Yong Liu

103

Papers

580

Total Citations

Papers (103)

ToolACE: Winning the Points of LLM Function Calling

Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

Sundial: A Family of Highly Capable Time Series Foundation Models

REEF: Representation Encoding Fingerprints for Large Language Models

Universal Segmentation at Arbitrary Granularity with Language Instruction

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models

Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection

Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective

Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning

InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models

Flash-VStream: Efficient Real-Time Understanding for Long Video Streams

OLinear: A Linear Model for Time Series Forecasting in Orthogonally Transformed Domain

A Multimodal, Multi-Task Adapting Framework for Video Action Recognition

Understanding Fairness Surrogate Functions in Algorithmic Fairness

TIMotion: Temporal and Interactive Framework for Efficient Human-Human Motion Generation

LORS: Low-rank Residual Structure for Parameter-Efficient Network Stacking

SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes

CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation

Decentralized Federated Learning with Model Caching on Mobile Agents

OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks

Understanding Model Ensemble in Transferable Adversarial Attack

HyperSeg: Hybrid Segmentation Assistant with Fine-grained Visual Perceiver

Action Detail Matters: Refining Video Recognition with Local Action Queries

High-Dimensional Analysis for Generalized Nonlinear Regression: From Asymptotics to Algorithm

Stepping Out of Similar Semantic Space for Open-Vocabulary Segmentation

PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution

Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology

GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language Model

Adaptive Assignment for Geometry Aware Local Feature Matching

RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer

Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space

Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution

Learning Federated Visual Prompt in Null Space for MRI Reconstruction

HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search

Face-to-Parameter Translation for Game Character Auto-Creation

RFNet: Recurrent Forward Network for Dense Point Cloud Completion

Self-Supervised Monocular Depth Estimation for All Day Images Using Domain Separation

Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning

Global Knowledge Calibration for Fast Open-Vocabulary Segmentation

RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction

Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning

Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching

Synchronize Feature Extracting and Matching: A Single Branch Framework for 3D Object Tracking

Learning Global-aware Kernel for Image Harmonization

Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning

DTVNet: Dynamic Time-lapse Video Generation via Single Still Image

Dive Deeper Into Box for Object Detection

Learning to Train a Point Cloud Reconstruction Network without Matching

Resolution-Free Point Cloud Sampling Network with Data Distillation

SuperLine3D: Self-Supervised Line Segmentation and Description for LiDAR Point Cloud

Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping

Learning Quality-Aware Dynamic Memory for Video Object Segmentation

Global Spectral Filter Memory Network for Video Object Segmentation

E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context

High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning

LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation

VQA4CIR: Boosting Composed Image Retrieval with Visual Question Answering

IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis

Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving

Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning

AdaO2B: Adaptive Online to Batch Conversion for Out-of-Distribution Generalization

Unsupervised Continual Anomaly Detection with Contrastively-Learned Prompt

ASWT-SGNN: Adaptive Spectral Wavelet Transform-Based Self-Supervised Graph Neural Network

WaveNet: Tackling Non-stationary Graph Signals via Graph Spectral Wavelets

Learning Multi-Scale Video-Text Correspondence for Weakly Supervised Temporal Article Gronding

Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection

MaxQ: Multi-Axis Query for N:M Sparsity Network

Open-Vocabulary Segmentation with Semantic-Assisted Calibration

An Aggregation-Free Federated Learning for Tackling Data Heterogeneity

SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking

Concentration Inequalities for General Functions of Heavy-Tailed Random Variables

Algorithmic Stability Unleashed: Generalization Bounds with Unbounded Losses

Perfect Alignment May be Poisonous to Graph Contrastive Learning

Timer: Generative Pre-trained Transformers Are Large Time Series Models

Large Margin Object Tracking With Circulant Feature Maps

Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships

FReeNet: Multi-Identity Face Reenactment

Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation

Towards Efficient and Scalable Sharpness-Aware Minimization

Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase

Region-Aware Face Swapping

Class-Aware Contrastive Semi-Supervised Learning

CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow

Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training

Multi-Class Learning: From Theory to Algorithm

Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test

Refined Learning Bounds for Kernel and Approximate $k$-Means

Improved Learning Rates of a Functional Lasso-type SVM with Sparse Multi-Kernel Representation

Searching Parameterized AP Loss for Object Detection

Analogous to Evolutionary Algorithm: Designing a Unified Sequence Model

Towards Sharper Generalization Bounds for Structured Prediction

Randomized Sketches for Clustering: Fast and Optimal Kernel $k$-Means

Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting

SoftPatch: Unsupervised Anomaly Detection with Noisy Data

Fine-Grained Analysis of Stability and Generalization for Modern Meta Learning Algorithms

Random Sharpness-Aware Minimization

Stability and Generalization of Kernel Clustering: from Single Kernel to Multiple Kernel

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

Real3D-AD: A Dataset of Point Cloud Anomaly Detection

SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration