Collection by 
17 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2608.11924
Collection by 
Aug 15
-
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
Paper • 2607.00341 • Published -
J-CoT: Chain-of-Thought in J-Space
Paper • 2607.21981 • Published • 2 -
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 185 -
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Paper • 2608.09888 • Published • 783
Collection by 
Aug 17
-
InstanceControl: Controllable Complex Image Generation without Instance Labeling
Paper • 2606.31924 • Published • 16 -
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
Paper • 2606.30968 • Published • 29 -
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
Paper • 2607.05373 • Published • 67 -
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 192
Collection by 
3 days ago
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Paper • 2606.07591 • Published • 105 -
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 56 -
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
Paper • 2606.10728 • Published • 37 -
Towards Diverse Scientific Hypothesis Search with Large Language Models
Paper • 2606.10587 • Published • 3
Collection by 
15 days ago
-
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
Paper • 2506.09790 • Published • 53 -
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance
Paper • 2506.06444 • Published • 73 -
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Paper • 2506.11763 • Published • 74 -
Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research
Paper • 2502.04644 • Published • 4
Collection by 
30 days ago
-
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 185 -
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Paper • 2608.11924 • Published • 293 -
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Paper • 2608.13417 • Published • 59 -
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Paper • 2608.09888 • Published • 783
Collection by 
Aug 13
-
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Paper • 2607.02980 • Published • 85 -
Gemma 4 Technical Report
Paper • 2607.02770 • Published • 83 -
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Paper • 2607.03451 • Published • 36 -
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Paper • 2607.05804 • Published • 21
Collection by 
Aug 14
-
SIA: Self Improving AI with Harness & Weight Updates
Paper • 2605.27276 • Published • 17 -
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 33 -
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Paper • 2607.04439 • Published • 64 -
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Paper • 2607.04438 • Published • 65
Collection by 
Aug 13
-
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
Paper • 2603.12056 • Published • 34 -
Memento-Skills: Let Agents Design Agents
Paper • 2603.18743 • Published • 59 -
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Paper • 2603.15401 • Published • 20 -
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 56
Collection by 
28 days ago
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 31 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 24
Collection by 17 days ago
Collection by 30 days ago
-
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 185 -
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Paper • 2608.11924 • Published • 293 -
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Paper • 2608.13417 • Published • 59 -
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Paper • 2608.09888 • Published • 783
Collection by Aug 15
-
DiscoLoop: Looping Discrete Embeddings and Continuous Hidden States for Multi-hop Reasoning
Paper • 2607.00341 • Published -
J-CoT: Chain-of-Thought in J-Space
Paper • 2607.21981 • Published • 2 -
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 185 -
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Paper • 2608.09888 • Published • 783
Collection by Aug 13
-
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
Paper • 2607.02980 • Published • 85 -
Gemma 4 Technical Report
Paper • 2607.02770 • Published • 83 -
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
Paper • 2607.03451 • Published • 36 -
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Paper • 2607.05804 • Published • 21
Collection by Aug 17
-
InstanceControl: Controllable Complex Image Generation without Instance Labeling
Paper • 2606.31924 • Published • 16 -
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
Paper • 2606.30968 • Published • 29 -
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
Paper • 2607.05373 • Published • 67 -
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Paper • 2605.20025 • Published • 192
Collection by Aug 14
-
SIA: Self Improving AI with Harness & Weight Updates
Paper • 2605.27276 • Published • 17 -
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
Paper • 2606.13662 • Published • 33 -
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes
Paper • 2607.04439 • Published • 64 -
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog
Paper • 2607.04438 • Published • 65
Collection by 3 days ago
-
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
Paper • 2606.07591 • Published • 105 -
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 56 -
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
Paper • 2606.10728 • Published • 37 -
Towards Diverse Scientific Hypothesis Search with Large Language Models
Paper • 2606.10587 • Published • 3
Collection by Aug 13
-
XSkill: Continual Learning from Experience and Skills in Multimodal Agents
Paper • 2603.12056 • Published • 34 -
Memento-Skills: Let Agents Design Agents
Paper • 2603.18743 • Published • 59 -
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Paper • 2603.15401 • Published • 20 -
Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Paper • 2603.25158 • Published • 56
Collection by 15 days ago
-
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
Paper • 2506.09790 • Published • 53 -
Saffron-1: Towards an Inference Scaling Paradigm for LLM Safety Assurance
Paper • 2506.06444 • Published • 73 -
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
Paper • 2506.11763 • Published • 74 -
Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research
Paper • 2502.04644 • Published • 4
Collection by 28 days ago
-
EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters
Paper • 2402.04252 • Published • 31 -
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Paper • 2402.03749 • Published • 15 -
ScreenAI: A Vision-Language Model for UI and Infographics Understanding
Paper • 2402.04615 • Published • 45 -
EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss
Paper • 2402.05008 • Published • 24