LinkedIn

LinkedIn on Hugging Face Daily Papers: 5 papers, 0 in the top 3 of their day, 0 paper of the day.

  1. Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts 10 upvotes, #50 of 2026-10-08
  2. Smaller Models, Better Rejects: Preference Distillation Scaling 30 upvotes, #40 of 2026-10-02
  3. TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning 13 upvotes, #22 of 2026-07-01
  4. Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning 5 upvotes, #19 of 2026-02-27
  5. SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens 15 upvotes, #11 of 2025-11-03

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.