Jiaming Wangacademic homepage

About

Research Profile

I am an undergraduate researcher at Nanjing University working on LLM post-training, code intelligence, and world models. My work is usually about training carefully, measuring honestly, and keeping systems legible. Incoming PhD student at HKUST CSE (Fall 2027), advised by Prof. Song Guo.

World modelsLLM post-trainingAgents and code intelligenceMultimodal learningData-centric methods

News

Recent Updates

2026-10

🎈 Reached 100 citations on Google Scholar!

2026-10

🎓 Received a written conditional offer for the HKUST CSE PhD program, starting in Fall 2027 with Prof. Song Guo.

2026-9

🌍 Released HappyWorld-Bench, our technical report on evaluating world models.

2026-8

🎊 Our survey on linear attention is accepted by TMLR.

2026-6

🎬 Join Alibaba Group (Token Foundry).

2026-5

🏆 Our team (Insta360 Research) won Top-2 and Top-3 in the CVPR 2026 PortraitCraft Challenge.

2026-5

🎊 T2AV-Compass is accepted by ICML 2026 Poster.

2026-4

✨ T2AV-Compass is accepted by CVPR 2026 VGBE Oral.

2026-4

🎊 FunPoison ( Train in Vain ) is accepted by ACL 2026 Findings.

2026-1

🎓 Begin as a Research Assistant at CUHK, MMLab.

2025-12

📷 Join Insta360 Research.

2025-10

🏆 Tencent Scholarship, 🎖️ Outstanding Student.

2024-10

🏆 People Scholarship, 🎖️ Outstanding Student Leader.

2024-3

🏃 Join NJU Orientation Team.

Selected Publications

Papers and Projects

HappyWorld-Bench

HappyWorld-Bench

Zhiqi Bai, Junai Cai, Yixin Chen, Jingrun Du, Tao Feng, Wei Gong, Siyuan Huang, Xiao Lin, Jiaheng Liu, Jun Luo, Yongzhe Lyu, Liya Ma, Zenan Meng, Lin Qu, Wenbo Su, Jiaming Wang, Qinghe Wang, Shaofei Wang, Yanghai Wang, Zequn Wang, Ziming Wang, Hu Wei, Jiangtao Wu, Ruiqi Wu, Jiaxin Xie, Yuchi Xu, Ze Xu, Chengting Yu, Liangyu Yuan, Gang Zeng, Yawen Zeng, Xingyao Zhang, Zizheng Zhang, Bo Zheng, Jiancheng Zhu, Song-Chun Zhu

Technical ReportArxiv
LongWM-Bench: Benchmarking Persistent and Navigable Worlds over Long-Horizon Interaction cover

LongWM-Bench: Benchmarking Persistent and Navigable Worlds over Long-Horizon Interaction

Jiaming Wang*, Yufei Chen*, Jiangtao Wu*, Zhiqi Bai, Ziming Pan, Yanghai Wang, Fangqi Zhu, Chengting Yu, Liangyu Yuan, Qinghe Wang, Jiaxin Xie, Wenbo Su, Zhaoxiang Zhang, Jiaheng Liu†

Under Review
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories cover

Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories

Jiaming Wang*, Ziteng Feng*, Jiangtao Wu, Ruihao Li, Qianqian Xie, Yuxiang Ren, He Zhu, Xueming Han, Fanyu Meng, Junlan Feng, Jiaheng Liu†

Under ReviewArxivCodeDataProject Page
Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning cover

Winning the Pruning Gamble: A Unified Approach to Joint Sample and Token Pruning for Efficient Supervised Fine-Tuning

Jiaming Wang*, Shaobo Wang*, Jiajun Zhang*, Cong Wang, Yue Min, Zichen Wen, Fei Huang, Huiqiang Jiang, Junyang Lin, Dayiheng Liu, Linfeng Zhang†

ICLR 2026 DATA-FMArxivCodeProject Page
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets cover

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets

Jiaming Wang*, Yuan Xiao*, Yuchen Chen*, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang†, Jin Song Dong, Zhenyu Chen†

ACL 2026 FindingsArxivCode
T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation cover

T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation

Zhe Cao*, Tao Wang*, Jiaming Wang*, Yanghai Wang*, Yuanxing Zhang, Jialu Chen, Miao Deng, Jiahao Wang, Yubin Guo, Chenxi Liao, Yize Zhang, Zhaoxiang Zhang, Jiaheng Liu†

ICML 2026 | CVPR 2026 VGBE OralArxivCodeDataProject Page
CoVEBench: Can Video Editing Models Handle Complex Instructions? cover

CoVEBench: Can Video Editing Models Handle Complex Instructions?

Jiangtao Wu*, Jiaming Wang*, Yiwen He*, Yuanxing Zhang, Jialu Chen, Shihao Li, Dunyuan Liu, Xuedong Zhao, Jiaheng Liu†

Under ReviewArxivCodeDataProject Page
Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence? cover

Agentic-MME: What Agentic Capability Really Brings to Multimodal Intelligence?

Qianshan Wei, Yishan Yang, Siyi Wang, Jinglin Chen, Binyu Wang, Jiaming Wang, Shuang Chen, Zechen Li, Yang Shi, Yuqi Tang, Weining Wang, Yi Yu, Chaoyou Fu, Qi Li, Yi-Fan Zhang†

arXivArxivCodeDataProject Page
ContextBench: A Benchmark for Context Retrieval in Coding Agents cover

ContextBench: A Benchmark for Context Retrieval in Coding Agents

Han Li, Letian Zhu, Bohan Zhang, Rili Feng, Jiaming Wang, Yue Pan, Earl T Barr, Federica Sarro, Zhaoyang Chu†, He Ye†

arXivArxivCodeDataProject Page
CodeTracer: Towards Traceable Agent cover

CodeTracer: Towards Traceable Agent

Han Li, Yifan Yao, Letian Zhu, Rili Feng, Hongyi Ye, Jiaming Wang, Yancheng He, Pengyu Zou, Lehan Zhang, Xinping Lei, Haoyang Huang, Ken Deng, Ming Sun, Zhaoxiang Zhang, He Ye, Jiaheng Liu†

arXivArxivCodeDataProject Page
Linear Attention

A Survey of Linear Attention: Algorithm, Theory, Application, and Infrastructure

Yudong Zhang, Weixuan Sun, Xingwu Sun, Wei Ding, Ruiqi Xie, Hongyi Wang, Junjie Chen, Jiacheng Liu, Shaobo Wang, Yuwei Zhang, Yiqing Huang, Jiaming Wang, Tianchen Zhao, Weidong Han, Yanfeng Chen, Kai Zhang, Shuaipeng Li, Ruobing Xie†, Di Wang, Jiansheng Chen, Linfeng Zhang†, Chengzhong Xu, Yu Wang†

TMLR 2026TechArxivCode

Experience

Research Experience

2027 - 2031 (Expected)

CSE PhD, Hong Kong University of Science and Technology.

2025.12- present

Research Intern on World Model

CUHK, MMLab.

2023.9 - 2027.6

Undergraduate, School of Computer Science, Nanjing University.