RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published 3 days ago • 69
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification Paper • 2607.01793 • Published 6 days ago • 7
OpenRath: Session-Centered Runtime State for Agent Systems Paper • 2606.19409 • Published 23 days ago • 77
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 24 days ago • 209
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 81
Self-Improving Language Models with Bidirectional Evolutionary Search Paper • 2605.28814 • Published May 27 • 61
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 431