4 papers
When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities
Weiduo Liao, Yunqiao Yang, Ying Wei
Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes…
Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts
Shengzhuang Chen, Ying Wei, Jonathan Richard Schwarz
We present Sparse Interpolated Mixture-of-Experts (SIMoE) instruction-tuning, an end-to-end algorithm designed to fine-tune a dense pre-trained Large Language Model (LLM) into a Mo…
CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models
Shengzhuang Chen, Yikai Liao, Xiaoxiao Sun +2
The advent of the foundation model era has sparked significant research interest in leveraging pre-trained representations for continual learning (CL), yielding a series of top-per…
Learning Where to Edit Vision Transformers
Yunqiao Yang, Long-Kai Huang, Shengzhuang Chen +2
Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintend…