4 papers
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…
RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval
Dawei Su, Dongsheng Wang
Multimodal information retrieval (MMIR) has gained attention for its flexibility in handling text, images, or mixed queries and candidates. Recent breakthroughs in multimodal large…
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…
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…