Pagehttps://arxiv.org/abs/2508.19205
https://paperswithcode.com/papers/2508.19205
VibeVoice Technical Reporthttps://paperswithcode.com/papers/2508.19205
Microsoft Researchhttps://paperswithcode.com/MicrosoftResearch
Upvote 187 https://paperswithcode.com/login?next=%2Fpapers%2F2508.19205
GitHub 57.5khttps://github.com/microsoft/VibeVoice
arXiv Pagehttps://arxiv.org/abs/2508.19205
https://paperswithcode.com/papers/2509.22186
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsinghttps://paperswithcode.com/papers/2509.22186
Upvote 185 https://paperswithcode.com/login?next=%2Fpapers%2F2509.22186
GitHub 84.1khttps://github.com/opendatalab/MinerU
arXiv Pagehttps://arxiv.org/abs/2509.22186
https://paperswithcode.com/papers/2509.22186
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsinghttps://paperswithcode.com/papers/2509.22186
Upvote 185 https://paperswithcode.com/login?next=%2Fpapers%2F2509.22186
GitHub 84.1khttps://github.com/opendatalab/MinerU
arXiv Pagehttps://arxiv.org/abs/2509.22186
https://paperswithcode.com/papers/2611.26409
WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understandinghttps://paperswithcode.com/papers/2611.26409
Tencenthttps://paperswithcode.com/tencent
Upvote 45 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26409
GitHub 68https://github.com/Tencent/WeMM-Video
arXiv Pagehttps://arxiv.org/abs/2611.26409
https://paperswithcode.com/papers/2611.26409
WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understandinghttps://paperswithcode.com/papers/2611.26409
Tencenthttps://paperswithcode.com/tencent
Upvote 45 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26409
GitHub 68https://github.com/Tencent/WeMM-Video
arXiv Pagehttps://arxiv.org/abs/2611.26409
https://paperswithcode.com/papers/2604.14141
Geometric Context Transformer for Streaming 3D Reconstructionhttps://paperswithcode.com/papers/2604.14141
Robbyanthttps://paperswithcode.com/robbyant
Upvote 40 https://paperswithcode.com/login?next=%2Fpapers%2F2604.14141
GitHub 18.9khttps://github.com/robbyant/lingbot-map
arXiv Pagehttps://arxiv.org/abs/2604.14141
https://paperswithcode.com/papers/2604.14141
Geometric Context Transformer for Streaming 3D Reconstructionhttps://paperswithcode.com/papers/2604.14141
Robbyanthttps://paperswithcode.com/robbyant
Upvote 40 https://paperswithcode.com/login?next=%2Fpapers%2F2604.14141
GitHub 18.9khttps://github.com/robbyant/lingbot-map
arXiv Pagehttps://arxiv.org/abs/2604.14141
https://paperswithcode.com/papers/2611.21339
MovieRoll: A Systematic Framework for Rolling Out Long-Form Videoshttps://paperswithcode.com/papers/2611.21339
Upvote 13 https://paperswithcode.com/login?next=%2Fpapers%2F2611.21339
GitHub 227https://github.com/Tencent-Hunyuan/MovieRoll
arXiv Pagehttps://arxiv.org/abs/2611.21339
https://paperswithcode.com/papers/2611.21339
MovieRoll: A Systematic Framework for Rolling Out Long-Form Videoshttps://paperswithcode.com/papers/2611.21339
Upvote 13 https://paperswithcode.com/login?next=%2Fpapers%2F2611.21339
GitHub 227https://github.com/Tencent-Hunyuan/MovieRoll
arXiv Pagehttps://arxiv.org/abs/2611.21339
https://paperswithcode.com/papers/2605.03042
ARIS: Autonomous Research via Adversarial Multi-Agent Collaborationhttps://paperswithcode.com/papers/2605.03042
Shanghai Jiao Tong Universityhttps://paperswithcode.com/SJTU
Upvote 158 https://paperswithcode.com/login?next=%2Fpapers%2F2605.03042
GitHub 19.6khttps://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
arXiv Pagehttps://arxiv.org/abs/2605.03042
