Fuchun Sun

papers

1,270

total citations

papers (24)

Deep Multimodal Fusion by Channel Exchanging

NEURIPS 2020arXiv

285

citations

Multimodal Token Fusion for Vision Transformers

CVPR 2022arXiv

251

citations

Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation

CVPR 2020arXiv

192

citations

Adversarial Texture for Fooling Person Detectors in the Physical World

CVPR 2022arXiv

145

citations

A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning

ECCV 2020arXiv

citations

Bridged Transformer for Vision and Point Cloud 3D Object Detection

CVPR 2022arXiv

citations

AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

ECCV 2024arXiv

citations

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

ICML 2024arXiv

citations

IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation

ICML 2024arXiv

citations

Sub-Bit Neural Networks: Learning To Compress and Accelerate Binary Neural Networks

ICCV 2021arXiv

citations

SNAKE: Shape-aware Neural 3D Keypoint Field

NEURIPS 2022arXiv

citations

Flow-Based Policy for Online Reinforcement Learning

NEURIPS 2025arXiv

citations

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

ICCV 2023arXiv

citations

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

AAAI 2024arXiv

citations

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

ICML 2024arXiv

citations

Compacting Binary Neural Networks by Sparse Kernel Selection

CVPR 2023arXiv

citations

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

ICML 2024arXiv

citations

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

ICML 2024arXiv

citations

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

ICML 2024

citations

Evolutionary Reinforcement Learning with Parameterized Action Primitives for Diverse Manipulation Tasks

AAAI 2025

citations

Fuchun Sun

papers (24)

Deep Multimodal Fusion by Channel Exchanging

Multimodal Token Fusion for Vision Transformers

Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation

Adversarial Texture for Fooling Person Detectors in the Physical World

A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning

Bridged Transformer for Vision and Point Cloud 3D Object Detection

AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

Resolution Switchable Networks for Runtime Efficient Image Recognition

Multi-Agent Embodied Question Answering in Interactive Environments

Small Scale Data-Free Knowledge Distillation

When to Update Your Model: Constrained Model-based Reinforcement Learning

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation

Sub-Bit Neural Networks: Learning To Compress and Accelerate Binary Neural Networks

SNAKE: Shape-aware Neural 3D Keypoint Field

Flow-Based Policy for Online Reinforcement Learning

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Compacting Binary Neural Networks by Sparse Kernel Selection

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Evolutionary Reinforcement Learning with Parameterized Action Primitives for Diverse Manipulation Tasks

papers (24)

Deep Multimodal Fusion by Channel Exchanging

Multimodal Token Fusion for Vision Transformers

Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation

Adversarial Texture for Fooling Person Detectors in the Physical World

A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning

Bridged Transformer for Vision and Point Cloud 3D Object Detection

AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation

Resolution Switchable Networks for Runtime Efficient Image Recognition

Multi-Agent Embodied Question Answering in Interactive Environments

Small Scale Data-Free Knowledge Distillation

When to Update Your Model: Constrained Model-based Reinforcement Learning

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation

Sub-Bit Neural Networks: Learning To Compress and Accelerate Binary Neural Networks

SNAKE: Shape-aware Neural 3D Keypoint Field

Flow-Based Policy for Online Reinforcement Learning

Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Compacting Binary Neural Networks by Sparse Kernel Selection

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Evolutionary Reinforcement Learning with Parameterized Action Primitives for Diverse Manipulation Tasks