From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 more institutions on single bylines are not listed.

Fields, topics and concepts

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

📚 Shelves 6Arts and Humanities · 4 works Computer Science · 4 works Artificial Intelligence · 4 works Language and Linguistics · 4 works Computer Vision and Pattern Recognition · 3 works Information Systems · 1 work

🧭 Topics 5Reasoning · 4 works Language models & pretraining · 3 works Evaluation & benchmarks · 1 work Vision & language · 1 work Efficient models & compression · 1 work

Works by year

2020s

20261 paper 20253 papers

Papers

The most cited first (OpenAlex and our library).

From System 1 to System 2: A Survey of Reasoning Large Language Models (2025 · 165 citations)
Conventional LLMs respond quickly and intuitively, much like the fast "System 1" of dual-process cognitive theory, but they often fail on problems that require careful multi-step analysis.
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025 · 30 citations)
Evaluation of document understanding has not kept pace with large vision-language models (LVLMs). Standard datasets such as DocVQA cover only single pages and are close to saturated. Multi-page sets like MP-DocVQA and DUDE stay under 20 pages and rarely test how models connect different layout elements.
TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning Compression (2025 · 8 citations)
Reasoning-focused LLMs that generate long Chain-of-Thought (CoT) often overthink, spending many tokens even on easy questions. Existing compression approaches usually need laborious data labeling, model interpolation (as in CoT-Valve), or costly RL with length penalties.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026 · 6 citations)
Scaling laws are well established for LLM pre-training, but little is known about how they behave when reinforcement learning is applied after pre-training.

All works

5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

From System 1 to System 2: A Survey of Reasoning Large Language ModelsarXiv:2502.17419Zhong-Zhi Li, Duzhen Zhang, Ming-Liang Zhang, et al.2025 · 165 citations
RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems? ↗arXiv:2501.11284 · no summary yetHaotian Xu et al.2025 · 37 citations
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and LocatingAnnual Meeting of the Association for Computational Linguistics (ACL)Chao Deng, Jiale Yuan, Pi Bu, et al.2025 · 30 citations
TL;DR: Too Long, Do Re-weighting for Efficient LLM Reasoning CompressionarXiv:2506.02678Zhong-Zhi Li, Xiao Liang, Zihao Tang, et al.2025 · 8 citations
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Zelin Tan, Hejia Geng, Xiaohang Yu, et al.2026 · 6 citations

Co-authors here

12 of 23 co-authors with a page, the most papers together first.

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) ×2: ACL 2026, ACL 2025

Cited by

Papers of our library cite their works 214 times (of the 149,439 papers whose bibliographies we read); 65 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhong-zhi-li/

🧑‍🔬 Zhong-Zhi Li

🏛️ Affiliations

🧭 Fields, topics and concepts

📅 Works by year

2020s

📄 Papers

All works

🤝 Co-authors here

Venues

🔗 Cited by

Zhong-Zhi Li

Affiliations

Fields, topics and concepts

Works by year

Papers

Co-authors here

Cited by