Live page · Day archive

TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models

Read the original at HF Daily Papers

Summary

Researchers propose TRACE, an FP4 quantization framework for reinforcement learning of Mixture-of-Experts language models that aligns training and rollout paths to reduce discrepancy.

Carried by: HF Daily Papers. First seen: 2026-10-07T04:30:07Z.