LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 7 days ago • 201
DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects Paper • 2606.15133 • Published 10 days ago • 71
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published 7 days ago • 74
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 13 days ago • 117
Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts Paper • 2606.05922 • Published 19 days ago • 67
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published 20 days ago • 124
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published 22 days ago • 232
MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft Paper • 2605.30931 • Published 25 days ago • 11
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 27 days ago • 430