6 papers
SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
Zhijing Zhang, Jiaqi Ding, Qianshan Wei +5
As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial solution for removing sensitive…
Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks
Yi Yu, Qixin Zhang, Shuhan Ye +6
Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We st…
Being-M0.5: A Real-Time Controllable Vision-Language-Motion Model
Bin Cao, Sipeng Zheng, Ye Wang +5
Human motion generation has emerged as a critical technology with transformative potential for real-world applications. However, existing vision-language-motion models (VLMMs) face…
Dual-Priv Pruning : Efficient Differential Private Fine-Tuning in Multimodal Large Language Models
Qianshan Wei, Jiaqi Li, Zihan You +9
Differential Privacy (DP) is a widely adopted technique, valued for its effectiveness in protecting the privacy of task-specific datasets, making it a critical tool for large langu…
Scaling Large Motion Models with Million-Level Human Motions
Ye Wang, Sipeng Zheng, Bin Cao +4
Inspired by the recent success of LLMs, the field of human motion understanding has increasingly shifted toward developing large motion models. Despite some progress, current effor…
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
Jiaqi Li, Qianshan Wei, Chuanyi Zhang +5
Machine unlearning empowers individuals with the `right to be forgotten' by removing their private or sensitive information encoded in machine learning models. However, it remains…