Xiao Liang

MasterVito's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper about 2 hours ago

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Paper • 2601.14004 • Published 2 days ago • 41

authored a paper about 2 months ago

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions

Paper • 2512.00097 • Published Nov 27, 2025 • 2

authored a paper 4 months ago

Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR

Paper • 2509.23808 • Published Sep 28, 2025 • 47

authored a paper 5 months ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19, 2025 • 118

authored 3 papers 7 months ago

TL;DR: Too Long, Do Re-weighting for Effcient LLM Reasoning Compression

Paper • 2506.02678 • Published Jun 3, 2025 • 5

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

Paper • 2506.14245 • Published Jun 17, 2025 • 45

SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning

Paper • 2506.08989 • Published Jun 10, 2025 • 14