The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published Jun 11 • 113
StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration Paper • 2605.25659 • Published May 25 • 17
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published Apr 9 • 103
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers Paper • 2604.02648 • Published Apr 3 • 48
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published Mar 17 • 248