Xuehai He

Xuehai He has 2 papers in our library, in 2025, most of them on Language models & pretraining, Reasoning; often with Shuohang Wang, Baolin Peng, Hao Cheng.

2 papers in our library · 2025

No OpenAlex profile matched yet.

The profile is the library's match of the name; two people with one name are not always told apart.

Fields, topics and concepts

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

Reinforcement Learning for Reasoning in Large Language Models with One Training Example (2025 · 87 citations)
The paper asks how small a training set can be for reinforcement learning with verifiable reward (RLVR). RLVR is the outcome-rewarded RL now used to strengthen math reasoning in LLMs. The authors draw a random sample of 1,209 problems from the DeepScaleR dataset (DSR-sub). They rank each problem by how much its…
Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space (2025 · 25 citations)
Standard Chain-of-Thought (CoT) decoding forces an LLM to pick a single discrete token at every reasoning step.

12 of 14 co-authors with a page, the most papers together first.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 105 times (of the 149,439 papers whose bibliographies we read); 36 citing papers with a page here →.

Updated 2 November 2026