Robust Real-Time Mortality Prediction in the Intensive Care Unit using Temporal Difference Learningby Thomas Frost,…
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Resetby Alexandre Galashov, Michalis K. Titsias,…
Self-Consistency Preference Optimizationby Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit…
A Post-Training Enhanced Optimization Approach for Small Language Modelsby Keke ZhaiFirst submitted to arxiv on:…
Specialized Foundation Models Struggle to Beat Supervised Baselinesby Zongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander…
On the Loss of Context-awareness in General Instruction Fine-tuningby Yihan Wang, Andrew Bai, Nanyun Peng,…
Towards certification: A complete statistical validation pipeline for supervised learning in industryby Lucas Lacasa, Abel…
Supervised Transfer Learning Framework for Fault Diagnosis in Wind Turbinesby Kenan Weber, Christine PreisachFirst submitted…
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHFby Atoosa Chegini, Hamid Kazemi, Iman Mirzadeh,…
Formal Theorem Proving by Rewarding LLMs to Decompose Proofs Hierarchicallyby Kefan Dong, Arvind Mahankali, Tengyu…