Xiao Liang

Xiao Liang on Hugging Face Daily Papers: 8 papers, 1 in the top 3 of their day, 265 upvotes.

1. Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability 9 upvotes, #37 of 2026-02-03
2. Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models 46 upvotes, #4 of 2026-01-21
3. Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions 1 upvotes, #41 of 2025-12-03
4. Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR 47 upvotes, #5 of 2025-09-30
5. Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR 116 upvotes, #2 of 2025-08-25
6. Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs 35 upvotes, #6 of 2025-06-18
7. SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning 14 upvotes, #9 of 2025-06-16
8. TL;DR: Too Long, Do Re-weighting for Effcient LLM Reasoning Compression 3 upvotes, #35 of 2025-06-04

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.