4 papers
From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents
Binhong Wang, Haidong Kang, Yanfeng Zhang +3
Audio Large Language Models (Audio LLMs) are embedded in agents for smart homes, vehicles, wearables, and embodied systems, where acoustic inputs can propagate from perception into…
RSRA: Training-Free Probing of Representation Sensitivity for Efficient LoRA Rank Allocation
Jiaqi Liu, Haidong Kang, Qihui Zhao +2
Parameter-efficient fine-tuning enables large language models to adapt to downstream tasks with substantially lower computational and storage cost, and Low-Rank Adaptation (LoRA) i…
Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
Haidong Kang, Lianbo Ma, Guo Yu +1
Mixed precision quantization (MPQ) is an effective quantization approach to achieve accuracy-complexity trade-off of neural network, through assigning different bit-widths to netwo…
One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
Lianbo Ma, Yuee Zhou, Jianlun Ma +2
Weight quantization is an effective technique to compress deep neural networks for their deployment on edge devices with limited resources. Traditional loss-aware quantization meth…