10 citations · 13 across the 4 of their papers we have counts for
5 papers
CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search
Guanhua Ding, Zi Wang, Ruichao Li +1
The best two-bit weight quantizers for large language models, such as QTIP and Proteus, rotate each weight matrix by a random orthogonal transform, which must be undone at every de…
Multipath Extended Target Tracking with Labeled Random Finite Sets
Guanhua Ding, Qinchen Wu, Jinping Sun +3
High-resolution radar sensors are critical for autonomous systems but pose significant challenges to traditional tracking algorithms due to the generation of multiple measurements…
OptiPMB: Enhancing 3D Multi-Object Tracking with Optimized Poisson Multi-Bernoulli Filtering
Guanhua Ding, Yuxuan Xia, Runwei Guan +5
Accurate 3D multi-object tracking (MOT) is crucial for autonomous driving, as it enables robust perception, navigation, and planning in complex environments. While deep learning-ba…
ProbRadarM3F: mmWave Radar based Human Skeletal Pose Estimation with Probability Map Guided Multi-Format Feature Fusion
Bing Zhu, Zixin He, Weiyi Xiong +3
Millimeter wave (mmWave) radar is a non-intrusive privacy and relatively convenient and inexpensive device, which has been demonstrated to be applicable in place of RGB cameras in…
Separate, Dynamic and Differentiable (SMART) Pruner for Block/Output Channel Pruning on Computer Vision Tasks
Guanhua Ding, Zexi Ye, Zhen Zhong +2
Block pruning, which eliminates contiguous blocks of weights, is a structural pruning method that can significantly enhance the performance of neural processing units (NPUs). In in…