Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generationby Huizhuo Yuan, Zixiang Chen, Kaixuan Ji, Quanquan…
Nonlinear spiked covariance matrices and signal propagation in deep neural networksby Zhichao Wang, Denny Wu,…
RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language…
Reinforcement Learning from Human Feedback with Active Queriesby Kaixuan Ji, Jiafan He, Quanquan GuFirst submitted…
Gradient Alignment with Prototype Feature for Fully Test-time Adaptationby Juhyeon Shin, Jonghyun Lee, Saehyung Lee,…
Attacking Large Language Models with Projected Gradient Descentby Simon Geisler, Tom Wollschläger, M. H. I.…
MaxMin-RLHF: Alignment with Diverse Human Preferencesby Souradip Chakraborty, Jiahao Qiu, Hui Yuan, Alec Koppel, Furong…
Evaluating DTW Measures via a Synthesis Framework for Time-Series Databy Kishansingh Rajput, Duong Binh Nguyen,…
Text-centric Alignment for Multi-Modality Learningby Yun-Da Tsai, Ting-Yu Yen, Pei-Fu Guo, Zhe-Yan Li, Shou-De LinFirst…
Towards Unified Alignment Between Agents, Humans, and Environmentby Zonghan Yang, An Liu, Zijun Liu, Kaiming…