Alert button
Picture for Qingyun Wu

Qingyun Wu

Alert button

Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search

Add code
Bookmark button
Alert button
May 09, 2024
Zachary Coalson, Huazheng Wang, Qingyun Wu, Sanghyun Hong

Viaarxiv icon

Embodied LLM Agents Learn to Cooperate in Organized Teams

Add code
Bookmark button
Alert button
Mar 19, 2024
Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L. Griffiths, Mengdi Wang

Figure 1 for Embodied LLM Agents Learn to Cooperate in Organized Teams
Figure 2 for Embodied LLM Agents Learn to Cooperate in Organized Teams
Figure 3 for Embodied LLM Agents Learn to Cooperate in Organized Teams
Figure 4 for Embodied LLM Agents Learn to Cooperate in Organized Teams
Viaarxiv icon

StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows

Add code
Bookmark button
Alert button
Mar 17, 2024
Yiran Wu, Tianwei Yue, Shaokun Zhang, Chi Wang, Qingyun Wu

Figure 1 for StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
Figure 2 for StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
Figure 3 for StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
Figure 4 for StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
Viaarxiv icon

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Add code
Bookmark button
Alert button
Mar 02, 2024
Yifan Zeng, Yiran Wu, Xiao Zhang, Huazheng Wang, Qingyun Wu

Figure 1 for AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Figure 2 for AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Figure 3 for AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Figure 4 for AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
Viaarxiv icon

Towards better Human-Agent Alignment: Assessing Task Utility in LLM-Powered Applications

Add code
Bookmark button
Alert button
Feb 22, 2024
Negar Arabzadeh, Julia Kiseleva, Qingyun Wu, Chi Wang, Ahmed Awadallah, Victor Dibia, Adam Fourney, Charles Clarke

Viaarxiv icon

Training Language Model Agents without Modifying Language Models

Add code
Bookmark button
Alert button
Feb 17, 2024
Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, Qingyun Wu

Viaarxiv icon

Coreset Selection with Prioritized Multiple Objectives

Add code
Bookmark button
Alert button
Nov 15, 2023
Xiaobo Xia, Jiale Liu, Shaokun Zhang, Qingyun Wu, Tongliang Liu

Viaarxiv icon

IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

Add code
Bookmark button
Alert button
Oct 16, 2023
Shaokun Zhang, Xiaobo Xia, Zhaoqing Wang, Ling-Hao Chen, Jiale Liu, Qingyun Wu, Tongliang Liu

Viaarxiv icon

Adversarial Attacks on Combinatorial Multi-Armed Bandits

Add code
Bookmark button
Alert button
Oct 08, 2023
Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli, Huazheng Wang, Qingyun Wu, Haoyu Zhao

Viaarxiv icon

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

Add code
Bookmark button
Alert button
Aug 16, 2023
Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, Chi Wang

Figure 1 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Figure 2 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Figure 3 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Figure 4 for AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
Viaarxiv icon