Not All Frequencies Are Created Equal:Towards a Dynamic Fusion of Frequencies in Time-Series Forecastingby Xingyu…
Base Models for Parabolic Partial Differential Equationsby Xingzi Xu, Ali Hasan, Jie Ding, Vahid TarokhFirst…
When can transformers compositionally generalize in-context?by Seijin Kobayashi, Simon Schug, Yassir Akram, Florian Redhardt, Johannes…
Chip Placement with Diffusion Modelsby Vint Lee, Minh Nguyen, Leena Elzeiny, Chun Deng, Pieter Abbeel,…
Enhancing Parameter Efficiency and Generalization in Large-Scale Models: A Regularized and Masked Low-Rank Adaptation Approachby…
GraphFM: A Scalable Framework for Multi-Graph Pretrainingby Divyansha Lachi, Mehdi Azabou, Vinam Arora, Eva DyerFirst…
Does Refusal Training in LLMs Generalize to the Past Tense?by Maksym Andriushchenko, Nicolas FlammarionFirst submitted…
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matricesby Jung Hyun…
Disentangling Representations through Multi-task Learningby Pantelis Vafidis, Aman Bhargava, Antonio RangelFirst submitted to arxiv on:…
Preconditioned Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regressionby Yingzhen YangFirst…