🧑‍🔬 Lei Bai

🏛️ Affiliations

🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2026 · 7 paperscurrent🎓Nankai UniversityTianjin · China2026 · 1 papercurrent

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. SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing (2025 · 20 citations)
   LLM-written literature surveys still lag well behind human ones. Their outlines are often badly organized, with sections too broad, too narrow, too deep or too shallow. Their reference lists tend to include marginal works and miss the field's most influential papers. Evaluation of such systems has also mostly relied…
2. Intern-S1: A Scientific Multimodal Foundation Model (2025 · 19 citations)
   Open-source foundation models now rival proprietary ones in math, code and natural-image tasks, but they still lag far behind in science.
3. Nature-Inspired Population-Based Evolution of Large Language Models (2026 · 8 citations)
   The paper frames a new problem: how to improve a whole group of large language models by treating it as an evolving population rather than tuning one model.
4. Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning (2026 · 1 citation)
   Reinforcement learning for LLM reasoning usually depends either on expensive human-verified answers or on label-free rewards such as majority voting and entropy.
5. A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement (2026)
   Systems that combine several LLMs struggle to scale. Router-based approaches need retraining whenever a model is added or depend on coarse skill labels. Answer-selection approaches judge outputs with a single criterion and only pick from responses that already exist. SMCS (Scalable Multi-LLM Collaboration System)…
6. R³: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning (2026)
   Multi-step retrosynthesis means breaking a target molecule down, step by step, into purchasable building blocks.

All works

8 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey WritingAnnual Meeting of the Association for Computational Linguistics (ACL)Xiangchao Yan, Shiyang Feng, Jiakang Yuan, et al.2025 · 20 citations
2. Intern-S1: A Scientific Multimodal Foundation ModelarXiv:2508.15763Lei Bai, Zhongrui Cai, Yuhang Cao, et al.2025 · 19 citations
3. Nature-Inspired Population-Based Evolution of Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Yiqun Zhang, Peng Ye, Xiaocui Yang, et al.2026 · 8 citations
4. Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement LearningFindings of the Association for Computational LinguisticsZhiyin Yu, Bo Zhang, Qibin Hou, et al.2026 · 1 citation
5. A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven EnhancementAnnual Meeting of the Association for Computational Linguistics (ACL)Shengji Tang, Jianjian Cao, Weihao Lin, et al.2026
6. R³: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement LearningAnnual Meeting of the Association for Computational Linguistics (ACL)YiFei Wang, Qizhi Pei, Jiangtao Feng, et al.2026
7. A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZhiyin Yu et al.2026
8. MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetYiqun Zhang et al.2026

🤝 Co-authors here

12 of 25 co-authors with a page, the most papers together first.

• Bo Zhang ×3
• Peng Ye ×2
• Shuyue Hu ×2
• Wanli Ouyang ×2
• Bin Wang
• Hao Zhou
• Haojiong Chen
• Jiangtao Feng
• Kai Chen
• Lijun Wu
• Maosong Cao
• Qizhi Pei

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) ×8: ACL 2026 ×3, ACL 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026

🔗 Cited by

Papers of our library cite their works 71 times (of the 149,439 papers whose bibliographies we read); 21 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/lei-bai/