Papers by Zhuoer Xu
Parameter-free and Accessible Prompt Learning to Enhance Adversarial Robustness for Pre-trained Vision-Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large pre-trained Vision-Language Models (VLMs) have revolutionized downstream vision-language tasks including classification, object detection, and segmentation. |
| Approach: | They propose to search for text prompts at the word level rather than optimizing continuous textual embeddings to boost adversarial robustness. |
| Outcome: | Experiments show that the proposed method outperforms hand-engineered prompts with average gains of +4.9% and +5.8%. |
MultiAgentESC: A LLM-based Multi-Agent Collaboration Framework for Emotional Support Conversation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies focus on generating responses directly and neglect integration of domain-specific reasoning and expert interaction. |
| Approach: | They propose a training-free multi-agent collaboration framework for ESC to emulate human-like process of providing emotional support through dialogue analysis, strategy deliberation, and response generation. |
| Outcome: | The proposed framework excels at providing emotional support and diversifying support strategy selection. |
WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback (2026.acl-long)
Copied to clipboard
Taiwei Shi, Zhuoer Wang, Longqi Yang, Ying-Chun Lin, Zexue He, Mengting Wan, Pei Zhou, Sujay Kumar Jauhar, Sihao Chen, Shan Xia, Hongfei Zhang, Jieyu Zhao, Xiaofeng Xu, Xia Song, Jennifer Neville
| Challenge: | Traditional alignment methods rely on human annotations and are subjective and misalignment with real-world user preferences. |
| Approach: | They propose a framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically. |
| Outcome: | The proposed framework identifies and classifies user feedback to LLM responses between conversation turns and creates examples of preferred and dispreferred responses according to user preferences. |