Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensemblesby Yuanzhao Zhai, Han Zhang,…
Second-Order Uncertainty Quantification: Variance-Based Measuresby Yusuf Sale, Paul Hofman, Lisa Wimmer, Eyke Hüllermeier, Thomas NaglerFirst…
Deep Generative Symbolic Regressionby Samuel Holt, Zhaozhi Qian, Mihaela van der SchaarFirst submitted to arxiv…
DXAI: Explaining Classification by Image Decompositionby Elnatan Kadar, Guy GilboaFirst submitted to arxiv on: 30…
Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actionsby Yinglun Xu, Tarun Suresh, Rohan Gumaste, David…
On the Burstiness of Distributed Machine Learning Trafficby Natchanon Luangsomboon, Fahimeh Fazel, Jörg Liebeherr, Ashkan…
Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillationby Sebastian-Vasile Echim, Iulian-Marius Tăiatu, Dumitru-Clementin…
Tight Finite Time Bounds of Two-Time-Scale Linear Stochastic Approximation with Markovian Noiseby Shaan Ul Haque,…
HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayesby Yuhta Takida, Yukara Ikemiya, Takashi Shibuya, Kazuki…
Predicting Evoked Emotions in Conversationsby Enas Altarawneh, Ameeta Agrawal, Michael Jenkin, Manos PapagelisFirst submitted to…