TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 92
Austin Rodriguez
AUSTINRODR
·
AI & ML interests
Interested in machine learning, NLP and open source AI.
Recent Activity
upvoted a paper 11 days ago
LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches liked a dataset 18 days ago
Sohaibsoussi/patient_doctor_chatbotOrganizations
None yet
upvoted 2
papers 11 days ago