https://paperswithcode.com/papers/2605.03042
ARIS: Autonomous Research via Adversarial Multi-Agent Collaborationhttps://paperswithcode.com/papers/2605.03042
Shanghai Jiao Tong Universityhttps://paperswithcode.com/SJTU
Upvote 158 https://paperswithcode.com/login?next=%2Fpapers%2F2605.03042
GitHub 19.6khttps://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
arXiv Pagehttps://arxiv.org/abs/2605.03042
https://paperswithcode.com/papers/2504.19413
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memoryhttps://paperswithcode.com/papers/2504.19413
Upvote 79 https://paperswithcode.com/login?next=%2Fpapers%2F2504.19413
GitHub 69.3khttps://github.com/mem0ai/mem0
arXiv Pagehttps://arxiv.org/abs/2504.19413
https://paperswithcode.com/papers/2504.19413
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memoryhttps://paperswithcode.com/papers/2504.19413
Upvote 79 https://paperswithcode.com/login?next=%2Fpapers%2F2504.19413
GitHub 69.3khttps://github.com/mem0ai/mem0
arXiv Pagehttps://arxiv.org/abs/2504.19413
https://paperswithcode.com/papers/2611.20992
MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understandinghttps://paperswithcode.com/papers/2611.20992
The Chinese University of Hong Konghttps://paperswithcode.com/CUHK-CSE
Upvote 12 https://paperswithcode.com/login?next=%2Fpapers%2F2611.20992
GitHub 160https://github.com/zfkarl/MedJev
arXiv Pagehttps://arxiv.org/abs/2611.20992
https://paperswithcode.com/papers/2611.20992
MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understandinghttps://paperswithcode.com/papers/2611.20992
The Chinese University of Hong Konghttps://paperswithcode.com/CUHK-CSE
Upvote 12 https://paperswithcode.com/login?next=%2Fpapers%2F2611.20992
GitHub 160https://github.com/zfkarl/MedJev
arXiv Pagehttps://arxiv.org/abs/2611.20992
https://paperswithcode.com/papers/2606.03264
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Traininghttps://paperswithcode.com/papers/2606.03264
PaddlePaddlehttps://paperswithcode.com/PaddlePaddle
Upvote 27 https://paperswithcode.com/login?next=%2Fpapers%2F2606.03264
GitHub 93khttps://github.com/PaddlePaddle/PaddleOCR
arXiv Pagehttps://arxiv.org/abs/2606.03264
https://paperswithcode.com/papers/2606.03264
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Traininghttps://paperswithcode.com/papers/2606.03264
PaddlePaddlehttps://paperswithcode.com/PaddlePaddle
Upvote 27 https://paperswithcode.com/login?next=%2Fpapers%2F2606.03264
GitHub 93khttps://github.com/PaddlePaddle/PaddleOCR
arXiv Pagehttps://arxiv.org/abs/2606.03264
https://paperswithcode.com/papers/2508.02739
Kronos: A Foundation Model for the Language of Financial Marketshttps://paperswithcode.com/papers/2508.02739
Upvote 67 https://paperswithcode.com/login?next=%2Fpapers%2F2508.02739
GitHub 48.1khttps://github.com/shiyu-coder/Kronos
arXiv Pagehttps://arxiv.org/abs/2508.02739
https://paperswithcode.com/papers/2508.02739
Kronos: A Foundation Model for the Language of Financial Marketshttps://paperswithcode.com/papers/2508.02739
Upvote 67 https://paperswithcode.com/login?next=%2Fpapers%2F2508.02739
GitHub 48.1khttps://github.com/shiyu-coder/Kronos
arXiv Pagehttps://arxiv.org/abs/2508.02739
https://paperswithcode.com/papers/2006.15704
PyTorch Distributed: Experiences on Accelerating Data Parallel Traininghttps://paperswithcode.com/papers/2006.15704
Upvote 15 https://paperswithcode.com/login?next=%2Fpapers%2F2006.15704
GitHub 106khttps://github.com/pytorch/pytorch
arXiv Pagehttps://arxiv.org/abs/2006.15704
https://paperswithcode.com/papers/2006.15704
