Zhaorun Chen - Publications

All Publications

0 publications

Sort by:

ICCV 2025

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding

Zhang, Y., Zhao, Z., Chen, Z., Ding, Z., Yang, X., & Sun, Y.

International Conference on Computer Vision (ICCV 2025), Honolulu, Hawaii, Oct 2025

Video

PDF

ICML 2025

ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning

Chen, Z., Kang, M., & Li, B.

International Conference on Machine Learning (ICML 2025), Vancouver, Canada, July 2025

Guardrail Agent Safety

PDF Project Page Code

ICLR 2025

SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations

Chen, Z., Pinto, F., Pan, M., & Li, B.

International Conference on Learning Representations (ICLR 2025), Singapore, Apr 2025

Guardrail Multimodal Safety Video

PDF Project Page Code

ICLR 2025

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Xu, C., Zhang, J., Chen, Z., Xie, C., Kang, M., Yuan, Z., Xiong, Z., Zhang, C., Yuan, L., Zeng, Y., Xu, P., Guo, C., Zhou, A., Tan, J. Z., Wang, Z., Xiong, A., Zhao, X., Gai, Y., Pinto, F., Potter, Y., Xiang, Z., Lin, Z., Hendrycks, D., Song, D., & Li, B.

International Conference on Learning Representations (ICLR 2025), Singapore, Apr 2025

Risk Assessment Multimodal Safety Evaluation

PDF Project Page Code

ICLR 2025

AnyPrefer: An Automatic Framework for Preference Data Synthesis

Zhou, Y., Wang, Z., Wang, T., Xing, S., Xia, P., Li, B., Zheng, K., Zhang, Z., Chen, Z., Zheng, W., Zhang, X., Bansal, C., Zhang, W., Wei, Y., Bansal, M., & Yao, H.

International Conference on Learning Representations (ICLR 2025), Singapore, Apr 2025

Safety Alignment Reinforcement Learning

PDF Project Page Code

ICLR 2025

MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models

Xia, P., Han, S., Qiu, S., Zhou, Y., Wang, Z., Zheng, W., Chen, Z., Cui, C., Ding, M., Li, L., Wang, L., & Yao, H.

International Conference on Learning Representations (ICLR 2025), Singapore, Apr 2025

Oral Presentation

Evaluation Multimodal Safety

PDF Project Page Code

ICLR 2025

Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment

Cui, C., Zhang, A., Zhou, Y., Chen, Z., Deng, G., Yao, H. and Chua, T.S.

International Conference on Learning Representations (ICLR 2025), Singapore, Apr 2025

Safety Alignment Multimodal Safety Reinforcement Learning

PDF Project Page Code

NeurIPS 2024

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Chen, Z., Xiang, Z., Xiao, C., Song, D., & Li, B.

Advances in Neural Information Processing Systems (NeurIPS 2024), Vancouver, Canada, Dec 2024

Risk Assessment Agent Safety

PDF Project Page Code

NeurIPS 2024

Calibrated Self-rewarding Vision Language Models

Zhou, Y., Fan, Z., Cheng, D., Yang, S., Chen, Z., Cui, C., Wang, X., Li, Y., Zhang, L., & Yao, H.

Advances in Neural Information Processing Systems (NeurIPS 2024), Vancouver, Canada, Dec 2024

Safety Alignment Multimodal Safety

PDF Code

ICML 2024

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Chen, Z., Zhao, Z., Luo, H., Yao, H., Li, B., & Zhou, J.

International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 2024

Safety Alignment Multimodal Safety

PDF Project Page Code

CoRL 2024

EscIRL: Evolving Self-Contrastive IRL for Trajectory Prediction in Autonomous Driving

Wang, S., Chen, Z., Zhao, Z., Mao, C., Zhou, Y., He, J., & Hu, A.S.

Conference on Robot Learning (CoRL 2024), Munich, Germany, Nov 2024

Safety Alignment Reinforcement Learning

PDF Code

NAACL 2024

AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition

Chen, Z., Zhao, Z., Zhu, Z., Zhang, R., Li, X., Raj, B., & Yao, H.

North American Chapter of the Association for Computational Linguistics (NAACL 2024), Mexico City, Mexico, Jun 2024

Safety Alignment

PDF

IROS 2024

Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards

Chen, Z., Zhao, Z., He, T., Chen, B., Zhao, X., Gong, L., & Liu C.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), Abu Dhabi, UAE, October 2024

Oral

Safety Alignment Reinforcement Learning

PDF

arXiv 2024

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Chen, Z., Du, Y., Wen, Z., Zhou, Y., Cui, C., Weng, Z., Tu, H., Wang, C., Tong, Z., Huang, Q., Chen, C., Ye, Q., Zhu, Z., Zhang, Y., Zhou, J., Zhao, Z., Rafailov, R., Finn, C., & Yao, H.

arXiv preprint arXiv:2407.04842, 2024

Evaluation Multimodal Safety Evaluation

PDF Project Page Code HuggingFace