Kai Wang

67

Papers

200

Total Citations

Papers (67)

Real-Time Video Generation with Pyramid Attention Broadcast

Efficient Online Reinforcement Learning for Diffusion Policy

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

Summarizing Stream Data for Memory-Constrained Online Continual Learning

ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement

FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

CALLIC: Content Adaptive Learning for Lossless Image Compression

Free-Lunch Color-Texture Disentanglement for Stylized Image Generation

StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

Info-Coevolution: An Efficient Framework for Data Model Coevolution

InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models

Single-View Graph Contrastive Learning with Soft Neighborhood Awareness

EnMatch: Matchmaking for Better Player Engagement via Neural Combinatorial Optimization

Unsupervised Learning for Class Distribution Mismatch

Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching

DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness

Richer Convolutional Features for Edge Detection

Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models

A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Semantic Drift Compensation for Class-Incremental Learning

Modeling Motion With Multi-Modal Features for Text-Based Video Segmentation

CAFE: Learning To Condense Dataset by Aligning Features

Crafting Better Contrastive Views for Siamese Representation Learning

MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning

An Efficient Training Approach for Very Large Scale Face Recognition

BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency

Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning

MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style

Interpretable Visual Reasoning via Induced Symbolic Space

Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models

Dataset Quantization

DREAM: Efficient Dataset Distillation by Representative Matching

Versatile Diffusion: Text, Images and Variations All in One Diffusion Model

CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision

Suppressing Mislabeled Data via Grouping and Self-Attention

The Shape Part Slot Machine: Contact-Based Reasoning for Generating 3D Shapes from Parts

Point-to-Box Network for Accurate Object Detection via Single Point Supervision

DLME: Deep Local-Flatness Manifold Embedding

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction

One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models

Optimizing for the Shortest Path in Denoising Diffusion Model

The Art of Deception: Color Visual Illusions and Diffusion Models

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

Distilling Long-tailed Datasets

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing

AR-1-to-3: Single Image to Consistent 3D Object via Next-View Prediction

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning

LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

Drawing Informative Gradients from Sources: A One-stage Transfer Learning Framework for Cross-city Spatiotemporal Forecasting

Automatically Learning Compact Quality-aware Surrogates for Optimization Problems

Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Making by Reinforcement Learning

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Dataset Distillation via Factorization

Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision Losses

Less-forgetting Multi-lingual Fine-tuning

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.

Does Graph Distillation See Like Vision Dataset Counterpart?

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

Expanding Small-Scale Datasets with Guided Imagination