Trending Papers - Hugging Face (original) (raw)
new
Get trending papers in your email inbox once a day!
Get trending papers in your email inbox!
by
AK and the research community
Submitted by
Paper99
Submitted by Paper99
Submitted by
Cxxs
Submitted by Cxxs
Submitted by
taesiri
Submitted by taesiri
Submitted by
Zuica96
Submitted by Zuica96
Submitted by
akhaliq
Submitted by akhaliq
Submitted by taesiri
DeepCode: Open Agentic Coding
DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.
- 5 authors
· Published on Dec 8, 2025
Submitted by taesiri
DeepCode: Open Agentic Coding
DeepCode, a fully autonomous framework, addresses the challenges of document-to-codebase synthesis by optimizing information flow through source compression, structured indexing, knowledge injection, and error correction, achieving state-of-the-art performance and surpassing human experts.
Submitted by
nuojohnchen
Submitted by nuojohnchen
Submitted by taesiri
SAM 3: Segment Anything with Concepts
Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.
Submitted by taesiri
SAM 3: Segment Anything with Concepts
Segment Anything Model 3 achieves state-of-the-art performance in promptable concept segmentation and tracking by leveraging a unified model architecture with decoupled recognition and localization.
LightRAG: Simple and Fast Retrieval-Augmented Generation
LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.
- 5 authors
· Published on Oct 8, 2024
Submitted by
wanderkid
Submitted by wanderkid
Submitted by taesiri
Submitted by taesiri
Submitted by
kenshinn
Submitted by kenshinn
Submitted by taesiri
LongCat-Image Technical Report
LongCat-Image is a bilingual open-source foundation model for image generation that addresses multilingual text rendering, photorealism, and deployment efficiency through rigorous data curation, compact design, and comprehensive open-source support.
LongCat · Published on Dec 8, 2025
Submitted by taesiri
LongCat-Image Technical Report
LongCat-Image is a bilingual open-source foundation model for image generation that addresses multilingual text rendering, photorealism, and deployment efficiency through rigorous data curation, compact design, and comprehensive open-source support.
Submitted by taesiri
Submitted by taesiri
Submitted by
Rbin
RAG-Anything: All-in-One RAG Framework
RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.
Submitted by Rbin
RAG-Anything: All-in-One RAG Framework
RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.
Submitted by
RuoyuFeng
Submitted by RuoyuFeng
Submitted by
Alicezrzhao
Submitted by Alicezrzhao
Submitted by akhaliq
Submitted by akhaliq
Submitted by akhaliq
Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.
· Published on Apr 28, 2025
Submitted by akhaliq
Submitted by taesiri
SAM 3D: 3Dfy Anything in Images
SAM 3D is a generative model that reconstructs 3D objects from single images using a multi-stage training framework that includes synthetic pretraining and real-world alignment, achieving high performance in human preference tests.
Submitted by taesiri
SAM 3D: 3Dfy Anything in Images
SAM 3D is a generative model that reconstructs 3D objects from single images using a multi-stage training framework that includes synthetic pretraining and real-world alignment, achieving high performance in human preference tests.
Submitted by
xandergos
Submitted by xandergos
Submitted by
fengerhu
MobiAgent: A Systematic Framework for Customizable Mobile Agents
MobiAgent, a comprehensive mobile agent system, achieves state-of-the-art performance in real-world mobile scenarios through its MobiMind-series models, AgentRR framework, and MobiFlow benchmarking suite, while also reducing data annotation costs.
· Published on Aug 30, 2025
Submitted by fengerhu
Submitted by
SereinH
Submitted by SereinH
Submitted by
wenyi
Submitted by wenyi
Submitted by
AdinaY
Submitted by AdinaY
Submitted by taesiri
Submitted by taesiri
Submitted by
Gynjn
Submitted by Gynjn
Submitted by akhaliq
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
UI-TARS, a native GUI agent model using screenshots as input, outperforms commercial models in various benchmarks through enhanced perception, unified action modeling, system-2 reasoning, and iterative training with reflective online traces.
· Published on Jan 21, 2025
Submitted by akhaliq
Submitted by
hiyouga
Submitted by hiyouga
Submitted by
Weiyun1025
Submitted by Weiyun1025
Submitted by
Jeff-Wang
Submitted by Jeff-Wang
Submitted by
dyyyyyyyy
Submitted by dyyyyyyyy
Submitted by
daixufang
Submitted by daixufang
Submitted by taesiri
Submitted by taesiri
Submitted by
KaituoFeng
Submitted by KaituoFeng
Submitted by
zhangshaolei
Submitted by zhangshaolei
Submitted by
Owen777
Submitted by Owen777
Submitted by
gaomingqi
Submitted by gaomingqi
Submitted by
Paranioar
Submitted by Paranioar
Submitted by
xw-eric
Submitted by xw-eric
Submitted by xw-eric
The Unreasonable Effectiveness of Scaling Agents for Computer Use
Behavior Best-of-N (bBoN) improves the reliability and success rates of computer-use agents by generating and selecting among multiple rollouts using behavior narratives, achieving state-of-the-art performance on OSWorld and strong generalization to different operating systems.
Simular · Published on Oct 2, 2025
Submitted by xw-eric
The Unreasonable Effectiveness of Scaling Agents for Computer Use
Behavior Best-of-N (bBoN) improves the reliability and success rates of computer-use agents by generating and selecting among multiple rollouts using behavior narratives, achieving state-of-the-art performance on OSWorld and strong generalization to different operating systems.