Xiao Liang
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
arXiv 2026
Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability
arXiv 2026
SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
arXiv 2025
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective
arXiv 2025
Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions
arXiv 2025
SAIL-VL2 Technical Report
arXiv 2025
Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR
arXiv 2025
Beyond the Exploration-Exploitation Trade-off: A Hidden State Approach for LLM Reasoning in RLVR
arXiv 2025
TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression
arXiv 2025
CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency
arXiv 2025
Integrative Decoding: Improve Factuality via Implicit Self-consistency
arXiv 2024
PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training
arXiv 2024
Affiliations
Frequent co-authors
10from 12 papers