6 papers
FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action Models
Jiuyi Xu, Chengyuan Qian, Zhengzhong Tu +2
Vision-Language-Action (VLA) models present a promising paradigm for general-purpose robot manipulation, but closed-loop deployment is often limited by inference efficiency: at eac…
VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models
Jiuyi Xu, Qing Jin, Meida Chen +3
Post-training quantization reduces the memory requirements of vision-language-action (VLA) models, but precision selection must account for the interaction between layer scope, num…
Generalization Bounds of Stochastic Gradient Descent in Homogeneous Neural Networks
Wenquan Ma, Yang Sui, Jiaye Teng +3
Algorithmic stability is among the most potent techniques in generalization analysis. However, its derivation usually requires a stepsize under non-convex…
LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition
Jiuyi Xu, Qing Jin, Meida Chen +3
Diffusion models have achieved remarkable success in image generation but their practical application is often hindered by the slow sampling speed. Prior efforts of improving effic…
AutoL2S: Auto Long-Short Reasoning for Efficient Large Language Models
Feng Luo, Yu-Neng Chuang, Guanchu Wang +8
Reasoning-capable large language models (LLMs) achieve strong performance on complex tasks but often exhibit overthinking after distillation, generating unnecessarily long chain-of…
Understanding Artificial Neural Network's Behavior from Neuron Activation Perspective
Yizhou Zhang, Yang Sui
This paper explores the intricate behavior of deep neural networks (DNNs) through the lens of neuron activation dynamics. We propose a probabilistic framework that can analyze mode…