collaborators

17 papers

cs.CL2026

Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks

Haoming Wen, Shi Chen, Qingyu Shi +4

Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with only a few steps of supervised…

cs.AI2026

Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion

Yizhuo Lu, Changde Du, Qingyu Shi +5

Modeling the interplay between external stimuli and internal neural representations is a pivotal research area for Brain-Computer Interfaces (BCIs). A major limitation of prior wor…

cs.LG2026

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Qingyu Shi, Jinbin Bai, Zhuoran Zhao +7

Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture…

cs.LG2026

Threshold-Guided Optimization for Visual Generative Models

Jinbin Bai, Yu Lei, Qingyu Shi +6

Aligning large visual generative models with human feedback is often performed through pairwise preference optimization. While such approaches are conceptually simple, they fundame…

cs.LG2026

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models

Jinbin Bai, Yixuan Li, Yuchen Zhu +8

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to d…

cs.LG2026

Towards Customized Multimodal Role-Play

Chao Tang, Jianzong Wu, Qingyu Shi +5

Unified multimodal understanding and generation models enable richer human-AI interaction. Yet jointly customizing a character's persona, dialogue style, and visual identity while…