Jun Xiao

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

RLHF & Preference Learning (2)Reasoning & Chain-of-Thought (1)Code Generation & Program Synthesis (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Yongliang Shen (2)Teng Pan (1)Tengyu Pan (1)Yuchen Yan (1)

Papers (2)

Mar 18, 2026

2w ago

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution

LLMs can escape the trap of confidently wrong reasoning by co-evolving a generator and verifier from a single model, bootstrapping each other to break free from flawed consensus.

Teng Pan, Tengyu Pan, Yuchen Yan +7

Reasoning & Chain-of-Thought RLHF & Preference Learning

Mar 16, 2026

Aozhe Wang +52w ago

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning

By adversarially co-evolving code and test LLMs, Code-A1 achieves code generation performance on par with human-annotated training, while simultaneously boosting the LLM's ability to find bugs.

Aozhe Wang, Nan Zhou, Zhengxi Lu +3

Code Generation & Program Synthesis Red-Teaming & Adversarial Robustness RLHF & Preference Learning

Search

Jun Xiao

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)