PyTorch Distributed: Experiences on Accelerating Data Parallel Traininghttps://paperswithcode.com/papers/2006.15704
Upvote 15 https://paperswithcode.com/login?next=%2Fpapers%2F2006.15704
GitHub 106khttps://github.com/pytorch/pytorch
arXiv Pagehttps://arxiv.org/abs/2006.15704
https://paperswithcode.com/papers/1910.03771
HuggingFace's Transformers: State-of-the-art Natural Language Processinghttps://paperswithcode.com/papers/1910.03771
Hugging Facehttps://paperswithcode.com/huggingface
Upvote 35 https://paperswithcode.com/login?next=%2Fpapers%2F1910.03771
GitHub 169khttps://github.com/huggingface/transformers
arXiv Pagehttps://arxiv.org/abs/1910.03771
https://paperswithcode.com/papers/1910.03771
HuggingFace's Transformers: State-of-the-art Natural Language Processinghttps://paperswithcode.com/papers/1910.03771
Hugging Facehttps://paperswithcode.com/huggingface
Upvote 35 https://paperswithcode.com/login?next=%2Fpapers%2F1910.03771
GitHub 169khttps://github.com/huggingface/transformers
arXiv Pagehttps://arxiv.org/abs/1910.03771
https://paperswithcode.com/papers/2611.24738
Jeveration: System One Models Now Generatehttps://paperswithcode.com/papers/2611.24738
National University of Singaporehttps://paperswithcode.com/NUS-DSA3101
Upvote 149 https://paperswithcode.com/login?next=%2Fpapers%2F2611.24738
GitHub 103https://github.com/Carol-lyh/Jeveration
arXiv Pagehttps://arxiv.org/abs/2611.24738
https://paperswithcode.com/papers/2611.24738
Jeveration: System One Models Now Generatehttps://paperswithcode.com/papers/2611.24738
National University of Singaporehttps://paperswithcode.com/NUS-DSA3101
Upvote 149 https://paperswithcode.com/login?next=%2Fpapers%2F2611.24738
GitHub 103https://github.com/Carol-lyh/Jeveration
arXiv Pagehttps://arxiv.org/abs/2611.24738
https://paperswithcode.com/papers/2503.11576
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversionhttps://paperswithcode.com/papers/2503.11576
IBM Granitehttps://paperswithcode.com/ibm-granite
Upvote 178 https://paperswithcode.com/login?next=%2Fpapers%2F2503.11576
GitHub 70.9khttps://github.com/docling-project/docling
arXiv Pagehttps://arxiv.org/abs/2503.11576
https://paperswithcode.com/papers/2503.11576
SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversionhttps://paperswithcode.com/papers/2503.11576
IBM Granitehttps://paperswithcode.com/ibm-granite
Upvote 178 https://paperswithcode.com/login?next=%2Fpapers%2F2503.11576
GitHub 70.9khttps://github.com/docling-project/docling
arXiv Pagehttps://arxiv.org/abs/2503.11576
https://paperswithcode.com/papers/2603.16790
InCoder-32B: Code Foundation Model for Industrial Scenarioshttps://paperswithcode.com/papers/2603.16790
Beihang Universityhttps://paperswithcode.com/Beihang
Upvote 169 https://paperswithcode.com/login?next=%2Fpapers%2F2603.16790
GitHub 297https://github.com/CSJianYang/Industrial-Coder
arXiv Pagehttps://arxiv.org/abs/2603.16790
https://paperswithcode.com/papers/2603.16790
InCoder-32B: Code Foundation Model for Industrial Scenarioshttps://paperswithcode.com/papers/2603.16790
Beihang Universityhttps://paperswithcode.com/Beihang
Upvote 169 https://paperswithcode.com/login?next=%2Fpapers%2F2603.16790
GitHub 297https://github.com/CSJianYang/Industrial-Coder
arXiv Pagehttps://arxiv.org/abs/2603.16790
https://paperswithcode.com/papers/2512.14692
Native and Compact Structured Latents for 3D Generationhttps://paperswithcode.com/papers/2512.14692
Microsofthttps://paperswithcode.com/microsoft
Upvote 11 https://paperswithcode.com/login?next=%2Fpapers%2F2512.14692
