Subliminal Clocks: Latent Time Modelling in Diffusion Language Models Paper • 2607.01774 • Published 8 days ago • 38
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning Paper • 2606.31825 • Published 28 days ago • 29
LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents Paper • 2606.30697 • Published 29 days ago • 7
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning Paper • 2606.08572 • Published Jun 7 • 14
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters Paper • 2606.02437 • Published Jun 1 • 241
HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos Paper • 2605.17543 • Published May 19 • 15
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433