Collection by 
11 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2609.15779
Collection by 
9 days ago
-
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Paper • 2604.28196 • Published • 26 -
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 355 -
Recursive Multi-Agent Systems
Paper • 2604.25917 • Published • 238 -
jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition
Paper • 2605.08384 • Published • 10
Collection by 
11 days ago
-
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Paper • 2506.19290 • Published • 53 -
Data Efficacy for Language Model Training
Paper • 2506.21545 • Published • 11 -
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
Paper • 2507.04009 • Published • 55 -
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Paper • 2507.03253 • Published • 19
Collection by 
11 days ago
-
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 28 -
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
Paper • 2607.21653 • Published • 33 -
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Paper • 2609.15779 • Published • 158
Collection by 1 day ago
-
EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale
Paper • 2604.17406 • Published • 5 -
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
Paper • 2605.15301 • Published • 21 -
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Paper • 2605.11739 • Published • 18 -
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Paper • 2605.18401 • Published • 79
Collection by 11 days ago
Collection by 11 days ago
-
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Paper • 2605.27366 • Published • 28 -
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
Paper • 2607.21653 • Published • 33 -
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
Paper • 2609.15779 • Published • 158
Collection by 9 days ago
-
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation
Paper • 2604.28196 • Published • 26 -
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 355 -
Recursive Multi-Agent Systems
Paper • 2604.25917 • Published • 238 -
jina-embeddings-v5-omni: Text-Geometry-Preserving Multimodal Embeddings via Frozen-Tower Composition
Paper • 2605.08384 • Published • 10
Collection by 1 day ago
-
EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale
Paper • 2604.17406 • Published • 5 -
Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
Paper • 2605.15301 • Published • 21 -
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
Paper • 2605.11739 • Published • 18 -
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Paper • 2605.18401 • Published • 79
Collection by 11 days ago
-
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Paper • 2506.19290 • Published • 53 -
Data Efficacy for Language Model Training
Paper • 2506.21545 • Published • 11 -
Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents
Paper • 2507.04009 • Published • 55 -
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Paper • 2507.03253 • Published • 19