Yu-Chiang Frank Wang

38

Papers

88

Total Citations

Papers (38)

SAM4MLLM: Enhance Multi-Modal Large Language Model for Referring Expression Segmentation

Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models

Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks

Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction

RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering

Segment Anything, Even Occluded

UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing

Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

Continual Personalization for Diffusion Models

EMLoC: Emulator-based Memory-efficient Fine-tuning with LoRA Correction

NeurIPS 2025arXiv

Language-Guided Transformer for Federated Multi-Label Classification

GSNeRF: Generalizable Semantic Neural Radiance Fields with Enhanced 3D Scene Understanding

Propagated Image Filtering

Learning Cross-Domain Landmarks for Heterogeneous Domain Adaptation

Multi-Label Zero-Shot Learning With Structured Knowledge Graphs

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation

Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation

Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification

Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis

Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment

LayoutTransformer: Scene Layout Generation With Conceptual and Spatial Diversity

NeurMiPs: Neural Mixture of Planar Experts for View Synthesis

Scene Graph Expansion for Semantics-Guided Image Outpainting

Bias-Eliminating Augmentation Learning for Debiased Federated Learning

Unsupervised Domain Adaptation With Imbalanced Cross-Domain Data

No More Discrimination: Cross City Adaptation of Road Scene Segmenters

Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification

Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation

Efficient Model Personalization in Federated Learning via Client-Specific Prompt Generation

Learning to Learn in a Semi-Supervised Fashion

VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models

VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models

3D Gaussian Inpainting with Depth-Guided Cross-View Consistency

Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration

Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

Adversarial Teacher-Student Representation Learning for Domain Generalization