World Action Models: The Next Frontier in Embodied AI Paper • 2605.12090 • Published 23 days ago • 67
MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 7 items • Updated May 2 • 63
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published Apr 13 • 144