🧑‍🔬 Wenjie Wang

🏛️ Affiliations

🎓National University of SingaporeSingapore · Singapore2020–2026 · 65 papersEducationcurrent🎓University of Science and Technology of ChinaHefei · China2023–2026 · 45 paperscurrent🏢Alibaba GroupHangzhou · China2025–2026 · 2 paperscurrent🎓Zhejiang UniversityHangzhou · China2025–2026 · 2 paperscurrent🏥First Affiliated Hospital of Kunming Medical UniversityKunming · China2026 · 1 papercurrent🎓Southwestern University of Finance and EconomicsChengdu · China2026 · 1 papercurrent🏥The First Hospital of KunmingKunming · China2026 · 1 papercurrent🎓Emory UniversityAtlanta · United States2020–2023 · 5 papers🎓Shandong UniversityJinan · China2018–2019 · 4 papers🏛️Chinese Academy of SciencesBeijing · China2006–2014 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 27 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. TokenSkip: Controllable Chain-of-Thought Compression in LLMs (2025 · 106 citations)
   Long chain-of-thought (CoT) outputs help LLMs reason better, but every extra generated token adds decoding time and key-value cache memory.
2. Personalized Generation In Large Model Era: A Survey (2025 · 24 citations)
   Work on generating content tailored to individual users has grown separately in NLP, computer vision and information retrieval.
3. Personalized Text Generation with Contrastive Activation Steering (2025 · 13 citations)
   The paper addresses personalized text generation: producing outputs, such as emails or headlines, that match an individual user's writing style as shown in their past texts.
4. MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation (2026 · 9 citations)
   Most reasoning benchmarks for LLMs test single-turn problems. Real problem solving is often interactive: a solver asks questions, gets feedback and revises its plan. Earlier multi-turn efforts such as MT-Bench and GameArena either focus on dialogue coherence or depend on costly human involvement.
5. PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models (2026 · 8 citations)
   LLMs used in emotionally sensitive settings often give generic or overly solution-focused replies instead of real emotional support.
6. Controllable LLM Reasoning via Sparse Autoencoder-Based Steering (2026 · 3 citations)
   Large Reasoning Models (LRMs) choose their own reasoning moves, such as re-checking or backtracking, and these choices can lead to wasted effort or wrong answers.

All works

7 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. FREE: Feature Refinement for Generalized Zero-Shot Learning ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetShiming Chen et al.2021 · 231 citations
2. TokenSkip: Controllable Chain-of-Thought Compression in LLMsConference on Empirical Methods in Natural Language Processing (EMNLP)Heming Xia, Chak Tou Leong, Wenjie Wang, et al.2025 · 106 citations
3. Personalized Generation In Large Model Era: A SurveyAnnual Meeting of the Association for Computational Linguistics (ACL)Yiyan Xu, Jinghao Zhang, Alireza Salemi, et al.2025 · 24 citations
4. Personalized Text Generation with Contrastive Activation SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Jinghao Zhang, Yuting Liu, Wenjie Wang, et al.2025 · 13 citations
5. MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning EvaluationAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoyuan Li, Keqin Bao, Yubo Ma, et al.2026 · 9 citations
6. PERM: Psychology-grounded Empathetic Reward Modeling for Large Language ModelsFindings of the Association for Computational LinguisticsChengbing Wang, Wuqiang Zheng, Yang Zhang, et al.2026 · 8 citations
7. Controllable LLM Reasoning via Sparse Autoencoder-Based SteeringAnnual Meeting of the Association for Computational Linguistics (ACL)Yi Fang, Wenjie Wang, Mingfeng Xue, et al.2026 · 3 citations

🤝 Co-authors here

12 of 24 co-authors with a page, the most papers together first.

• Fuli Feng ×4
• Dayiheng Liu ×2
• Jinghao Zhang ×2
• Tat-Seng Chua ×2
• Alireza Salemi
• Boyi Deng
• Chak Tou Leong
• Fengbin Zhu
• Fengli Xu
• Hamed Zamani
• Heming Xia
• Liang 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) ×4: ACL 2026 ×2, ACL 2025 ×2
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• IEEE/CVF International Conference on Computer Vision (ICCV)

🔗 Cited by

Papers of our library cite their works 142 times (of the 149,439 papers whose bibliographies we read); 62 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/wenjie-wang/