TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 88
I. Vasilyev
Scottchristopher
AI & ML interests
None yet
Recent Activity
upvoted a paper about 17 hours ago
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models upvoted a paper about 17 hours ago
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents upvoted a paper about 17 hours ago
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient SketchesOrganizations
None yet
upvoted 3
papers about 17 hours ago