841 citations · 1.1k across the 23 of their papers we have counts for
24 papers
Rethinking Closed-loop Training for Autonomous Driving
Chris Zhang, Runsheng Guo, Wenyuan Zeng +5
Recent advances in high-fidelity simulators have enabled closed-loop training of autonomous driving agents, potentially solving the distribution shift in training v.s. deployment a…
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention
Wenxuan Zeng, Meng Li, Wenjie Xiong +5
Secure multi-party computation (MPC) enables computation directly on encrypted data and protects both data and model privacy in deep learning inference. However, existing neural ne…
Converge to the Truth: Factual Error Correction via Iterative Constrained Editing
Jiangjie Chen, Rui Xu, Wenxuan Zeng +3
Given a possibly false claim sentence, how can we automatically correct it with minimal editing? Existing methods either require a large number of pairs of false and corrected clai…
Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Dingwen Zhang, Wenyuan Zeng, Guangyu Guo +4
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches wo…
Just Label What You Need: Fine-Grained Active Selection for Perception and Prediction through Partially Labeled Scenes
Sean Segal, Nishanth Kumar, Sergio Casas +4
Self-driving vehicles must perceive and predict the future positions of nearby actors in order to avoid collisions and drive safely. A learned deep learning module is often respons…
End-to-end Interpretable Neural Motion Planner
Wenyuan Zeng, Wenjie Luo, Simon Suo +4
In this paper, we propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interaction…
LaneRCNN: Distributed Representations for Graph-Centric Motion Forecasting
Wenyuan Zeng, Ming Liang, Renjie Liao +1
Forecasting the future behaviors of dynamic actors is an important task in many robotics applications such as self-driving. It is extremely challenging as actors have latent intent…
Network Automatic Pruning: Start NAP and Take a Nap
Wenyuan Zeng, Yuwen Xiong, Raquel Urtasun
Network pruning can significantly reduce the computation and memory footprint of large neural networks. To achieve a good trade-off between model size and performance, popular prun…
Safety-Oriented Pedestrian Motion and Scene Occupancy Forecasting
Katie Luo, Sergio Casas, Renjie Liao +4
In this paper, we address the important problem in self-driving of forecasting multi-pedestrian motion and their shared scene occupancy map, critical for safe navigation. Our contr…
Deep Structured Reactive Planning
Jerry Liu, Wenyuan Zeng, Raquel Urtasun +1
An intelligent agent operating in the real-world must balance achieving its goal with maintaining the safety and comfort of not only itself, but also other participants within the…
Auto4D: Learning to Label 4D Objects from Sequential Point Clouds
Bin Yang, Min Bai, Ming Liang +2
In the past few years we have seen great advances in object perception (particularly in 4D space-time dimensions) thanks to deep learning methods. However, they typically rely on l…
Self-Supervised Representation Learning from Flow Equivariance
Yuwen Xiong, Mengye Ren, Wenyuan Zeng +1
Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few ob…
Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving
Bob Wei, Mengye Ren, Wenyuan Zeng +3
In this paper, we propose an end-to-end self-driving network featuring a sparse attention module that learns to automatically attend to important regions of the input. The attentio…
Permute, Quantize, and Fine-tune: Efficient Compression of Neural Networks
Julieta Martinez, Jashan Shewakramani, Ting Wei Liu +3
Compressing large neural networks is an important step for their deployment in resource-constrained computational platforms. In this context, vector quantization is an appealing fr…
Weakly-supervised 3D Shape Completion in the Wild
Jiayuan Gu, Wei-Chiu Ma, Sivabalan Manivasagam +5
3D shape completion for real data is important but challenging, since partial point clouds acquired by real-world sensors are usually sparse, noisy and unaligned. Different from pr…
V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Prediction
Tsun-Hsuan Wang, Sivabalan Manivasagam, Ming Liang +4
In this paper, we explore the use of vehicle-to-vehicle (V2V) communication to improve the perception and motion forecasting performance of self-driving vehicles. By intelligently…
DSDNet: Deep Structured self-Driving Network
Wenyuan Zeng, Shenlong Wang, Renjie Liao +3
In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network. T…
End-to-end Contextual Perception and Prediction with Interaction Transformer
Lingyun Luke Li, Bin Yang, Ming Liang +4
In this paper, we tackle the problem of detecting objects in 3D and forecasting their future motion in the context of self-driving. Towards this goal, we design a novel approach th…
PnPNet: End-to-End Perception and Prediction with Tracking in the Loop
Ming Liang, Bin Yang, Wenyuan Zeng +4
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles. Towards this goal we propose PnPNet, an end-to-end model that takes as inp…
LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World
Sivabalan Manivasagam, Shenlong Wang, Kelvin Wong +6
We tackle the problem of producing realistic simulations of LiDAR point clouds, the sensor of preference for most self-driving vehicles. We argue that, by leveraging real data, we…
Differentiable Compositional Kernel Learning for Gaussian Processes
Shengyang Sun, Guodong Zhang, Chaoqi Wang +3
The generalization properties of Gaussian processes depend heavily on the choice of kernel, and this choice remains a dark art. We present the Neural Kernel Network (NKN), a flexib…
Learning to Reweight Examples for Robust Deep Learning
Mengye Ren, Wenyuan Zeng, Bin Yang +1
Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit t…
Efficient Summarization with Read-Again and Copy Mechanism
Wenyuan Zeng, Wenjie Luo, Sanja Fidler +1
Encoder-decoder models have been widely used to solve sequence to sequence prediction tasks. However current approaches suffer from two shortcomings. First, the encoders compute a…
Incorporating Relation Paths in Neural Relation Extraction
Wenyuan Zeng, Yankai Lin, Zhiyuan Liu +1
Distantly supervised relation extraction has been widely used to find novel relational facts from plain text. To predict the relation between a pair of two target entities, existin…