Huaping Liu

OpenReview

papers

2,166

total citations

papers (16)

EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models

CVPR 2024arXiv

citations

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

NEURIPS 2023arXiv

citations

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

CVPR 2024arXiv

citations

Multi-Agent Embodied Question Answering in Interactive Environments

ECCV 2020

citations

Small Scale Data-Free Knowledge Distillation

CVPR 2024arXiv

citations

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

CVPR 2025arXiv

citations

Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach

AAAI 2025arXiv

citations

Rethinking Causal Relationships Learning in Graph Neural Networks

AAAI 2024arXiv

citations

MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation

CVPR 2025arXiv

citations

Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks

ICML 2025arXiv

citations

Unsupervised Representation Learning by Invariance Propagation

NEURIPS 2020

citations

Huaping Liu

papers (16)

Understanding the Behaviour of Contrastive Loss

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

Text-to-3D using Gaussian Splatting

Vision-Language Foundation Models as Effective Robot Imitators

Mixed Neural Voxels for Fast Multi-view Video Synthesis

EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

Multi-Agent Embodied Question Answering in Interactive Environments

Small Scale Data-Free Knowledge Distillation

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach

Rethinking Causal Relationships Learning in Graph Neural Networks

MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation

Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks

Unsupervised Representation Learning by Invariance Propagation

papers (16)

Understanding the Behaviour of Contrastive Loss

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

Text-to-3D using Gaussian Splatting

Vision-Language Foundation Models as Effective Robot Imitators

Mixed Neural Voxels for Fast Multi-view Video Synthesis

EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

Efficient Multi-scale Network with Learnable Discrete Wavelet Transform for Blind Motion Deblurring

Multi-Agent Embodied Question Answering in Interactive Environments

Small Scale Data-Free Knowledge Distillation

MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception

Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach

Rethinking Causal Relationships Learning in Graph Neural Networks

MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation

Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks

Unsupervised Representation Learning by Invariance Propagation