TRACE

Headlines · 2

1. Oct 18
   TRACE Models Daily Clinical Trajectories for Inpatient Risk Prediction

   Minjun Kim and Jong Hak Moon submitted TRACE to arXiv on October 19, 2026, introducing a daily-scale framework for predicting in-hospital mortality, prolonged length of stay, and readmission. TRACE organizes EHR data, chest X-rays, radiology reports, and discharge summaries into temporal trajectories while allowing unavailable modalities to contribute no tokens. The paper reports the highest AUROC across all nine dataset-task settings on MIMIC-IV, eICU, and MIMIC-III, with the highest accuracy in eight settings.

   Hugging Face · Papers · 🔥 0
2. Oct 5
   TRACE Aligns FP4 Training and Rollout for MoE Reinforcement Learning

   Alibaba Qwen and Ohio State University researchers proposed TRACE, a framework that uses rollout-side FP4 quantization outcomes to guide training-side rounding for reinforcement learning of MoE language models. Evaluated on four models across reasoning, coding, and long-horizon RL tasks, the authors report performance comparable to BF16 rollout with joint FP4 weights, activations, and KV cache, plus up to a 5.4× rollout speedup. A compact caching scheme stores selected mantissa and scale information to reduce the overhead of transferring rollout guidance.

   Hugging Face · Papers · 🔥 0

Experience and discussion from the community

Share my TRACE experienceAsk about TRACE

All

AI Coding Makers•寒蝉•3d

BossKey-Stock — A Terminal Market-Watching Tool for Slacking Off

BossKey-Stock is a pure terminal-based real-time market monitoring tool for A-shares. No need to open a browser, switch windows, or use an API Key. Press Enter after bosskey, and your terminal becomes a market dashboard full of red and green figures. When you hear someone approaching, press b, and it turns into a perfectly respectable Docker build log. One-Click Installation pip install bosskey-s…

Translated from Chinese by AI · See original

DockerPython

github.comhttps://github.com/hancic128/bosskey-stock