LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 6 days ago • 199
Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance Paper • 2606.19195 • Published 5 days ago • 114
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published 13 days ago • 165
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published 6 days ago • 73
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 14 days ago • 102
InterleaveThinker: Reinforcing Agentic Interleaved Generation Paper • 2606.13679 • Published 11 days ago • 80
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 12 days ago • 115
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 25 days ago • 246
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security Paper • 2605.29801 • Published 25 days ago • 144
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 26 days ago • 429
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints Paper • 2605.21085 • Published May 20 • 5
ECHO: Terminal Agents Learn World Models for Free Paper • 2605.24517 • Published about 1 month ago • 7