Yu Li

47

Papers

332

Total Citations

Papers (47)

DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation

AgentSquare: Automatic LLM Agent Search in Modular Design Space

Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

Atlantis: Enabling Underwater Depth Estimation with Stable Diffusion

Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations

A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing

Protein Multimer Structure Prediction via Prompt Learning

HRAvatar: High-Quality and Relightable Gaussian Head Avatar

Blind Face Restoration under Extreme Conditions: Leveraging 3D-2D Prior Fusion for Superior Structural and Texture Recovery

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding

DF-MIA: A Distribution-Free Membership Inference Attack on Fine-Tuned Large Language Models

CanonSwap: High-Fidelity and Consistent Video Face Swapping via Canonical Space Modulation

AnyTalk: Multi-modal Driven Multi-domain Talking Head Generation

Adaptive Articulated Object Manipulation On The Fly with Foundation Model Reasoning and Part Grounding

MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment

Nighttime Haze Removal With Glow and Multiple Light Colors

SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs

Instances As Queries

Crossover Learning for Fast Online Video Instance Segmentation

Towards Vivid and Diverse Image Colorization With Generative Color Prior

Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding

Learning Rain Location Prior for Nighttime Deraining

From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels

Accurate 3D Face Reconstruction with Facial Component Tokens

Fast Video Object Segmentation using the Global Context Module

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

CT2: Colorization Transformer via Color Tokens

L-CoDer: Language-Based Colorization with Color-Object Decoupling Transformer

MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions

ProReflow: Progressive Reflow with Decomposed Velocity

GUAVA: Generalizable Upper Body 3D Gaussian Avatar

TAMER: Tree-Aware Transformer for Handwritten Mathematical Expression Recognition

Identification of Causal Structure in the Presence of Missing Data with Additive Noise Model

Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models

Rain Streak Removal Using Layer Priors

Unsupervised Learning for Intrinsic Image Decomposition From a Single Image

Overcoming Classifier Imbalance for Long-Tail Object Detection With Balanced Group Softmax

Towards Real-World Blind Face Restoration With Generative Facial Prior

Learning Temporal Consistency for Low Light Video Enhancement From Single Images

Active Learning for Open-Set Annotation

Temporally Efficient Vision Transformer for Video Instance Segmentation

One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer

L-CoIns: Language-Based Colorization With Instance Awareness

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

L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors