activity
20242026
collaborators

8 papers

cs.LG2026

LASER: Loss-Aware Singular-value Decomposition and Rank Allocation for Efficient Low-Precision Vision-Language Models

Haiyu Wang, Yutong Wang, Leshu Li +2

Vision-language models (VLMs) deliver strong multimodal reasoning capabilities, but their large computational cost and high parameter counts make deployment challenging on resource…

cs.LG2026

DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation

Zining Liu, Yunhai Hu, Tianhua Xia +4

Speculative decoding (SD) has proven to be an effective technique for accelerating autoregressive generation in large language models (LLMs) however, its application to vision-lang…

cs.LG2026

CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts

Xiangyang Yin, Xingyu Liu, Tianhua Xia +5

Outliers have emerged as a fundamental bottleneck in preserving accuracy for low-precision large models, particularly within Mixture-of-Experts (MoE) architectures that are increas…

cs.CV2026

WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models

Haiyu Wang, Yutong Wang, Jack Jiang +1

Singular Value Decomposition (SVD) has become an important technique for reducing the computational burden of Vision Language Models (VLMs), which play a central role in tasks such…

cs.CV2025

CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models

Kedong Xiu, Sai Qian Zhang

As Vision-Language Models (VLMs) are increasingly deployed in split-DNN configurations--with visual encoders (e.g., ResNet, ViT) operating on user devices and sending intermediate…

cs.AR2025

Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing

Tianhua Xia, Sai Qian Zhang

Running Large Language Models (LLMs) on edge devices is crucial for reducing latency, improving real-time processing, and enhancing privacy. By performing inference directly on the…