An Optimistic Algorithm for Online Convex Optimization with Adversarial Constraintsby Jordan Lekeufack, Michael I. JordanFirst…
Multi-Response Preference Optimization with Augmented Ranking Datasetby Hansle Gwon, Imjin Ahn, Young-Hak Kim, Sanghyun Park,…
Low-Rank Correction for Quantized LLMsby Meyer Scetbon, James HensmanFirst submitted to arxiv on: 10 Dec…
Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimizationby Zongkai Liu, Qian Lin, Chao Yu,…
SurvBETA: Ensemble-Based Survival Models Using Beran Estimators and Several Attention Mechanismsby Lev V. Utkin, Semen…
RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewritingby Shuo Yang, Bardh Prenkaj, Gjergji…
LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Modelsby Ziqi Lu, Heng Yang, Danfei Xu, Boyi…
Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequencesby Alan Nawzad Amin,…
Video Motion Transfer with Diffusion Transformersby Alexander Pondaven, Aliaksandr Siarohin, Sergey Tulyakov, Philip Torr, Fabio…
Reconstructing Deep Neural Networks: Unleashing the Optimization Potential of Natural Gradient Descentby Weihua Liu, Said…