Bingqing Jiang — accepted AI-conference papers

2026

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

Xu Wang, Bingqing Jiang, Yu Wan, Baosong Yang, Lingpeng Kong, Difan Zou

ICML 2026poster

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior. Recently, as diffusion language models (DLMs) have become an i…

Cited by 0 Source ↗Scholar ↗

2026

Personalized Federated Training of Diffusion Models with Privacy Guarantees

Kumar Kshitij Patel, Bingqing Jiang, A F M Mahfuzul Kabir, Weitong Zhang, Difan Zou, Lingxiao Wang

CVPR 2026

We propose a federated framework for training diffusion models on decentralized and private datasets. The method learns a shared generative model alongside personalized client models, allowing clients to benefit from cross-client structure while ensuring that the shared model cannot reproduce any cl

Cited by 0 Source ↗Scholar ↗