| CARVIEW |
I am a second-year Ph.D. student in Computer Science at Northwestern University, fortunately advised by Prof. Manling Li. I collaborate closely with the Stanford Vision and Learning Lab (SVL), working with Prof. Li Fei-Fei and Prof. Jiajun Wu on spatial intelligence and embodied agents. Before Northwestern, I received my bachelor's degree from Zhejiang University.
I am looking for 2026 summer internships focused on foundation models (MLLMs) for embodied agents — feel free to reach out!
Research Interests
Research vision: I study how foundation models develop spatial understanding and decision-making skills, so that embodied agents can act over long horizons and across diverse embodied experiences in complex environments.
- Foundation Models for Embodied Agents. (1) Leverage foundation models to plan over long horizons for embodied decision making [EAI, EmbodiedBench] (2) Leverage foundation models to model the world dynamics [ENACT, EmbodiedBench]
- Spatial Intelligence. Investigate the spatial reasoning capability of foundation models [MindCube]
- Reasoning Agents with Foundation Models. Combine multi-agent collaboration, reinforcement learning, and language models to unlock robust reasoning in interactive settings [CMD, RAGEN, VAGEN]
Publications (show selected / show by date / show by topic)
Research Topics: Embodied World Modeling / Embodied Decision Making / Spatial Intelligence / Reasoning Agents
(* indicates equal contribution; † denotes co-advising.)
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Qineng Wang*, Wenlong Huang*, Yu Zhou, Hang Yin, Tianwei Bao, Jianwen Lyu, Weiyu Liu, Ruohan Zhang†, Jiajun Wu†, Li Fei-Fei†, Manling Li†
Spatial Mental Modeling from Limited Views
Qineng Wang*, Baiqiao Yin*, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Jiajun Wu†, Li Fei-Fei†, Manling Li†
ICCV 2025 (SP4V Workshop) Best Paper Award · The Best of ICCV (featured by Voxel51)
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang*, Pingyue Zhang*, Zihan Wang*, Yaning Gao*, Linjie Li*, Qineng Wang, Hanyang Chen, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Yejin Choi, Manling Li
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-turn Reinforcement Learning
Zihan Wang*, Kangrui Wang*, Qineng Wang*, Pingyue Zhang*, Linjie Li*, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li
Best Poster Award
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang*, Hanyang Chen*, Junyu Zhang*, Mark Zhao*, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang
ICML Oral Presentation
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Manling Li*, Shiyu Zhao*, Qineng Wang*, Kangrui Wang*, Yu Zhou*, Sanjana Srivastava, Jem Gokmen, Tony Lee, Li Li Erran, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu
NeurIPS Oral Presentation · SoCal NLP 2024 Best Paper Award
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Qineng Wang*, Zihao Wang*, Ying Su, Hanghang Tong, Yangqiu Song
2025
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Qineng Wang*, Wenlong Huang*, Yu Zhou, Hang Yin, Tianwei Bao, Jianwen Lyu, Weiyu Liu, Ruohan Zhang†, Jiajun Wu†, Li Fei-Fei†, Manling Li†
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied Agents
Simon Sinong Zhan*, Yao Liu*, Philip Wang*, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu
Spatial Mental Modeling from Limited Views
Qineng Wang*, Baiqiao Yin*, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Jiajun Wu†, Li Fei-Fei†, Manling Li†
ICCV 2025 (SP4V Workshop) Best Paper Award · The Best of ICCV (featured by Voxel51)
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang*, Pingyue Zhang*, Zihan Wang*, Yaning Gao*, Linjie Li*, Qineng Wang, Hanyang Chen, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Yejin Choi, Manling Li
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-turn Reinforcement Learning
Zihan Wang*, Kangrui Wang*, Qineng Wang*, Pingyue Zhang*, Linjie Li*, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li
Best Poster Award
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang*, Hanyang Chen*, Junyu Zhang*, Mark Zhao*, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang
ICML Oral Presentation
2024
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Manling Li*, Shiyu Zhao*, Qineng Wang*, Kangrui Wang*, Yu Zhou*, Sanjana Srivastava, Jem Gokmen, Tony Lee, Li Li Erran, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu
NeurIPS Oral Presentation · SoCal NLP 2024 Best Paper Award
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Qineng Wang*, Zihao Wang*, Ying Su, Hanghang Tong, Yangqiu Song
Lens: A Foundation Model for Network Traffic in Cybersecurity
Qineng Wang, Chen Qian, Xiaochang Li, Ziyu Yao, Huajie Shao
Embodied World Modeling
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Qineng Wang*, Wenlong Huang*, Yu Zhou, Hang Yin, Tianwei Bao, Jianwen Lyu, Weiyu Liu, Ruohan Zhang†, Jiajun Wu†, Li Fei-Fei†, Manling Li†
