collaborators

6 papers

cs.AI2026

Enhancing SAE-based Steering via Neighbor Integrated Feature Selection

Yutian Liu, Xu Wang, Difan Zou

Sparse autoencoders (SAEs) disentangle model activations into interpretable features and are widely used for steering large language models. Most existing SAE-based steering method…

cs.CV2026

Toward Native Multimodal Modeling: A Roadmap

Siyu An, Junru Lu, Junnan Dong +18

Multimodal modeling represents a vital step from modality-agnostic reasoning toward world modeling. While early approaches predominantly rely on late-fusion that assembles encoders…

cs.LG2026

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders

Xu Wang, Bingqing Jiang, Yu Wan +3

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, huma…

cs.LG2025

Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders

Xu Wang, Yan Hu, Benyou Wang +1

Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavio…

cs.CL2025

Model Unlearning via Sparse Autoencoder Subspace Guided Projections

Xu Wang, Zihao Li, Benyou Wang +2

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing…

cs.CL2025

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis

Xu Wang, Yan Hu, Wenyu Du +3

Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth i…