HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and…
Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Samplingby Imad Aouali,…
Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Modelby Jinyin Chen, Xiaoming Zhao,…
Cycles of Thought: Measuring LLM Confidence through Stable Explanationsby Evan Becker, Stefano SoattoFirst submitted to…
FILS: Self-Supervised Video Feature Prediction In Semantic Language Spaceby Mona Ahmadian, Frank Guerin, Andrew GilbertFirst…
Pre-trained Large Language Models Use Fourier Features to Compute Additionby Tianyi Zhou, Deqing Fu, Vatsal…
Distributional Adversarial Lossby Saba Ahmadi, Siddharth Bhandari, Avrim Blum, Chen Dan, Prabhav JainFirst submitted to…
Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approachby Haoyu Han, Juanhui Li,…
Solving Differential Equations using Physics-Informed Deep Equilibrium Modelsby Bruno Machado Pacheco, Eduardo CamponogaraFirst submitted to…
Does your data spark joy? Performance gains from domain upsampling at the end of trainingby…