Publications

LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models
Shu Yu, Chaochao Lu
Technical Report, 2025
[Preprint]

CauSight: Learning to Supersense for Visual Causal Discovery
Yize Zhang, Meiqi Chen, Sirui Chen, Bo Peng, Yanxi Zhang, Tianyu Li, Chaochao Lu
Technical Report, 2025
[Preprint]

AI Alignment and Deception: A Primer
Isabella Duan, Saad Siddiqui, Sören Mindermann, Adam Gleave, Wei Xu, Chaochao Lu, Xudong Pan
Technical Report, 2025
[Preprint]

DEPO: Dual-Efficiency Preference Optimization for LLM Agents
Sirui Chen, Mengshi Zhao, Lei Xu, Yuying Zhao, Beier Zhu, Hanwang Zhang, Shengjie Zhao, Chaochao Lu
in Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2025
[Preprint]

VLMs Can Aggregate Scattered Training Patches
Zhanhui Zhou, Lingjie Chen, Chao Yang, Chaochao Lu
in Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2025
[Preprint]

IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data
Bo Peng, Zhiheng Wang, Heyang Gong, Chaochao Lu
Empirical Methods in Natural Language Processing (EMNLP) Findings, 2025
[Preprint]

Towards Safe and Trustworthy Embodied AI: Foundations, Status, and Prospects
Xin Tan*, Bangwei Liu*, Yicheng Bao, Qijian Tian, Zhenkun Gao, Xiongbin Wu, Zhihao Luo, Sen Wang, Yuqi Zhang, Xuhong Wang, Chaochao Lu, Bowen Zhou
Technical Report, 2025
[Preprint]

R²AI: Towards Resistant and Resilient AI in an Evolving World
Youbang Sun, Xiang Wang, Jie Fu, Chaochao Lu, Bowen Zhou
Technical Report, 2025
[Preprint]

SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law
Shanghai AI Laboratory
Technical Report, 2025
[Preprint][Blogpost]

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report
Shanghai AI Laboratory
Technical Report, 2025
[Preprint][Blogpost]

Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks
Sirui Chen, Shuqin Ma, Shu Yu, Hanwang Zhang, Shengjie Zhao, Chaochao Lu
Technical Report, 2025
[Preprint]

ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search
Yize Zhang, Tianshu Wang, Sirui Chen, Kun Wang, Xingyu Zeng, Hongyu Lin, Xianpei Han, Le Sun, Chaochao Lu
The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025
[Preprint]

From Imitation to Introspection: Probing Self-Consciousness in Language Models
Sirui Chen, Shu Yu, Shengjie Zhao, Chaochao Lu
The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025
[Preprint]

Adversarial Preference Learning for Robust LLM Alignment
Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang
The 63rd Annual Meeting of the Association for Computational Linguistics (ACL) Findings, 2025
[Preprint]

A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond
Xiaoye Qu, Yafu Li, Zhaochen Su, Weigao Sun, Jianhao Yan, Dongrui Liu, Ganqu Cui, Daizong Liu, Shuxian Liang, Junxian He, Peng Li, Wei Wei, Jing Shao, Chaochao Lu, Yue Zhang, Xian-Sheng Hua, Bowen Zhou, Yu Cheng
Technical Report, 2025
[Preprint]

Bare Minimum Mitigations for Autonomous AI Development
Joshua Clymer, Isabella Duan, Chris Cundy, Yawen Duan, Fynn Heide, Chaochao Lu, Sören Mindermann, Conor McGurk, Xudong Pan, Saad Siddiqui, Jingren Wang, Min Yang, Xianyuan Zhan
Technical Report, 2025
[Preprint]

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
Yucheng Hu*, Yanjiang Guo*, Pengchao Wang, Xiaoyu Chen, Yen-Jen Wang, Jianke Zhang, Koushil Sreenath, Chaochao Lu, Jianyu Chen
in Proceedings of International Conference on Machine Learning (ICML), 2025
[Preprint]

