activity
20142025
most citedAPTQ: Attention-aware Post-Training Mixed-Precision Quantization for Large Language Models

26 citations · 35 across the 11 of their papers we have counts for

collaborators

6 papers

cs.LG2023

Lite it fly: An All-Deformable-Butterfly Network

Rui Lin, Jason Chun Lok Li, Jiajun Zhou +3

Most deep neural networks (DNNs) consist fundamentally of convolutional and/or fully connected layers, wherein the linear transform can be cast as the product between a filter matr…

cs.CV2023

Context-Aware Transformer for 3D Point Cloud Automatic Annotation

Xiaoyan Qian, Chang Liu, Xiaojuan Qi +3

3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious. However, existing methods are usually complicated, e.g., pipelined…

cs.LG20222 cited

PECAN: A Product-Quantized Content Addressable Memory Network

Jie Ran, Rui Lin, Jason Chun Lok Li +2

A novel deep neural network (DNN) architecture is proposed wherein the filtering and linear transform are realized solely with product quantization (PQ). This results in a natural…

cs.CV20222 cited

Multimodal Transformer for Automatic 3D Annotation and Object Detection

Chang Liu, Xiaoyan Qian, Binxiao Huang +4

Despite a growing number of datasets being collected for training 3D object detection models, significant human effort is still required to annotate 3D boxes on LiDAR scans. To aut…

physics.comp-ph20145 cited

An Approximate Framework for Quantum Transport Calculation with Model Order Reduction

Quan Chen, Jun Li, Chiyung Yam +3

A new approximate computational framework is proposed for computing the non-equilibrium charge density in the context of the non-equilibrium Green's function (NEGF) method for quan…

math.NA2014

A Constructive Algorithm for Decomposing a Tensor into a Finite Sum of Orthonormal Rank-1 Terms

Kim Batselier, Haotian Liu, Ngai Wong

We propose a constructive algorithm that decomposes an arbitrary real tensor into a finite sum of orthonormal rank-1 outer products. The algorithm, named TTr1SVD, works by converti…