Ge Li

papers

1,105

total citations

papers (28)

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

ICCV 2021arXiv

269

citations

Deep Image Spatial Transformation for Person Image Generation

CVPR 2020arXiv

195

citations

ST-LLM: Large Language Models Are Effective Temporal Learners

ECCV 2024arXiv

129

citations

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

CVPR 2022arXiv

citations

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring

CVPR 2023arXiv

citations

SKFlow: Learning Optical Flow with Super Kernels

NEURIPS 2022arXiv

citations

Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

AAAI 2024arXiv

citations

Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation

CVPR 2022arXiv

citations

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

CVPR 2024arXiv

citations

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

NEURIPS 2022arXiv

citations

Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection

CVPR 2024arXiv

citations

Salient Object Detection for Point Clouds

ECCV 2022arXiv

citations

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

ICLR 2024arXiv

citations

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

NEURIPS 2023

citations

Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection

AAAI 2025arXiv

citations

Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations

AAAI 2025arXiv

citations

Integrating Tree Path in Transformer for Code Representation

NEURIPS 2021

citations

Learning to Share in Networked Multi-Agent Reinforcement Learning

NEURIPS 2022

citations

Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

CVPR 2023

citations

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

ICML 2025

citations

Structure-Transformed Texture-Enhanced Network for Person Image Synthesis

ICCV 2021

citations

Contextual Debiasing for Visual Recognition With Causal Mechanisms

CVPR 2022

citations

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

CVPR 2023

citations

AdaNIC: Towards Practical Neural Image Compression via Dynamic Transform Routing

ICCV 2023

citations

DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads

ICCV 2025

citations

Ge Li

papers (28)

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

Deep Image Spatial Transformation for Person Image Generation

ST-LLM: Large Language Models Are Effective Temporal Learners

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring

SKFlow: Learning Optical Flow with Super Kernels

Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection

Salient Object Detection for Point Clouds

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval

Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow

ContextHOI: Spatial Context Learning for Human-Object Interaction Detection

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection

Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations

Integrating Tree Path in Transformer for Code Representation

Learning to Share in Networked Multi-Agent Reinforcement Learning

Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

Structure-Transformed Texture-Enhanced Network for Person Image Synthesis

Contextual Debiasing for Visual Recognition With Causal Mechanisms

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

AdaNIC: Towards Practical Neural Image Compression via Dynamic Transform Routing

DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads

papers (28)

PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering

Deep Image Spatial Transformation for Person Image Generation

ST-LLM: Large Language Models Are Effective Temporal Learners

Neural Texture Extraction and Distribution for Controllable Person Image Synthesis

Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring

SKFlow: Learning Optical Flow with Super Kernels

Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models

Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation

BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning

Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively

Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection

Salient Object Detection for Point Clouds

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

MUSE: Mamba Is Efficient Multi-scale Learner for Text-video Retrieval

Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow

ContextHOI: Spatial Context Learning for Human-Object Interaction Detection

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

Orchestrating the Symphony of Prompt Distribution Learning for Human-Object Interaction Detection

Point Cloud Semantic Segmentation with Sparse and Inhomogeneous Annotations

Integrating Tree Path in Transformer for Code Representation

Learning to Share in Networked Multi-Agent Reinforcement Learning

Efficient Hierarchical Entropy Model for Learned Point Cloud Compression

Dataflow-Guided Neuro-Symbolic Language Models for Type Inference

Structure-Transformed Texture-Enhanced Network for Person Image Synthesis

Contextual Debiasing for Visual Recognition With Causal Mechanisms

Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering

AdaNIC: Towards Practical Neural Image Compression via Dynamic Transform Routing

DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads