Zhe Wang

35

Papers

147

Total Citations

Papers (35)

RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

AT4CTR: Auxiliary Match Tasks for Enhancing Click-Through Rate Prediction

Radiology Report Generation via Multi-objective Preference Optimization

PurpCode: Reasoning for Safer Code Generation

NeurIPS 2025arXiv

nuCraft: Crafting High Resolution 3D Semantic Occupancy for Unified 3D Scene Understanding

Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning

TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion

Learnable Retrieval Enhanced Visual-Text Alignment and Fusion for Radiology Report Generation

MamV2XCalib: V2X-based Target-less Infrastructure Camera Calibration with State Space Model

FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers

PScalpel: A Machine Learning-based Guider for Protein Phase-Separating Behaviour Alteration

Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities

Enhancing NLU in Large Language Models Using Adversarial Noisy Instruction Tuning

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

Attention Calibration for Disentangled Text-to-Image Personalization

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations

MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization

Magicoder: Empowering Code Generation with OSS-Instruct

Learning Depth-Guided Convolutions for Monocular 3D Object Detection

PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection

AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching

ST3D: Self-Training for Unsupervised Domain Adaptation on 3D Object Detection

RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior

ConQueR: Query Contrast Voxel-DETR for 3D Object Detection

Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving

Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks

ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language

PPT: Token-Pruned Pose Transformer for Monocular and Multi-View Human Pose Estimation

RDO-Q: Extremely Fine-Grained Channel-Wise Quantization via Rate-Distortion Optimization

WaveGAN: Frequency-Aware GAN for High-Fidelity Few-Shot Image Generation

Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

NeurIPS 2020arXiv

Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering

NeurIPS 2022arXiv

Towards Efficient 3D Object Detection with Knowledge Distillation

NeurIPS 2022arXiv

FreGAN: Exploiting Frequency Components for Training GANs under Limited Data

NeurIPS 2022arXiv