Yue Wang

56

Papers

184

Total Citations

Papers (56)

Driving Everywhere with Large Language Model Policy Adaptation

Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting

NeurIPS 2017arXiv

Language-Image Models with 3D Understanding

Graphical Time Warping for Joint Alignment of Multiple Curves

Semantics-aware Motion Retargeting with Vision-Language Models

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Neural Eulerian Scene Flow Fields

Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions

Model-Free Offline Reinforcement Learning with Enhanced Robustness

Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting

Out-of-Distribution Detection with Prototypical Outlier Proxy

Symbolic Representation for Any-to-Any Generative Tasks

Towards Realistic Scene Generation with LiDAR Diffusion Models

HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting

PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving

Parallelized Spatiotemporal Slot Binding for Videos

QBMK: Quantum-based Matching Kernels for Un-attributed Graphs

Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement

GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

Multimodal Industrial Anomaly Detection via Hybrid Fusion

Neural Map Prior for Autonomous Driving

PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow

FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization

ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries

Deep Closest Point: Learning Representations for Point Cloud Registration

On Feature Decorrelation in Self-Supervised Learning

SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-Powered Intelligent PhlatCam

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

Rethinking Few-shot Image Classification: A Good Embedding is All You Need?

Pillar-based Object Detection for Autonomous Driving

A Visual Navigation Perspective for Category-Level Object Pose Estimation

How to Re-enable PDE Loss for Physical Systems Modeling Under Partial Observation

EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis

CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-Scale Reinforcement Learning in Autonomous Driving

InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

Extrapolated Urban View Synthesis Benchmark

Learning an Implicit Physics Model for Image-based Fluid Simulation

COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets

Learning Temporally Consistent Video Depth from Video Diffusion Priors

Adaptive Wavelet-Positional Encoding for High-Frequency Information Learning in Implicit Neural Representation

Contradicted in Reliable, Replicated in Unreliable: Dual-Source Reference for Fake News Early Detection

EDA: Evolving and Distinct Anchors for Multimodal Motion Prediction

Social Physics Informed Diffusion Model for Crowd Simulation

E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings

PRNet: Self-Supervised Learning for Partial-to-Partial Registration

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training

Online Robust Reinforcement Learning with Model Uncertainty

Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation

R-Drop: Regularized Dropout for Neural Networks

Object DGCNN: 3D Object Detection using Dynamic Graphs

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions