publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. no_single.png
    No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks
    Simiao Xie, Chuancheng Shi , Shangze Li, and 5 more authors
    Under Review., 2026
    arXiv
  2. one_anchor.png
    One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs
    Enyi Shi, Fei Shen, Chuancheng Shi , and 4 more authors
    Under Review., 2026
    arXiv
  3. TISNE.png
    Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models
    Enyi Shi, Fei Shen, Chuancheng Shi , and 5 more authors
    Under Review., 2026
  4. SeqNeuron.png
    SeqNeuronVEP: Recovering Assay-Relevant Variant-Effect Signals Beyond PLM Likelihood
    Hongyi Gao, Chuancheng Shi , Yanli Li, and 6 more authors
    Under Review., 2026
  5. V-FIND.png
    V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors
    Shichao Kan, Chengpeng Hong, Jingtong Dou, and 7 more authors
    Under Review., 2026
    arXiv
  6. SIM.png
    SimFoundry: Closed-Loop Simulation Generation with Embodied Program Validation
    Wei Liu, Jiaqi Cheng, Zhaoren Zhou, and 1 more author
    Under Review., 2026
  7. UATS.png
    Uniformity Matters: Spatio-Temporal Token Reduction for Memory-Efficient VideoLLMs
    Yutong Wang, Zhuqiang Lu, Chuancheng Shi , and 4 more authors
    Under Review., 2026
  8. Moving.png
    Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
    Shangze Li*, Chuancheng Shi* , Simiao Xie, and 6 more authors
    Under Review., 2026
    arXiv
  9. ACMMM 2026
    acm_bni.png
    Beyond Surface Artifacts: Capturing Shared Latent Forgery Knowledge Across Modalities
    Jingtong Dou*, Chuancheng Shi* , Jian Wang, and 3 more authors
    ACMMM 2026, 2026
    arXiv
  10. ACMMM 2026
    conf.png
    ConfAvatar: Confidence-Aware Self-Bootstrapping for Monocular 4D Head Avatar Reconstruction
    ACM MM 2026, 2026
    arXiv
  11. ACMMM 2026
    ad_w.png
    Latent Anomaly Knowledge in VLMs: Excavation and Activation via Anomaly-Sensitive Neurons
    Shaotian Li, Shangze Li, Chuancheng Shi , and 5 more authors
    ACM MM 2026, 2026
  12. culture_pami.png
    Unlocking Latent Cultural Knowledge in Multilingual Text-to-Image Models
    Chuancheng Shi , Shangze Li, Wenhua Wu, and 2 more authors
    Under Review., 2026
  13. ECCV 2026
    ortho.png
    OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
    Chuancheng Shi , Wenhua Wu, Fei Shen, and 3 more authors
    European Conference on Computer Vision (ECCV 2026), 2026
    arXiv
  14. ICML 2026
    DNA.png
    DNA: Uncovering Universal Latent Forgery Knowledge
    Jingtong Dou*, Chuancheng Shi* , Yemin Wang, and 6 more authors
    International Conference on Machine Learning (ICML 2026), 2026
    arXiv
  15. ICML 2026
    neuron_ers.png
    TraceRouter: Robust Safety for Foundation Models via Path-Level Intervention
    Chuancheng Shi* , Shangze Li*, Wenjun Lu, and 5 more authors
    International Conference on Machine Learning (ICML 2026), 2026
    arXiv
  16. deb.png
    A Heuristic Perspective on Debiasing Language Models
    Tian Lan, Yemin Wang, Chuancheng Shi , and 6 more authors
    Under Review., 2026
  17. ICME 2026
    gongye.png
    HarmoniAD: Harmonizing Local Structures and Global Semantics for Anomaly Detection
    Naiqi Zhang*, Chuancheng Shi* , Jingtong Dou, and 3 more authors
    International Conference on Multimedia and Expo (ICME 2026), 2026
    arXiv

2025

  1. CVPR 2026 Highlight
    culture.png
    Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation
    Chuancheng Shi* , Shangze Li*, Shiming Guo*, and 8 more authors
    Computer Vision and Pattern Recognition (CVPR 2026 Highlight), 2025
    arXiv
  2. AAAI 2026 Oral
    hand.png
    SGMHand: Structure-Guided Modulation for Structure-Aware Hand Inpainting
    Chuancheng Shi* , Shiming Guo*, Ke Shui, and 2 more authors
    AAAI Conference on Artificial Intelligence (AAAI Oral), 2025
    PDF
  3. fashionpose.png
    FashionPose: Text to Pose to Relight Image Generation for Personalized Fashion Visualization
    Chuancheng Shi , Naiqi Zhang, Canran Xiao, and 3 more authors
    Under Review., 2025