Publications (10)
NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model
Zhongqun Zhang, Hengfei Wang, Ziwei Yu +3
Modeling the physical contacts between the hand and object is standard for refining inaccurate hand poses and generating novel human grasp in 3D hand-object reconstruction. However…
Scalable Gaussian Process Classification with Additive Noise for Various Likelihoods
Haitao Liu, Yew-Soon Ong, Ziwei Yu +2
Gaussian process classification (GPC) provides a flexible and powerful statistical framework describing joint distributions over function space. Conventional GPCs however suffer fr…
HiFloat4 Format for Language Model Pre-training on Ascend NPUs
Mehran Taghian, Yunke Peng, Xing Huang +22
Large foundation models have become central to modern machine learning, with performance scaling predictably with model size and data. However, training and deploying such models i…
Enhancing Video Super-Resolution via Implicit Resampling-based Alignment
Kai Xu, Ziwei Yu, Xin Wang +2
In video super-resolution, it is common to use a frame-wise alignment to support the propagation of information over time. The role of alignment is well-studied for low-level enhan…
Wizundry: A Cooperative Wizard of Oz Platform for Simulating Future Speech-based Interfaces with Multiple Wizards
Siying Hu, Hen Chen Yen, Ziwei Yu +3
Wizard of Oz (WoZ) as a prototyping method has been used to simulate intelligent user interfaces, particularly for speech-based systems. However, as our societies' expectations on…
UV-Based 3D Hand-Object Reconstruction with Grasp Optimization
Ziwei Yu, Linlin Yang, You Xie +2
We propose a novel framework for 3D hand shape reconstruction and hand-object grasp optimization from a single RGB image. The representation of hand-object contact regions is criti…
Overcoming the Trade-off Between Accuracy and Plausibility in 3D Hand Shape Reconstruction
Ziwei Yu, Chen Li, Linlin Yang +4
Direct mesh fitting for 3D hand shape reconstruction is highly accurate. However, the reconstructed meshes are prone to artifacts and do not appear as plausible hand shapes. Conver…
Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation
Ziwei Yu, Linlin Yang, Shicheng Chen +1
This paper addresses the 3D point cloud reconstruction and 3D pose estimation of the human hand from a single RGB image. To that end, we present a novel pipeline for local and glob…
HiFloat4 Format for Language Model Inference
Yuanyong Luo, Jing Huang, Yu Cheng +19
This paper introduces HiFloat4 (HiF4), a block floating-point data format tailored for deep learning. Each HiF4 unit packs 64 4-bit elements with 32 bits of shared scaling metadata…
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats
Pengxiang Zhao, Hui-Ling Zhen, Xing Li +10
As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family…