GitHub 13.1khttps://github.com/microsoft/TRELLIS.2
arXiv Pagehttps://arxiv.org/abs/2512.14692
https://paperswithcode.com/papers/2512.14692
Native and Compact Structured Latents for 3D Generationhttps://paperswithcode.com/papers/2512.14692
Microsofthttps://paperswithcode.com/microsoft
Upvote 11 https://paperswithcode.com/login?next=%2Fpapers%2F2512.14692
GitHub 13.1khttps://github.com/microsoft/TRELLIS.2
arXiv Pagehttps://arxiv.org/abs/2512.14692
https://paperswithcode.com/papers/2510.12323
RAG-Anything: All-in-One RAG Frameworkhttps://paperswithcode.com/papers/2510.12323
Data Intelligence Lab@HKUhttps://paperswithcode.com/hkuds
Upvote 86 https://paperswithcode.com/login?next=%2Fpapers%2F2510.12323
GitHub 24.8khttps://github.com/HKUDS/RAG-Anything
arXiv Pagehttps://arxiv.org/abs/2510.12323
https://paperswithcode.com/papers/2510.12323
RAG-Anything: All-in-One RAG Frameworkhttps://paperswithcode.com/papers/2510.12323
Data Intelligence Lab@HKUhttps://paperswithcode.com/hkuds
Upvote 86 https://paperswithcode.com/login?next=%2Fpapers%2F2510.12323
GitHub 24.8khttps://github.com/HKUDS/RAG-Anything
arXiv Pagehttps://arxiv.org/abs/2510.12323
https://paperswithcode.com/papers/2605.31264
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillationhttps://paperswithcode.com/papers/2605.31264
shanghai ailab https://paperswithcode.com/ShanghaiAiLab
Upvote 130 https://paperswithcode.com/login?next=%2Fpapers%2F2605.31264
GitHub 26.8khttps://github.com/titanwings/colleague-skill
arXiv Pagehttps://arxiv.org/abs/2605.31264
https://paperswithcode.com/papers/2605.31264
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillationhttps://paperswithcode.com/papers/2605.31264
shanghai ailab https://paperswithcode.com/ShanghaiAiLab
Upvote 130 https://paperswithcode.com/login?next=%2Fpapers%2F2605.31264
GitHub 26.8khttps://github.com/titanwings/colleague-skill
arXiv Pagehttps://arxiv.org/abs/2605.31264
https://paperswithcode.com/papers/2611.20254
VoxMel TTS Technical Reporthttps://paperswithcode.com/papers/2611.20254
VoxDance-Labhttps://paperswithcode.com/VoxDance-Lab
Upvote 17 https://paperswithcode.com/login?next=%2Fpapers%2F2611.20254
GitHub 220https://github.com/VoxDance-Lab/VoxMel
arXiv Pagehttps://arxiv.org/abs/2611.20254
https://paperswithcode.com/papers/2611.20254
VoxMel TTS Technical Reporthttps://paperswithcode.com/papers/2611.20254
VoxDance-Labhttps://paperswithcode.com/VoxDance-Lab
Upvote 17 https://paperswithcode.com/login?next=%2Fpapers%2F2611.20254
GitHub 220https://github.com/VoxDance-Lab/VoxMel
arXiv Pagehttps://arxiv.org/abs/2611.20254
https://paperswithcode.com/papers/2410.17799
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversationhttps://paperswithcode.com/papers/2410.17799
Upvote 19 https://paperswithcode.com/login?next=%2Fpapers%2F2410.17799
GitHub 65khttps://github.com/karpathy/nanogpt
arXiv Pagehttps://arxiv.org/abs/2410.17799
https://paperswithcode.com/papers/2410.17799
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversationhttps://paperswithcode.com/papers/2410.17799
Upvote 19 https://paperswithcode.com/login?next=%2Fpapers%2F2410.17799
GitHub 65khttps://github.com/karpathy/nanogpt
arXiv Pagehttps://arxiv.org/abs/2410.17799
https://paperswithcode.com/papers/2611.23226
FastFrames: Video Generation at Interactive Latencyhttps://paperswithcode.com/papers/2611.23226
Applehttps://paperswithcode.com/apple
Upvote 32 https://paperswithcode.com/login?next=%2Fpapers%2F2611.23226
GitHub 122https://github.com/apple-aiml-research/ml-fastframes
arXiv Pagehttps://arxiv.org/abs/2611.23226
https://paperswithcode.com/papers/2611.23226
FastFrames: Video Generation at Interactive Latencyhttps://paperswithcode.com/papers/2611.23226
Applehttps://paperswithcode.com/apple
Upvote 32 https://paperswithcode.com/login?next=%2Fpapers%2F2611.23226
GitHub 122https://github.com/apple-aiml-research/ml-fastframes
arXiv Pagehttps://arxiv.org/abs/2611.23226
https://paperswithcode.com/papers/2305.10973
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldhttps://paperswithcode.com/papers/2305.10973
Upvote 42 https://paperswithcode.com/login?next=%2Fpapers%2F2305.10973
GitHub 35.8khttps://github.com/XingangPan/DragGAN
arXiv Pagehttps://arxiv.org/abs/2305.10973
https://paperswithcode.com/papers/2305.10973
Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifoldhttps://paperswithcode.com/papers/2305.10973
Upvote 42 https://paperswithcode.com/login?next=%2Fpapers%2F2305.10973
GitHub 35.8khttps://github.com/XingangPan/DragGAN
arXiv Pagehttps://arxiv.org/abs/2305.10973
https://paperswithcode.com/papers/2611.12806
Learning Heterogeneous Tactile Representation for General Dexterous Manipulationhttps://paperswithcode.com/papers/2611.12806
Robbyanthttps://paperswithcode.com/robbyant
Upvote 109 https://paperswithcode.com/login?next=%2Fpapers%2F2611.12806
GitHub 801https://github.com/Robbyant/lingbot-touch
arXiv Pagehttps://arxiv.org/abs/2611.12806
https://paperswithcode.com/papers/2611.12806
Learning Heterogeneous Tactile Representation for General Dexterous Manipulationhttps://paperswithcode.com/papers/2611.12806
Robbyanthttps://paperswithcode.com/robbyant
Upvote 109 https://paperswithcode.com/login?next=%2Fpapers%2F2611.12806
GitHub 801https://github.com/Robbyant/lingbot-touch
arXiv Pagehttps://arxiv.org/abs/2611.12806
https://paperswithcode.com/papers/2606.03748
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Modelshttps://paperswithcode.com/papers/2606.03748
Ultralyticshttps://paperswithcode.com/Ultralytics
Upvote 27 https://paperswithcode.com/login?next=%2Fpapers%2F2606.03748
GitHub 63.7khttps://github.com/ultralytics/ultralytics
arXiv Pagehttps://arxiv.org/abs/2606.03748
https://paperswithcode.com/papers/2606.03748
Ultralytics YOLO26: Unified Real-Time End-to-End Vision Modelshttps://paperswithcode.com/papers/2606.03748
Ultralyticshttps://paperswithcode.com/Ultralytics
Upvote 27 https://paperswithcode.com/login?next=%2Fpapers%2F2606.03748
GitHub 63.7khttps://github.com/ultralytics/ultralytics
arXiv Pagehttps://arxiv.org/abs/2606.03748
https://paperswithcode.com/papers/2611.22925
Code World Model 2.0: Towards Infinite Controllable Video Generationhttps://paperswithcode.com/papers/2611.22925
inclusionAIhttps://paperswithcode.com/inclusionAI
Upvote 20 https://paperswithcode.com/login?next=%2Fpapers%2F2611.22925
GitHub 164https://github.com/inclusionAI/CodeWorldModel
arXiv Pagehttps://arxiv.org/abs/2611.22925
https://paperswithcode.com/papers/2611.22925
Code World Model 2.0: Towards Infinite Controllable Video Generationhttps://paperswithcode.com/papers/2611.22925
inclusionAIhttps://paperswithcode.com/inclusionAI
Upvote 20 https://paperswithcode.com/login?next=%2Fpapers%2F2611.22925
GitHub 164https://github.com/inclusionAI/CodeWorldModel
arXiv Pagehttps://arxiv.org/abs/2611.22925
https://paperswithcode.com/papers/2611.21373
WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detectionhttps://paperswithcode.com/papers/2611.21373
Tencenthttps://paperswithcode.com/tencent
