DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published 19 days ago • 51
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 17 days ago • 163
PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking Paper • 2607.00115 • Published 15 days ago • 12
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 431
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks Paper • 2605.22535 • Published May 21 • 11