TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 93
Rohit Kumar
Kumarkum96
AI & ML interests
computer vision
Recent Activity
upvoted a paper 1 day ago
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers? liked a model 1 day ago
autotrust/GEV-26B-DecideOrganizations
None yet