collaborators

6 papers

cs.CR2026

Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks

Shangze Li, Chuancheng Shi, Simiao Xie +6

With the widespread deployment of large foundation models (LFMs) in open environments, safety threats are shifting from black-box jailbreaks toward white-box attacks that directly…

cs.AI2026

No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks

Simiao Xie, Chuancheng Shi, Shangze Li +5

With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to neuron-level white-box attacks that directly identify and ma…

cs.CV2026

Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models

Shaotian Li, Shangze Li, Chuancheng Shi +5

Large-scale vision-language models (VLMs) exhibit remarkable zero-shot capabilities, yet the internal mechanisms driving their anomaly detection (AD) performance remain poorly unde…

cs.CV2026

TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention

Chuancheng Shi, Shangze Li, Wenjun Lu +5

Despite their capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current defenses predominantly rely on the "locality hypothesis", suppres…

cs.CV2025

OmniPerson: Unified Identity-Preserving Pedestrian Generation

Changxiao Ma, Chao Yuan, Xincheng Shi +6

Person re-identification (ReID) suffers from a lack of large-scale high-quality training data due to challenges in data privacy and annotation costs. While previous approaches have…

cs.CV2025

Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

Chuancheng Shi, Shangze Li, Shiming Guo +9

Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilized. Yet outputs vary across cultural conte…