Xinchao Wang

120

Papers

652

Total Citations

Papers (120)

DeepCache: Accelerating Diffusion Models for Free

Kolmogorov-Arnold Transformer

dKV-Cache: The Cache for Diffusion Language Models

Thinkless: LLM Learns When to Think

FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

POSTA: A Go-to Framework for Customized Artistic Poster Generation

CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up

Hash3D: Training-free Acceleration for 3D Generation

Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching

Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling

Relation Rectification in Diffusion Model

Neural Lineage

Ultra-Resolution Adaptation with Ease

1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering

Generative Sparse-View Gaussian Splatting

Unsegment Anything by Simulating Deformation

Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classifications

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning

Distilled Datamodel with Reverse Gradient Matching

Heavy Labels Out! Dataset Distillation with Label Space Lightening

InceptionNeXt: When Inception Meets ConvNeXt

Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation

Receptive Fields As Experts in Convolutional Neural Architectures

Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models

MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization

What Players Do With the Ball: A Physically Constrained Interaction Modeling

On Compressing Deep Models by Low Rank and Sparse Decomposition

Geometry-Aware Scene Text Detection With Instance Transformation Network

Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More

World From Blur

DEPARA: Deep Attribution Graph for Deep Knowledge Transferability

Distilling Knowledge From Graph Convolutional Networks

Learning Oracle Attention for High-Fidelity Face Completion

Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN

Online Multiple Object Tracking With Cross-Task Synergy

Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking

Scene Essence

Tree-Like Decision Distillation

Training Generative Adversarial Networks in One Stage

Turning Frequency to Resolution: Video Super-Resolution via Event Cameras

Amalgamating Knowledge From Heterogeneous Graph Neural Networks

Point2Seq: Detecting 3D Objects As Sequences

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

MetaFormer Is Actually What You Need for Vision

CAFE: Learning To Condense Dataset by Aligning Features

Slimmable Domain Adaptation

Geometric Structure Preserving Warp for Natural Image Stitching

Shunted Self-Attention via Multi-Scale Token Aggregation

PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision

EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning

DepGraph: Towards Any Structural Pruning

Task Residual for Tuning Vision-Language Models

Distribution Shift Inversion for Out-of-Distribution Prediction

Diffusion Probabilistic Model Made Slim

Slimmable Dataset Condensation

Deep Graph Reprogramming

Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer

Partial Network Cloning

Non-Markovian Globally Consistent Multi-Object Tracking

Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation

Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts

Mutual-Complementing Framework for Nuclei Detection and Segmentation in Pathology Image

Self-Born Wiring for Neural Trees

Meta-Aggregator: Learning To Aggregate for 1-Bit Graph Neural Networks

Stochastic Partial Swap: Enhanced Model Generalization and Interpretability for Fine-Grained Recognition

Few-Shot Dataset Distillation via Translative Pre-Training

PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection

Priority-Centric Human Motion Generation in Discrete Latent Space

Diffusion Model as Representation Learner

SG-Former: Self-guided Transformer with Evolving Token Reallocation

TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration

Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction

Hallucinating Visual Instances in Total Absentia

Collaboration by Competition: Self-coordinated Knowledge Amalgamation for Multi-talent Student Learning

Learning Propagation Rules for Attribution Map Generation

Learning Graph Neural Networks for Image Style Transfer

Learning with Recoverable Forgetting

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection

Factorizing Knowledge in Neural Networks

Attention Diversification for Domain Generalization

Relationship Spatialization for Depth Estimation

Mutual-Modality Adversarial Attack with Semantic Perturbation

MambaOut: Do We Really Need Mamba for Vision?

CoSER: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation

Few-shot Implicit Function Generation via Equivariance

Event-based Video Super-Resolution via State Space Models

TinyFusion: Diffusion Transformers Learned Shallow

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Diffusion Model is Effectively Its Own Teacher

Towards Performance Consistency in Multi-Level Model Collaboration

C4D: 4D Made from 3D through Dual Correspondences

OminiControl: Minimal and Universal Control for Diffusion Transformer

UniversalBooth: Model-Agnostic Personalized Text-to-Image Generation

Auto-Controlled Image Perception in MLLMs via Visual Perception Tokens

IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation

RogSplat: Robust Gaussian Splatting via Generative Priors

GFlow: Recovering 4D World from Monocular Video

ERF: A Benchmark Dataset for Robust Semantic Segmentation Under Extreme Rainfall Conditions

Ungeneralizable Examples

Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images

MindBridge: A Cross-Subject Brain Decoding Framework

Dual Swap Disentangling

Deep Model Transferability from Attribution Maps

Factorizable Graph Convolutional Networks

One-sample Guided Object Representation Disassembling

Mosaicking to Distill: Knowledge Distillation from Out-of-Domain Data

Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning

Dataset Distillation via Factorization

Training Spiking Neural Networks with Local Tandem Learning

Inception Transformer

NeurIPS 2022arXiv

Deep Model Reassembly

Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

Structural Pruning for Diffusion Models

LLM-Pruner: On the Structural Pruning of Large Language Models

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

Generator Born from Classifier

MGDD: A Meta Generator for Fast Dataset Distillation