Jun Wang

Professor, Computer Science, University College London

Joined

March 2018

Names

Jun Wang (Preferred)

Emails

****@cs.ucl.ac.uk (Confirmed)

****@huawei.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Professor

Computer Science, University College London (ucl.ac.uk)

2017 – Present

Advisors, Relations & Conflicts

Coauthor

Kun Shao

2023 – Present

Expertise

machine learning

Present

information retrieval

Present

data science

Present

Publications

Self-Verifying Reflection Helps Transformers with CoT Reasoning
Zhongwei Yu, Wannian Xia, Xue Yan, Bo XU, Haifeng Zhang, Yali Du, Jun Wang
- NeurIPS 2025
- Readers: Everyone
Agent Exchange: An Auction Platform for AI Agent Marketplaces
Yingxuan Yang, Ying Wen, Jun Wang, Weinan Zhang
- ICLR 2026 Workshop AIMS
- Readers: Everyone
BEYOND SYNTAX: ACTION SEMANTICS LEARNING FOR APP AGENTS
Dezhao Luo, Bohan Tang, Jianheng Liu, Jingxuan Chen, Shaogang Gong, Jianye HAO, Jun Wang, Kun Shao
- LLA 2026 Poster
- Readers: Everyone
BEYOND SYNTAX: ACTION SEMANTICS LEARNING FOR APP AGENTS
Bohan Tang, Dezhao Luo, Jianheng Liu, Jingxuan Chen, Shaogang Gong, Jianye HAO, Jun Wang, Kun Shao
- MALGAI
- Readers: Everyone
Advancing Autonomous VLM Agents via Variational Subgoal-Conditioned Reinforcement Learning
Qingyuan Wu, Jianheng Liu, Jianye HAO, Jun Wang, Kun Shao
- VLM4RWD2025 Regular
- Readers: Everyone
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhong-Zhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Francisco Piedrahita Velez, Yue Liao, Hongru WANG, Mengyue Yang et al. (5 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
Hugo Hazard, Zafeirios Fountas, Martin Benfeghoul, Adnan Oomerjee, Jun Wang, Haitham Bou Ammar
- Submitted to ICLR 2026
- Readers: Everyone
Emergent Bayesian Behaviour and Optimal Cue Combination in LLMs
Julian Ma, Jun Wang, Zafeirios Fountas
- Submitted to ICLR 2026
- Readers: Everyone
Subjective Depth and Timescale Transformers: Learning Where and When to Compute
Frederico Wieser, Martin Benfeghoul, Haitham Bou Ammar, Jun Wang, Zafeirios Fountas
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Paying Attention to Hybrid Attention: Untangling the Issues with Conversion Methods
Martin Benfeghoul, Teresa Delgado, Adnan Oomerjee, Haitham Bou Ammar, Jun Wang, Zafeirios Fountas
- Submitted to ICLR 2026
- Readers: Everyone

View all 193 publications

Co-Authors

View all 471 co-authors