Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Improving Sparse Autoencoder with Dynamic Attention
Dongsheng Wang, Jinsen Zhang, Dawei Su +1
Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts…
cs.LG2025
LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data
Peng Wang, Dongsheng Wang, He Zhao +3
Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing adva…
cs.LG2025
Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
Bingjie Zhang, Hongkang Li, Changlong Shi +5
Multi-task learning (MTL) concurrently trains a model on diverse task datasets to exploit common features, thereby improving overall performance across the tasks. Recent studies ha…