meta-models/Muse-Spark-Open-816B-A42B-NVFP4 Image-Text-to-Text • 822B • Updated 3 days ago • 87.1k • 256
Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL Paper • 2610.21439 • Published Oct 15 • 29
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight Paper • 2610.08077 • Published Oct 6 • 170