MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 9 items • Updated 25 days ago • 66
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published Apr 13 • 144
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing Paper • 2602.12205 • Published Feb 13 • 83
RoboOmni: Proactive Robot Manipulation in Omni-modal Context Paper • 2510.23763 • Published Oct 27, 2025 • 62
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models Paper • 2510.13626 • Published Oct 15, 2025 • 48