collaborators

5 papers

cs.CV2026

AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss

Mingju Gao, Jingkai Zhou, Kun Gai +2

Fréchet distance has recently emerged as an effective distribution-level objective for generator post-training, complementing the conventional sample-level diffusion and flow-match…

cs.CL2026

SAID: Accelerating Diffusion-Based Language Models via Scaffold-Aware Iterative Decoding

Na Li, Chengda Wang, Mingju Gao +1

Diffusion large language models (DLLMs) enable non-autoregressive generation by iteratively denoising corrupted token sequences with bidirectional context. Despite their ability to…

cs.CL2026

SemBlock: Semantic Boundary Dynamic Blocks for Diffusion LLMs

Xinrui Song, Zhuoran Wang, Mingju Gao +1

Diffusion language models (DLMs) generate text through iterative denoising, and blockwise decoding improves their practicality by committing tokens in local blocks. However, existi…

cs.CV2025

ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models

Chihan Huang, Hao Tang

Despite the success of deep learning across various domains, it remains vulnerable to adversarial attacks. Although many existing adversarial attack methods achieve high success ra…

cs.CL2025

CtrlDiff: Boosting Large Diffusion Language Models with Dynamic Block Prediction and Controllable Generation

Chihan Huang, Hao Tang

Although autoregressive models have dominated language modeling in recent years, there has been a growing interest in exploring alternative paradigms to the conventional next-token…