15 papers
CST: Collaborative Selective Transmission for Communication-Efficient Multimodal Edge Inference
Hai Chi, Junrui Zhang, Rui Ning +4
Collaborative multimodal inference improves edge perception by combining observations from distributed sensing devices, but transmitting high-dimensional helper representations inc…
SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers
Jianing Deng, Yuanzhe Li, Jialu Wang +4
Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic com…
GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs
Jianing Deng, Song Wang, Dongwei Wang +4
Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization…
MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation
Ronyu Zhang, Aosong Cheng, Gaole Dai +8
Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error…
From Sparsity to Simplicity: Enabling Simpler Sequential Replacements via Sparse Attention Distillation
Yuxin Ren, Maxwell D Collins, Miao Hu +1
Self-attention serves as the core foundation of large-scale transformer pretraining, but its quadratic token interaction cost makes inference expensive. Replacing attention with si…
SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
Hengyu Fang, Yijiang Liu, Yuan Du +2
Vision-Language-Action (VLA) models exhibit unprecedented capabilities for embodied intelligence. However, their extensive computational and memory costs hinder their practical dep…