Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detectionby Linas Nasvytis, Kai…
Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfittingby Nathaniel Dean, Dilip SarkarFirst submitted…
Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphsby Bowen Jin, Chulin Xie, Jiawei…
Continuous Language Model Interpolation for Dynamic and Controllable Text Generationby Sara Kangaslahti, David Alvarez-MelisFirst submitted…
What needs to go right for an induction head? A mechanistic study of in-context learning…
Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attentionby Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth…
How Consistent are Clinicians? Evaluating the Predictability of Sepsis Disease Progression with Dynamics Modelsby Unnseo…
Scaling Laws for Data Filtering – Data Curation cannot be Compute Agnosticby Sachin Goyal, Pratyush…
A Gauss-Newton Approach for Min-Max Optimization in Generative Adversarial Networksby Neel Mishra, Bamdev Mishra, Pratik…
VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identificationby Florian Sestak,…