Upvote 56 https://paperswithcode.com/login?next=%2Fpapers%2F2611.21373
GitHub 51https://github.com/Tencent/WeVisForensics
arXiv Pagehttps://arxiv.org/abs/2611.21373
https://paperswithcode.com/papers/2611.21373
WeVisForensics: Self-Evolving Agent for Omni AI-Generated Video Detectionhttps://paperswithcode.com/papers/2611.21373
Tencenthttps://paperswithcode.com/tencent
Upvote 56 https://paperswithcode.com/login?next=%2Fpapers%2F2611.21373
GitHub 51https://github.com/Tencent/WeVisForensics
arXiv Pagehttps://arxiv.org/abs/2611.21373
https://paperswithcode.com/papers/2512.10685
Sharp Monocular View Synthesis in Less Than a Secondhttps://paperswithcode.com/papers/2512.10685
Applehttps://paperswithcode.com/apple
Upvote 31 https://paperswithcode.com/login?next=%2Fpapers%2F2512.10685
GitHub 9.2khttps://github.com/apple/ml-sharp
arXiv Pagehttps://arxiv.org/abs/2512.10685
https://paperswithcode.com/papers/2512.10685
Sharp Monocular View Synthesis in Less Than a Secondhttps://paperswithcode.com/papers/2512.10685
Applehttps://paperswithcode.com/apple
Upvote 31 https://paperswithcode.com/login?next=%2Fpapers%2F2512.10685
GitHub 9.2khttps://github.com/apple/ml-sharp
arXiv Pagehttps://arxiv.org/abs/2512.10685
https://paperswithcode.com/papers/2510.22200
LongCat-Video Technical Reporthttps://paperswithcode.com/papers/2510.22200
LongCathttps://paperswithcode.com/meituan-longcat
Upvote 45 https://paperswithcode.com/login?next=%2Fpapers%2F2510.22200
GitHub 9.64khttps://github.com/meituan-longcat/LongCat-Video
arXiv Pagehttps://arxiv.org/abs/2510.22200
https://paperswithcode.com/papers/2510.22200
LongCat-Video Technical Reporthttps://paperswithcode.com/papers/2510.22200
LongCathttps://paperswithcode.com/meituan-longcat
Upvote 45 https://paperswithcode.com/login?next=%2Fpapers%2F2510.22200
GitHub 9.64khttps://github.com/meituan-longcat/LongCat-Video
arXiv Pagehttps://arxiv.org/abs/2510.22200
https://paperswithcode.com/papers/2609.23088
OmniEdu: Open Foundation Models for Learning and Teachinghttps://paperswithcode.com/papers/2609.23088
Peking Universityhttps://paperswithcode.com/PekingUniversity
Upvote 55 https://paperswithcode.com/login?next=%2Fpapers%2F2609.23088
GitHub 1.33khttps://github.com/haolpku/Omni-Edu
arXiv Pagehttps://arxiv.org/abs/2609.23088
https://paperswithcode.com/papers/2609.23088
OmniEdu: Open Foundation Models for Learning and Teachinghttps://paperswithcode.com/papers/2609.23088
Peking Universityhttps://paperswithcode.com/PekingUniversity
Upvote 55 https://paperswithcode.com/login?next=%2Fpapers%2F2609.23088
GitHub 1.33khttps://github.com/haolpku/Omni-Edu
arXiv Pagehttps://arxiv.org/abs/2609.23088
https://paperswithcode.com/papers/2611.26510
AutoMaster: Autonomous Post-Training by Making the Same Model a Better Teacherhttps://paperswithcode.com/papers/2611.26510
RUC-AIBOXhttps://paperswithcode.com/RUC-AIBOX
Upvote 14 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26510
GitHub 23https://github.com/RUCAIBox/AutoMaster
arXiv Pagehttps://arxiv.org/abs/2611.26510
https://paperswithcode.com/papers/2611.26510
AutoMaster: Autonomous Post-Training by Making the Same Model a Better Teacherhttps://paperswithcode.com/papers/2611.26510
RUC-AIBOXhttps://paperswithcode.com/RUC-AIBOX
Upvote 14 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26510
GitHub 23https://github.com/RUCAIBox/AutoMaster
arXiv Pagehttps://arxiv.org/abs/2611.26510
https://paperswithcode.com/papers/2611.09501
e-means: outperforming k-means (in one-tenth the epochs)https://paperswithcode.com/papers/2611.09501
