RS-DPO: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language…
Multi-Fidelity Methods for Optimization: A Surveyby Ke Li, Fan LiFirst submitted to arxiv on: 15…
PAL: Proxy-Guided Black-Box Attack on Large Language Modelsby Chawin Sitawarin, Norman Mu, David Wagner, Alexandre…
Efficient Prompt Optimization Through the Lens of Best Arm Identificationby Chengshuai Shi, Kun Yang, Zihan…
UMOEA/D: A Multiobjective Evolutionary Algorithm for Uniform Pareto Objectives based on Decompositionby Xiaoyuan Zhang, Xi…
Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learningby Jason Yoo, Yunpeng Liu,…
Exact, Fast and Expressive Poisson Point Processes via Squared Neural Familiesby Russell Tsuchida, Cheng Soon…
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorizationby Idan Attias, Gintare Karolina…
Loss Shaping Constraints for Long-Term Time Series Forecastingby Ignacio Hounie, Javier Porras-Valenzuela, Alejandro RibeiroFirst submitted…
Reinforcement Learning from Human Feedback with Active Queriesby Kaixuan Ji, Jiafan He, Quanquan GuFirst submitted…