Scholar

Xiangyu Chen

Google Scholar ID: xBv-PMEAAAAJ

PhD Student, Cornell University

Computer VisionMachine Learning

Citations & Impact

All-time

Citations

740

H-index

i10-index

Publications

Co-authors

Contact

Resume

Academic Achievements

DiffuBox: Refining 3D Object Detection with Point Diffusion (preprint)
Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery (NeurIPS 2023)
Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research (NeurIPS 2023)
Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning (UAI 2023)
Learning Iterative Neural Optimizers for Image Steganography (ICLR 2023)
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions (CVPR 2022)
Fixed Neural Network Steganography: Train the images, not the network (ICLR 2022)
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception (ICLR 2022)
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision (ICML 2021)
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize (CVPR 2020)
Transferable Active Grasping and Real Embodied Dataset (ICRA 2020)
TendencyRL: Multi-stage discriminative hints for efficient goal-oriented reverse curriculum learning (IROS 2019)
Semantic Predictive Control for Interpretable and Efficient Policy Learning (ICRA 2019)

Background

Research interests: Computer Vision, Machine Learning, and their intersections in Self-Driving.

Miscellany