Search Results for author: Pei Sun

Found 21 papers, 4 papers with code

Theoretical foundations of studying criticality in the brain

no code implementations9 Jun 2023 Yang Tian, Zeren Tan, Hedong Hou, Guoqi Li, Aohua Cheng, Yike Qiu, Kangyu Weng, Chun Chen, Pei Sun

These problems stem from the non-triviality and immaturity of the physical theories that analytically derive brain criticality and the statistic techniques that estimate brain criticality from empirical data.

WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting

no code implementations7 Apr 2023 Kan Chen, Runzhou Ge, Hang Qiu, Rami Ai-Rfou, Charles R. Qi, Xuanyu Zhou, Zoey Yang, Scott Ettinger, Pei Sun, Zhaoqi Leng, Mustafa Mustafa, Ivan Bogun, Weiyue Wang, Mingxing Tan, Dragomir Anguelov

To study the effect of these modular approaches, design new paradigms that mitigate these limitations, and accelerate the development of end-to-end motion forecasting models, we augment the Waymo Open Motion Dataset (WOMD) with large-scale, high-quality, diverse LiDAR data for the motion forecasting task.

Motion Forecasting

Koopman neural operator as a mesh-free solver of non-linear partial differential equations

1 code implementation24 Jan 2023 Wei Xiong, Xiaomeng Huang, Ziyang Zhang, Ruixuan Deng, Pei Sun, Yang Tian

In machine learning, numerous latest advances of solver designs are accomplished in developing neural operators, a kind of mesh-free approximators of the infinite-dimensional operators that map between different parameterization spaces of equation solutions.

KoopmanLab: machine learning for solving complex physics equations

1 code implementation3 Jan 2023 Wei Xiong, Muyuan Ma, Xiaomeng Huang, Ziyang Zhang, Pei Sun, Yang Tian

To overcome this challenge, we present KoopmanLab, an efficient module of the Koopman neural operator family, for learning PDEs without analytic solutions or closed forms.

Statistical Physics of Deep Neural Networks: Initialization toward Optimal Channels

no code implementations4 Dec 2022 Kangyu Weng, Aohua Cheng, Ziyang Zhang, Pei Sun, Yang Tian

Finally, we analyze our findings with information bottleneck theory to confirm the precise relations among dynamic isometry, mutual information maximization, and optimal channel properties in deep learning.

LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

no code implementations10 Oct 2022 Chenxi Liu, Zhaoqi Leng, Pei Sun, Shuyang Cheng, Charles R. Qi, Yin Zhou, Mingxing Tan, Dragomir Anguelov

Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving.

3D Object Detection Autonomous Driving +2

A unified theory of information transfer and causal relation

no code implementations21 Apr 2022 Yang Tian, Hedong Hou, Yaoyuan Wang, Ziyang Zhang, Pei Sun

Information transfer between coupled stochastic dynamics, measured by transfer entropy and information flow, is suggested as a physical process underlying the causal relation of systems.

Causal Inference

Self-organized critical dynamics of RNA virus evolution

no code implementations19 Apr 2022 Xiaofei Ge, Kaichao You, Zeren Tan, Hedong Hou, Yang Tian, Pei Sun

We anticipate our approach to be a general formalism to portray RNA virus evolution and help identify potential virus lineages to be concerned.

Offboard 3D Object Detection from Point Cloud Sequences

no code implementations CVPR 2021 Charles R. Qi, Yin Zhou, Mahyar Najibi, Pei Sun, Khoa Vo, Boyang Deng, Dragomir Anguelov

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality 3D labels.

3D Object Detection 3D Object Recognition +1

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

1 code implementation20 May 2020 Alex Bewley, Pei Sun, Thomas Mensink, Dragomir Anguelov, Cristian Sminchisescu

This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images.

3D Object Detection Autonomous Driving +1

End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds

no code implementations15 Oct 2019 Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, Vijay Vasudevan

In this paper, we aim to synergize the birds-eye view and the perspective view and propose a novel end-to-end multi-view fusion (MVF) algorithm, which can effectively learn to utilize the complementary information from both.

3D Object Detection object-detection

StarNet: Targeted Computation for Object Detection in Point Clouds

no code implementations29 Aug 2019 Jiquan Ngiam, Benjamin Caine, Wei Han, Brandon Yang, Yuning Chai, Pei Sun, Yin Zhou, Xi Yi, Ouais Alsharif, Patrick Nguyen, Zhifeng Chen, Jonathon Shlens, Vijay Vasudevan

We show how our redesign---namely using only local information and using sampling instead of learned proposals---leads to a significantly more flexible and adaptable system: we demonstrate how we can vary the computational cost of a single trained StarNet without retraining, and how we can target proposals towards areas of interest with priors and heuristics.

3D Object Detection object-detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.