17 papers
SuperAI: Merging Capabilities Across Heterogeneous Foundation Models
Jingtong Dou, Chuancheng Shi, Wenhua Wu +4
Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable artificial intelligence (AI) sys…
A note on stability conditions on product-quotient surfaces
Uttaran Dutta
Let be a product-quotient surface, which is by definition a minimal resolution of , where are smooth curves of genus and is a finite group…
Hub-Spectral Activation of Latent Multimodal Knowledge
Ying Guo, Haidong Chen, Linrui Xu +7
Multimodal representation learning seeks shared representations for cross-modal retrieval and knowledge transfer. Hub-based binding reduces pairwise supervision costs, but separate…
V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors
Shichao Kan, Chengpeng Hong, Jingtong Dou +8
As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors a…
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…
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…
A Heuristic Perspective on Debiasing Language Models
Tian Lan, Yemin Wang, Chuancheng Shi +6
Language models (LMs) often acquire various biases during pre-training and may express them in interactions, potentially causing social harm. Existing methods often rely on counter…
One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs
Enyi Shi, Fei Shen, Chuancheng Shi +4
As large vision-language models (LVLMs) are deployed globally, the combination of multilingual instructions and visual information makes malicious attacks more covert and sophistic…
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…
Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities
Jingtong Dou, Chuancheng Shi, Jian Wang +3
As generative artificial intelligence evolves, deepfake attacks have escalated from single-modality manipulations to complex, multimodal threats. Existing forensic techniques face…
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models
Enyi Shi, Fei Shen, Chuancheng Shi +5
With the widespread deployment of vision-language large models (VLLMs), their safety alignment faces dual challenges across languages and modalities. Existing methods model multili…
OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
Chuancheng Shi, Wenhua Wu, Fei Shen +3
Text-to-image (T2I) models face significant safety risks from adversarial induction, yet current concept erasure methods often cause collateral damage to benign attributes when sup…
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…
DNA: Uncovering Universal Latent Forgery Knowledge
Jingtong Dou, Chuancheng Shi, Yemin Wang +6
As generative AI achieves hyper-realism, superficial artifact detection has become obsolete. While prevailing methods rely on resource-intensive fine-tuning of black-box backbones,…
HarmoniAD: Harmonizing Local Structures and Global Semantics for Anomaly Detection
Naiqi Zhang, Chuancheng Shi, Jingtong Dou +3
Anomaly detection is crucial in industrial product quality inspection. Failing to detect tiny defects often leads to serious consequences. Existing methods face a structure-semanti…
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…
FashionPose: Unified Text-Driven Fashion Synthesis with Joint Geometric and Photometric Control
Chuancheng Shi, Shaotian Li, Zhenlong Yuan +2
Realistic and controllable garment synthesis is essential for fashion e-commerce, yet it demands precise coordination between human pose geometry and environmental photometry. Conv…