Offline Regularised Reinforcement Learning for Large Language Models Alignmentby Pierre Harvey Richemond, Yunhao Tang, Daniel…
Can Graph Learning Improve Planning in LLM-based Agents?by Xixi Wu, Yifei Shen, Caihua Shan, Kaitao…
Spatio-Spectral Graph Neural Networksby Simon Geisler, Arthur Kosmala, Daniel Herbst, Stephan GünnemannFirst submitted to arxiv…
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learningby Arthur Juliani, Jordan T. AshFirst…
I Bet You Did Not Mean That: Testing Semantic Importance via Bettingby Jacopo Teneggi, Jeremias…
Beyond Discrepancy: A Closer Look at the Theory of Distribution Shiftby Robi Bhattacharjee, Nick Rittler,…
Transformers as Neural Operators for Solutions of Differential Equations with Finite Regularityby Benjamin Shih, Ahmad…
Does learning the right latent variables necessarily improve in-context learning?by Sarthak Mittal, Eric Elmoznino, Leo…
Online Linear Regression in Dynamic Environments via Discountingby Andrew Jacobsen, Ashok CutkoskyFirst submitted to arxiv…
MetaToken: Detecting Hallucination in Image Descriptions by Meta Classificationby Laura Fieback, Jakob Spiegelberg, Hanno GottschalkFirst…