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
Yujin Han, Andi Han, Wei Huang, Chaochao Lu, Difan Zou
in Proceedings of International Conference on Machine Learning (ICML), 2025
[Preprint]

Emergent Response Planning in LLM
Zhichen Dong, Zhanhui Zhou, Zhixuan Liu, Chao Yang, Chaochao Lu
in Proceedings of International Conference on Machine Learning (ICML), 2025
[Preprint]

Beyond Surface Structure: A Causal Assessment of LLMs’ Comprehension Ability
Yujin Han, Lei Xu, Sirui Chen, Difan Zou, Chaochao Lu
in Proceedings of International Conference on Learning Representations (ICLR), 2025
[Preprint]

ADAM: An Embodied Causal Agent in Open-World Environments
Shu Yu, Chaochao Lu
in Proceedings of International Conference on Learning Representations (ICLR), 2025
[Preprint]

Interpreting Low-level Vision Models with Causal Effect Maps
Jinfan Hu, Jinjin Gu, Shiyao Yu, Fanghua Yu, Zheyuan Li, Zhiyuan You, Chaochao Lu, Chao Dong
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
[Preprint]

Towards AI-45 Law: A Roadmap to Trustworthy AGI
Chao Yang, Chaochao Lu, Yingchun Wang, Bowen Zhou
Technical Report, 2024
[Preprint]

Prediction with Action: Visual Policy Learning via Joint Denoising Process
Yanjiang Guo, Yucheng Hu, Jianke Zhang, Yen-Jen Wang, Xiaoyu Chen, Chaochao Lu, Jianyu Chen
in Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS), 2024
[Paper]

CELLO: Causal Evaluation of Large Vision-Language Models
Meiqi Chen, Bo Peng, Yan Zhang, Chaochao Lu.
Empirical Methods in Natural Language Processing (EMNLP), 2024
[Paper]

CLEAR: Can Language Models Really Understand Causal Graphs?
Sirui Chen, Mengying Xu, Kun Wang, Xingyu Zeng, Rui Zhao, Shengjie Zhao, Chaochao Lu.
Empirical Methods in Natural Language Processing (EMNLP) Findings, 2024
[Paper]

Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective
Meiqi Chen, Yixin Cao, Yan Zhang, Chaochao Lu.
Empirical Methods in Natural Language Processing (EMNLP) Findings, 2024
[Paper]

Causal Evaluation of Language Models
Sirui Chen*, Bo Peng*, Meiqi Chen, Ruiqi Wang, Mengying Xu, Xingyu Zeng, Rui Zhao, Shengjie Zhao, Yu Qiao, Chaochao Lu.
Technical Report, 2024
[Preprint]

From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness, and Causality through Four Modalities
Chaochao Lu, Chen Qian, Guodong Zheng, Hongxing Fan, Hongzhi Gao, Jie Zhang, Jing Shao, Jingyi Deng, Jinlan Fu, Kexin Huang, Kunchang Li, Lijun Li, Limin Wang, Lu Sheng, Meiqi Chen, Ming Zhang, Qibing Ren, Sirui Chen, Tao Gui, Wanli Ouyang, Yali Wang, Yan Teng, Yaru Wang, Yi Wang, Yinan He, Yingchun Wang, Yixu Wang, Yongting Zhang, Yu Qiao, Yujiong Shen, Yurong Mou, Yuxi Chen, Zaibin Zhang, Zhelun Shi, Zhenfei Yin, Zhipin Wang. (Authors listed in alphabetical order)
Technical Report, 2024
[Preprint]

Distribution-consistency Structural Causal Models
Heyang Gong, Chaochao Lu, Yu Zhang.
Technical Report, 2024
[Preprint]

ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation
Bo Peng, Xinyuan Chen, Yaohui Wang, Chaochao Lu, Yu Qiao.
in Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024
[Paper]

ACAMDA: Improving Data Efficiency in Reinforcement Learning Through Guided Counterfactual Data Augmentation
Yuewen Sun, Erli Wang, Biwei Huang, Chaochao Lu, Lu Feng, Changyin Sun, Kun Zhang.
in Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), 2024
[Paper]