Spatial Mental Modeling from Limited Views
Qineng Wang*, Baiqiao Yin*, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Jiajun Wu†, Li Fei-Fei†, Manling Li†
ICCV 2025 (SP4V Workshop) Best Paper Award · The Best of ICCV (featured by Voxel51)
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang*, Hanyang Chen*, Junyu Zhang*, Mark Zhao*, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang
ICML Oral Presentation
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Manling Li*, Shiyu Zhao*, Qineng Wang*, Kangrui Wang*, Yu Zhou*, Sanjana Srivastava, Jem Gokmen, Tony Lee, Li Li Erran, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu
NeurIPS Oral Presentation · SoCal NLP 2024 Best Paper Award
Embodied Decision Making
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied Agents
Simon Sinong Zhan*, Yao Liu*, Philip Wang*, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang*, Pingyue Zhang*, Zihan Wang*, Yaning Gao*, Linjie Li*, Qineng Wang, Hanyang Chen, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Yejin Choi, Manling Li
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-turn Reinforcement Learning
Zihan Wang*, Kangrui Wang*, Qineng Wang*, Pingyue Zhang*, Linjie Li*, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li
Best Poster Award
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Rui Yang*, Hanyang Chen*, Junyu Zhang*, Mark Zhao*, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, Huan Zhang, Tong Zhang
ICML Oral Presentation
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
Manling Li*, Shiyu Zhao*, Qineng Wang*, Kangrui Wang*, Yu Zhou*, Sanjana Srivastava, Jem Gokmen, Tony Lee, Li Li Erran, Ruohan Zhang, Weiyu Liu, Percy Liang, Li Fei-Fei, Jiayuan Mao, Jiajun Wu
NeurIPS Oral Presentation · SoCal NLP 2024 Best Paper Award
Spatial Intelligence
ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
Qineng Wang*, Wenlong Huang*, Yu Zhou, Hang Yin, Tianwei Bao, Jianwen Lyu, Weiyu Liu, Ruohan Zhang†, Jiajun Wu†, Li Fei-Fei†, Manling Li†
Spatial Mental Modeling from Limited Views
Qineng Wang*, Baiqiao Yin*, Pingyue Zhang, Jianshu Zhang, Kangrui Wang, Zihan Wang, Jieyu Zhang, Keshigeyan Chandrasegaran, Han Liu, Ranjay Krishna, Saining Xie, Jiajun Wu†, Li Fei-Fei†, Manling Li†
ICCV 2025 (SP4V Workshop) Best Paper Award · The Best of ICCV (featured by Voxel51)
Reasoning Agents
SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied Agents
Simon Sinong Zhan*, Yao Liu*, Philip Wang*, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu
VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
Kangrui Wang*, Pingyue Zhang*, Zihan Wang*, Yaning Gao*, Linjie Li*, Qineng Wang, Hanyang Chen, Yiping Lu, Zhengyuan Yang, Lijuan Wang, Ranjay Krishna, Jiajun Wu, Li Fei-Fei, Yejin Choi, Manling Li
RAGEN: Understanding Self-Evolution in LLM Agents via Multi-turn Reinforcement Learning
Zihan Wang*, Kangrui Wang*, Qineng Wang*, Pingyue Zhang*, Linjie Li*, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li
Best Poster Award
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Qineng Wang*, Zihao Wang*, Ying Su, Hanghang Tong, Yangqiu Song
News
- Nov 2025. 📢 We released the ENACT! Check out the paper and the tl;dr!
- Oct 2025. 🚀 My new homepage went online! Welcome!
- Sep 2025. 🎉 VAGEN was accepted to NeurIPS 2025.
- Aug 2025. 🎉 MindCube was selected as a The Best of ICCV by Voxel51 and highlighted as a spotlight at the SP4V Workshop @ ICCV 2025.
- May 2025. Launched the Embodied Agent Interface Challenge to benchmark embodied reasoning.
- May 2025. EmbodiedBench was accepted to ICML 2025 as an oral presentation.
- Mar 2025. We released RAGEN, the first multi-turn reinforcement learning framework for LLM agents.
- Mar 2025. Co-organising the Foundation Models Meet Embodied Agents workshop at CVPR 2025.
- Nov 2024. Embodied Agent Interface won the Best Paper Award at SoCal NLP 2024.
- Sep 2024. Embodied Agent Interface was accepted to NeurIPS 2024 as an oral presentation.
- Jun 2024. Graduated as an outstanding undergrad from Zhejiang University.
- May 2024. CMD was accepted to ACL 2024.
- Mar 2024. Will join Northwestern University as a CS Ph.D. student, working with Prof. Manling Li.
Talks
- Jul 2025. Shanghai AI Lab, Spatial Mental Modeling from Limited Views (Invited Talk)
- Jul 2025. Qingke AI, Spatial Mental Modeling from Limited Views (Invited Talk)
Honors
- The Best of ICCV, Voxel51 2025
- Best Poster Award, MMLS 2025
- Best Paper, SoCal NLP Symposium 2024
- McCormick School of Engineering Fellowship (USD 45,000), Northwestern University 2024
- Outstanding Undergraduate Student, Zhejiang University 2024
- Excellent Undergraduate Thesis, Zhejiang University 2024
- Bronze Medal, 36th Chinese Physics Olympiad (CPhO) 2019
Professional Service
- Workshop Organization
- Conference Reviews
- ICLR 2026
- AAAI 2026
- NeurIPS 2025
- FMEA @ CVPR 2025
- KnowLM @ ACL 2024
- Journal Reviews
- Transactions of the ACL (TACL) 2024