Metahttps://paperswithcode.com/meta
Upvote 22 https://paperswithcode.com/login?next=%2Fpapers%2F2611.09501
GitHub 41.9khttps://github.com/facebookresearch/faiss
arXiv Pagehttps://arxiv.org/abs/2611.09501
https://paperswithcode.com/papers/2611.09501
e-means: outperforming k-means (in one-tenth the epochs)https://paperswithcode.com/papers/2611.09501
Metahttps://paperswithcode.com/meta
Upvote 22 https://paperswithcode.com/login?next=%2Fpapers%2F2611.09501
GitHub 41.9khttps://github.com/facebookresearch/faiss
arXiv Pagehttps://arxiv.org/abs/2611.09501
https://paperswithcode.com/papers/2611.26414
ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brainhttps://paperswithcode.com/papers/2611.26414
ZYT AI Teamhttps://paperswithcode.com/ZYT-AI
Upvote 22 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26414
GitHub 25https://github.com/hzx122/ZeroVLN
arXiv Pagehttps://arxiv.org/abs/2611.26414
https://paperswithcode.com/papers/2611.26414
ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brainhttps://paperswithcode.com/papers/2611.26414
ZYT AI Teamhttps://paperswithcode.com/ZYT-AI
Upvote 22 https://paperswithcode.com/login?next=%2Fpapers%2F2611.26414
GitHub 25https://github.com/hzx122/ZeroVLN
arXiv Pagehttps://arxiv.org/abs/2611.26414
https://paperswithcode.com/papers/2609.33757
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Qualityhttps://paperswithcode.com/papers/2609.33757
Multimodal Art Projectionhttps://paperswithcode.com/m-a-p
Upvote 156 https://paperswithcode.com/login?next=%2Fpapers%2F2609.33757
GitHub 13.7khttps://github.com/multimodal-art-projection/YuE
arXiv Pagehttps://arxiv.org/abs/2609.33757
https://paperswithcode.com/papers/2609.33757
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Qualityhttps://paperswithcode.com/papers/2609.33757
Multimodal Art Projectionhttps://paperswithcode.com/m-a-p
Upvote 156 https://paperswithcode.com/login?next=%2Fpapers%2F2609.33757
GitHub 13.7khttps://github.com/multimodal-art-projection/YuE
arXiv Pagehttps://arxiv.org/abs/2609.33757
https://paperswithcode.com/papers/2604.07429
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agentshttps://paperswithcode.com/papers/2604.07429
National University of Singaporehttps://paperswithcode.com/NationalUniversityofSingapore
Upvote 60 https://paperswithcode.com/login?next=%2Fpapers%2F2604.07429
GitHub 356https://github.com/gameworld-project/gameworld
arXiv Pagehttps://arxiv.org/abs/2604.07429
https://paperswithcode.com/papers/2604.07429
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agentshttps://paperswithcode.com/papers/2604.07429
National University of Singaporehttps://paperswithcode.com/NationalUniversityofSingapore
Upvote 60 https://paperswithcode.com/login?next=%2Fpapers%2F2604.07429
GitHub 356https://github.com/gameworld-project/gameworld
arXiv Pagehttps://arxiv.org/abs/2604.07429
TOShttps://paperswithcode.com/terms-of-service
Privacyhttps://paperswithcode.com/privacy
Abouthttps://paperswithcode.com/huggingface
Careershttps://apply.workable.com/huggingface/
https://paperswithcode.com/
Modelshttps://paperswithcode.com/models
Datasetshttps://paperswithcode.com/datasets
Spaceshttps://paperswithcode.com/spaces
Pricinghttps://paperswithcode.com/pricing
Docshttps://paperswithcode.com/docs

Response headers:
Content-Typetext/html; charset=utf-8
X-Powered-Byhuggingface-moon
Via1.1 7189b8cad57dc2d1ab0dd5f90144f2a2.cloudfront.net (CloudFront)

Viewport: width=device-width, initial-scale=1.0, user-scalable=no


URLs of crawlers that visited me.