collaborators

5 papers

cs.LG2026

An Overview of Low-Rank Structures in the Training and Adaptation of Large Models

Laura Balzano, Tianjiao Ding, Benjamin D. Haeffele +5

The substantial computational demands of modern large-scale deep learning present significant challenges for efficient training and deployment. Recent research has revealed a wides…

cs.LG2026

Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs

Tushaar Gangavarapu, Jiping Li, Christopher Vattheuer +2

Can modifying the training data distribution guide optimizers toward solutions with improved generalization when training large language models (LLMs)? In this work, we theoretical…

cs.GR2025

Neon: Negative Extrapolation From Self-Training Improves Image Generation

Sina Alemohammad, Zhangyang Wang, Richard G. Baraniuk

Scaling generative AI models is bottlenecked by the scarcity of high-quality training data. The ease of synthesizing from a generative model suggests using (unverified) synthetic d…

cs.CL2025

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang +5

Time series data are foundational in finance, healthcare, and energy domains. However, most existing methods and datasets remain focused on a narrow spectrum of tasks, such as fore…

cs.LG2025

On How Iterative Magnitude Pruning Discovers Local Receptive Fields in Fully Connected Neural Networks

William T. Redman, Zhangyang Wang, Alessandro Ingrosso +1

Since its use in the Lottery Ticket Hypothesis, iterative magnitude pruning (IMP) has become a popular method for extracting sparse subnetworks that can be trained to high performa…