The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation Paper • 2511.20256 • Published 14 days ago • 26
UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback Paper • 2511.01678 • Published Nov 3 • 34
Paper2Video: Automatic Video Generation from Scientific Papers Paper • 2510.05096 • Published Oct 6 • 116
Code2Video: A Code-centric Paradigm for Educational Video Generation Paper • 2510.01174 • Published Oct 1 • 33
Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models Paper • 2507.07484 • Published Jul 10 • 17
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Paper • 2505.23380 • Published May 29 • 22
DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles Paper • 2503.03651 • Published Mar 5 • 16
Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models Paper • 2503.01774 • Published Mar 3 • 44
PhotoDoodle: Learning Artistic Image Editing from Few-Shot Pairwise Data Paper • 2502.14397 • Published Feb 20 • 41