Hybrid Preference Optimization for Alignment: Provably Faster Convergence Rates by Combining Offline Preferences with Online…
OP-LoRA: The Blessing of Dimensionalityby Piotr Teterwak, Kate Saenko, Bryan A. Plummer, Ser-Nam LimFirst submitted…
Reinforcement Learning Enhanced LLMs: A Surveyby Shuhe Wang, Shengyu Zhang, Jie Zhang, Runyi Hu, Xiaoya…
AdvPrefix: An Objective for Nuanced LLM Jailbreaksby Sicheng Zhu, Brandon Amos, Yuandong Tian, Chuan Guo,…
Federated Learning of Dynamic Bayesian Network via Continuous Optimization from Time Series Databy Jianhong Chen,…
Understand the Effectiveness of Shortcuts through the Lens of DCAby Youran Sun, Yihua Liu, Yi-Shuai…
Brain-inspired Chaotic Graph Backpropagation for Large-scale Combinatorial Optimizationby Peng Tao, Kazuyuki Aihara, Luonan ChenFirst submitted…
Capturing the Temporal Dependence of Training Data Influenceby Jiachen T. Wang, Dawn Song, James Zou,…
Sail into the Headwind: Alignment via Robust Rewards and Dynamic Labels against Reward Hackingby Paria…
SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothingby Xueting Li, Ye Yuan, Shalini De Mello,…