9 papers
OPTD: On-Policy Transition Distillation with Consistency-Guided Adaptive Compression for Few-Step Diffusion Language Models
Xiaocheng Lu, Hualei Zhang, Shuhan Guo +8
Diffusion language models (dLLMs) can predict many tokens in parallel, but accurate generation still requires many iterative denoising steps. Few-step distillation accelerates deco…
Inverting the Hidden: Unveiling Multimodal Privacy Leakage in Collaborative LVLM Inference
Shuaifan Jin, Zhibo Wang, Qiyuan Wang +5
Collaborative inference deploys Large Vision-Language Models (LVLMs) by partitioning computation between edge devices and the cloud. While withholding raw inputs supposedly ensures…
Attention-Free and Lightweight Token Reduction for Efficient Vision-Language Models
Xuanyi Hao, Zuoyuan Zhang, Zhibo Wang +4
Vision-Language Models (VLMs) have achieved strong performance in multimodal understanding, yet remain challenging to deploy on resource-constrained edge devices due to the substan…
Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations
Zeyu Liu, Xuanzhi Feng, Sing Kwong Lai +6
The financial market is a typical low signal-to-noise ratio (SNR) setting, which often destabilizes off-policy maximum-entropy methods like Soft Actor-Critic (SAC). Specifically, n…
DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern
Xiaoyi Pang, Xuanyi Hao, Pengyu Liu +3
Recent intelligent systems integrate powerful Large Language Models (LLMs) through APIs, but their trustworthiness may be critically undermined by targeted attacks like backdoor an…
TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
Zhibo Wang, Zuoyuan Zhang, Xiaoyi Pang +4
Vision Transformers (ViTs) have demonstrated strong performance across a wide range of vision tasks, yet their substantial computational and memory demands hinder efficient deploym…
AFLoRA: Adaptive Federated Fine-Tuning of Large Language Models with Resource-Aware Low-Rank Adaption
Yajie Zhou, Xiaoyi Pang, Zhibo Wang
Federated fine-tuning has emerged as a promising approach to adapt foundation models to downstream tasks using decentralized data. However, real-world deployment remains challengin…
Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaboration
Shuaifan Jin, Xiaoyi Pang, Zhibo Wang +4
Recent studies improve on-device language model (LM) inference through end-cloud collaboration, where the end device retrieves useful information from cloud databases to enhance lo…
Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
Zhibo Wang, Zhiwei Chang, Jiahui Hu +4
Federated Learning (FL) exhibits privacy vulnerabilities under gradient inversion attacks (GIAs), which can extract private information from individual gradients. To enhance privac…