3 citations · 8 across the 24 of their papers we have counts for
9 papers · 1 filter
Vulnerability-Aware Robust Multimodal Adversarial Training
Junrui Zhang, Xinyu Zhao, Jie Peng +3
Multimodal learning has shown significant superiority on various tasks by integrating multiple modalities. However, the interdependencies among modalities increase the susceptibili…
Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures
Pingzhi Li, Morris Yu-Chao Huang, Zhen Tan +6
Knowledge Distillation (KD) accelerates training of large language models (LLMs) but poses intellectual property protection and LLM diversity risks. Existing KD detection methods b…
RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction
Leshu Li, Jiayin Qin, Jie Peng +8
3D Gaussian Splatting (3DGS) based Simultaneous Localization and Mapping (SLAM) systems can largely benefit from 3DGS's state-of-the-art rendering efficiency and accuracy, but have…
GEM: 3D Gaussian Splatting for Efficient and Accurate Cryo-EM Reconstruction
Huaizhi Qu, Xiao Wang, Gengwei Zhang +2
Cryo-electron microscopy (cryo-EM) has become a central tool for high-resolution structural biology, yet the massive scale of datasets (often exceeding 100k particle images) render…
I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts
Jiayi Xin, Sukwon Yun, Jie Peng +4
Modality fusion is a cornerstone of multimodal learning, enabling information integration from diverse data sources. However, vanilla fusion methods are limited by (1) inability to…
Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
Shuqing Luo, Pingzhi Li, Jie Peng +7
Mixture-of-experts (MoE) architectures could achieve impressive computational efficiency with expert parallelism, which relies heavily on all-to-all communication across devices. U…
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
Vaidehi Patil, Yi-Lin Sung, Peter Hase +3
LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multim…
Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
Mohan Zhang, Pingzhi Li, Jie Peng +2
Mixture-of-Experts (MoE) has successfully scaled up models while maintaining nearly constant computing costs. By employing a gating network to route input tokens, it selectively ac…
LightDefense: A Lightweight Uncertainty-Driven Defense against Jailbreaks via Shifted Token Distribution
Zhuoran Yang, Yanyong Zhang
Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies…