Yunchao Wei

Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing

arXiv 2026

VideoWorld 2: Learning Transferable Knowledge from Real-world Videos

arXiv 2026

Let ViT Speak: Generative Language-Image Pre-training

arXiv 2026

ThinkGen: Generalized Thinking for Visual Generation

arXiv 2025

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

arXiv 2025

Taming Generative Synthetic Data for X-ray Prohibited Item Detection

arXiv 2025

CharaConsist: Fine-Grained Consistent Character Generation

ICCV 2025

Frequency-Aware Deepfake Detection: Improving Generalizability through Frequency Space Learning

arXiv 2024

Foundations and Recent Trends in Multimodal Mobile Agents: A Survey

arXiv 2024

Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation

arXiv 2024

Region-Adaptive Transform with Segmentation Prior for Image Compression

arXiv 2024

Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention

arXiv 2024

Transferable and Principled Efficiency for Open-Vocabulary Segmentation

CVPR 2024 1

ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance

arXiv 2024

Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection

CVPR 2024 1

SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model

ICCV 2023 1

StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

arXiv 2023

CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation

arXiv 2023