MARS: Enabling Autoregressive Models Multi-Token Generation Paper • 2604.07023 • Published 3 days ago • 26
GEditBench v2: A Human-Aligned Benchmark for General Image Editing Paper • 2603.28547 • Published 11 days ago • 33
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling Paper • 2603.25746 • Published 15 days ago • 154
AVControl: Efficient Framework for Training Audio-Visual Controls Paper • 2603.24793 • Published 16 days ago • 26