Gu, Xiangming

1. Why do LLMs attend to the first token?
   2025/04/03 by Federico Barbero, Barbero, Federico, Álvaro Arroyo +11 · 3 voices · 37 citations
   #cs.CL
2. On Memorization in Diffusion Models
   2023/10/04 by Xiangming Gu, Chao‐Hai Du, Gu, Xiangming +9 · 29 citations
   Computer Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Music and Audio Processing
3. When Attention Sink Emerges in Language Models: An Empirical View
   2024/10/14 by Xuejing Gu, Gu, Xiangming, Pang, Tianyu +12 · 42 citations
   Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
4. Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
   2024/02/13 by Gu, Xiangming, Zheng, Xiaosen, Pang, Tianyu +5 · 22 citations
   #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA)
5. On Calibration of LLM-based Guard Models for Reliable Content Moderation
   2024/10/14 by Hongfu Liu, Liu, Hongfu, Xiang Gu +6 · 6 citations
   Computer Science · #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Spam and Phishing Detection
6. Extracting alignment data in open models
   2025/10/21 by Federico Barbero, Barbero, Federico, Xiangming Gu +15 · 3 voices
   Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Testing and Debugging Techniques #Topic Modeling #cs.AI