Xiaorong Wang

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Reasoning & Chain-of-Thought (3)Inference & Quantization (2)Eval Frameworks & Benchmarks (1)Data Curation & Synthetic Data (1)RLHF & Preference Learning (1)

Frequent co-authors

Chaojun Xiao (3)Xiaoang Xu (2)Zhu Zhang (2)Jixun Wang (2)Siyuan Liu (1)Shuo Wang (1)Junlan Feng (1)Fanyu Meng (1)

Papers (3)

Sep 7, 2026

Tsinghua AISep 7, 2026·also Affiliation:

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

Chain-of-thought context can be halved without sacrificing accuracy by using the geometric trajectory of hidden states to selectively compress exploratory reasoning steps into continuous latent tokens.

Xiaoang Xu, Siyuan Liu, Shuo Wang +11

Inference & Quantization Reasoning & Chain-of-Thought

Aug 19, 2026

Tsinghua AIAug 19, 2026

Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning

Group-Calibrated On-Policy Distillation boosts long-context reasoning performance by reconciling teacher guidance with verifier feedback, achieving up to a 12-point increase in benchmark scores.

Zhu Zhang, Jixun Wang, Xiaoang Xu +5

Eval Frameworks & Benchmarks Inference & Quantization Reasoning & Chain-of-Thought

Jun 17, 2026

Tsinghua AIJun 17, 2026·also Affiliation:

Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning

A simple data recipe can outperform complex reward engineering in enhancing long-context reasoning for large language models.

Xiaoyue Xu, Si-Kui Zhang, Xiaorong Wang +1

Data Curation & Synthetic Data Reasoning & Chain-of-Thought RLHF & Preference Learning