Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 10 days ago • 564
When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections Paper • 2609.32488 • Published 11 days ago • 26
CompoWorld: Compositional Environment Scaling for General Agents Paper • 2609.33665 • Published 10 days ago • 42
AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs Paper • 2609.31590 • Published 12 days ago • 13
Agent-Editing World Model: Rethinking World Modeling for LLM Agents Paper • 2609.28416 • Published 14 days ago • 43
Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings Paper • 2609.25165 • Published 16 days ago • 77
Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models Paper • 2609.24657 • Published 16 days ago • 40
Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies Paper • 2609.24682 • Published 16 days ago • 12
WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory Paper • 2609.24984 • Published 16 days ago • 157
GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning Paper • 2609.19315 • Published 21 days ago • 5
JEPA-Anything: Learning Predictive Models across Different Worlds Paper • 2609.20800 • Published 20 days ago • 76
Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model Paper • 2609.18323 • Published 21 days ago • 133
When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation Paper • 2609.20511 • Published 20 days ago • 114
Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control Paper • 2609.17909 • Published 22 days ago • 47
Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training Paper • 2609.14306 • Published 24 days ago • 20
ActionSplice: In-Flight Action Editing for Interactive World Models Paper • 2609.08230 • Published 29 days ago • 12