papers

Publications (127)

cs.RO2021

Road Mapping and Localization using Sparse Semantic Visual Features

Wentao Cheng, Sheng Yang, Maomin Zhou +3

We present a novel method for visual mapping and localization for autonomous vehicles, by extracting, modeling, and optimizing semantic road elements. Specifically, our method inte…

cond-mat.str-el2025

Thermal states emerging from low-entanglement background in disordered spin models

Yule Ma, Qianqian Chen, Mingyang Li +2

Thermalization in isolated quantum systems is governed by the eigenstate thermalization hypothesis, while strong disorder can induce its breakdown via many-body localization. Here…

cs.DC2026

Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices

Yangyijian Liu, Hongyi Ye, Mingyang Li +1

The paper introduces ATSInfer, a system that schedules tensor-level offloading between CPU and GPU to improve large language model inference on consumer devices, using static place…

#large language models#cpu-gpu offloading#tensor scheduling#inference optimization
cs.CV2020

Accelerating Neural Network Inference by Overflow Aware Quantization

Hongwei Xie, Shuo Zhang, Huanghao Ding +5

The inherent heavy computation of deep neural networks prevents their widespread applications. A widely used method for accelerating model inference is quantization, by replacing t…

cs.CV2026

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

Bin Ren, Hang Guo, Yan Shu +60

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a…

stat.ML2020

Semi-supervised deep learning for high-dimensional uncertainty quantification

Zequn Wang, Mingyang Li

Conventional uncertainty quantification methods usually lacks the capability of dealing with high-dimensional problems due to the curse of dimensionality. This paper presents a sem…