5 papers
LiftQuant: Continuous Bit-Width LLM via Dimensional Lifting and Projection
Liulu He, XuanAng Liu, Juntao Liu +8
Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), resulting in a ``deployment gap" where Large Language Models cannot be…
CoSTA: Cognitive-State-Conditioned TTS Data Augmentation Using ASR Transcripts for Alzheimer's Disease Detection
Yin-Long Liu, Yuanchao Li, Yiming Wang +8
Speech-based Alzheimer's Disease (AD) detection is constrained by scarce pathological speech data. To address this, we propose CoSTA, a Text-to-Speech (TTS)-based data augmentation…
BASE-Q: Bias and Asymmetric Scaling Enhanced Rotational Quantization for Large Language Models
Liulu He, Shenli Zheng, Karwei Sun +6
Rotations have become essential to state-of-the-art quantization pipelines for large language models (LLMs) by effectively smoothing outliers in weights and activations. However, f…
FBQuant: FeedBack Quantization for Large Language Models
Yijiang Liu, Hengyu Fang, Liulu He +4
Deploying Large Language Models (LLMs) on edge devices is increasingly important, as it eliminates reliance on network connections, reduces expensive API calls, and enhances user p…
SFC: Achieve Accurate Fast Convolution under Low-precision Arithmetic
Liulu He, Yufei Zhao, Rui Gao +2
Fast convolution algorithms, including Winograd and FFT, can efficiently accelerate convolution operations in deep models. However, these algorithms depend on high-precision arithm…