🧑‍🔬 Jian Liang

🏛️ Affiliations

🏛️Chinese Academy of SciencesBeijing · China2026 · 7 paperscurrent🔬Institute of AutomationBeijing · China2026 · 7 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2026 · 7 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 Fields, topics and concepts

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

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time (2026 · 2 citations)
   Test-Time Reinforcement Learning (TTRL) lets LLMs improve their reasoning on unlabeled test questions by using the majority-voted answer among sampled rollouts as a pseudo-reward.
2. Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning (2026)
   Test-time reinforcement learning (TTRL) lets an LLM improve on unlabeled test questions. It samples many answers, takes the majority vote as a pseudo-label, and trains with GRPO. Because rewards come only from the model's own outputs, wrong pseudo-labels introduce misleading training signals. The authors examine…

🤝 Co-authors here

4 co-authors with a page, the most papers together first.

• Ran He ×2
• Dong Yan
• Meng Wang
• Yanbo Wang

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 2 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 2 November 2026

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jian-liang/