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding
Junda Wu, Tong Yu, Rui Wang, Zhao Song, Ruiyi Zhang, Handong Zhao, Chaochao Lu, Shuai Li, Ricardo Henao.
in Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS), 2023
[Paper]

Few-Shot Composition Learning for Image Retrieval with Prompt Tuning
Junda Wu*, Rui Wang*, Handong Zhao, Ruiyi Zhang, Chaochao Lu, Shuai Li, Ricardo Henao. (*Equal Contribution)
in Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), 2023
[Paper]

Action-Sufficient State Representation Learning for Control with Structural Constraints
Biwei Huang*, Chaochao Lu*, Liu Leqi, José Miguel Hernández-Lobato, Clark Glymour, Bernhard Schölkopf, Kun Zhang. (*Equal Contribution)
in Proceedings of International Conference on Machine Learning (ICML), 2022
[Paper]

Invariant Causal Representation Learning for Generalization in Imitation and Reinforcement Learning
Chaochao Lu, José Miguel Hernández-Lobato, Bernhard Schölkopf.
in Proceedings of International Conference on Learning Representations (ICLR) Workshop on PAIR2Struct (Oral Presentation), 2022
[Paper]

Invariant Causal Representation Learning for Out-of-Distribution Generalization
Chaochao Lu, Yuhuai Wu, José Miguel Hernández-Lobato, Bernhard Schölkopf.
in Proceedings of International Conference on Learning Representations (ICLR), 2022
[Paper]

AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
Biwei Huang, Fan Feng, Chaochao Lu, Sara Magliacane, Kun Zhang.
in Proceedings of International Conference on Learning Representations (ICLR), 2022
[Paper]

Nonlinear Invariant Risk Minimization: A Causal Approach
Chaochao Lu, Yuhuai Wu, José Miguel Hernández-Lobato, Bernhard Schölkopf.
Technical Report, Cambridge Machine Learning Group, 2021
[Paper]

Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
Chaochao Lu*, Biwei Huang*, Ke Wang, José Miguel Hernández-Lobato, Kun Zhang, Bernhard Schölkopf. (*Equal Contribution)
in Proceedings of Neural Information Processing Systems Workshop on Offline Reinforcement Learning, Virtually, 2020
[Paper]

Interpreting Spatially Infinite Generative Models
Chaochao Lu, Richard Turner, Yingzhen Li, Nate Kushman.
in Proceedings of ICML Workshop on Human Interpretability in Machine Learning (WHI), Virtually, 2020
[Paper] [Video][Generated High-Resolution Samples]

Deconfounding Reinforcement Learning in Observational Settings
Chaochao Lu, Bernhard Schölkopf, José Miguel Hernández-Lobato.
Technical Report, Cambridge Machine Learning Group, 2018
[Paper]

Flexible Spatio-Temporal Networks for Video Prediction
Chaochao Lu, Michael Hirsch, Bernhard Schölkopf.
in Proceedings of IEEE Computer Society Conference on Computer Vision and Patter Recognition (CVPR), Honolulu, Hawaii, USA, 2017 
[Paper]

Surpassing Human-Level Face Verification Performance on LFW with GaussianFace
Chaochao Lu, Xiaoou Tang.
in Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI), Austin, Texas, USA, 2015 
Outstanding Student Paper Award
For the first time, the human-level performance in face verification on LFW is surpassed. 
[Paper] [Supplementary] Selected News: [Science News] [Nature News] [Discover] [The Register] [Physics arXiv Blog]
[Tech Xplore] [Technology] [Rootnotion] [I Programmer]

Learning the Face Prior for Bayesian Face Recognition
Chaochao Lu, Xiaoou Tang.
in Proceedings of European Conference on Computer Vision (ECCV), Zurich, Switzerland, 2014 
[Paper] [Poster] [Video]

Face Recognition Using Face Patch Networks
Chaochao Lu, Deli Zhao, Xiaoou Tang.
in Proceedings of IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 2013 
[Paper] [Poster]