Dynamical loss functions shape landscape topography and improve learning in artificial neural networksby Eduardo Lavin,…
TRESTLE: A Model of Concept Formation in Structured Domainsby Christopher J. MacLellan, Erik Harpstead, Vincent…
Non-convergence to global minimizers in data driven supervised deep learning: Adam and stochastic gradient descent…
Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learningby Hung Le, Kien Do, Dung Nguyen,…
Self-Data Distillation for Recovering Quality in Pruned Large Language Modelsby Vithursan Thangarasa, Ganesh Venkatesh, Mike…
A Holistic Weakly Supervised Approach for Liver Tumor Segmentation with Clinical Knowledge-Informed Label Smoothingby Hairong…
Retrieval Instead of Fine-tuning: A Retrieval-based Parameter Ensemble for Zero-shot Learningby Pengfei Jin, Peng Shu,…
Toward General Instruction-Following Alignment for Retrieval-Augmented Generationby Guanting Dong, Xiaoshuai Song, Yutao Zhu, Runqi Qiao,…
Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Modelsby Jiaxin Zhang,…
Debiasing Vison-Language Models with Text-Only Trainingby Yunfan Yang, Chaoquan Jiang, Zhiyu Lin, Jinlin Xiao, Jiaming…