Haonan Wang

papers

656

total citations

papers (20)

A Neural Corpus Indexer for Document Retrieval

NEURIPS 2022arXiv

185

citations

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

CVPR 2023arXiv

138

citations

Efficient Dataset Distillation via Minimax Diffusion

CVPR 2024arXiv

citations

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation

NEURIPS 2023arXiv

citations

Subclass-balancing Contrastive Learning for Long-tailed Recognition

ICCV 2023arXiv

citations

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

CVPR 2024arXiv

citations

Deep Active Learning by Leveraging Training Dynamics

NEURIPS 2022arXiv

citations

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

ICLR 2025arXiv

citations

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

ICCV 2025arXiv

citations

Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow

CVPR 2025arXiv

citations

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

NEURIPS 2025arXiv

citations

STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene

ICCV 2025arXiv

citations

TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking

ICCV 2025arXiv

citations

The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline

ICML 2024

citations

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

NEURIPS 2021arXiv

citations

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

NEURIPS 2025arXiv

citations

Haonan Wang

papers (20)

A Neural Corpus Indexer for Document Retrieval

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

Efficient Dataset Distillation via Minimax Diffusion

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation

Subclass-balancing Contrastive Learning for Long-tailed Recognition

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

Deep Active Learning by Leveraging Training Dynamics

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Understanding Programmatic Weak Supervision via Source-aware Influence Function

Token Activation Map to Visually Explain Multimodal LLMs

Model-enhanced Vector Index

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene

TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking

The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

papers (20)

A Neural Corpus Indexer for Document Retrieval

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

Efficient Dataset Distillation via Minimax Diffusion

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation

Subclass-balancing Contrastive Learning for Long-tailed Recognition

AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

Deep Active Learning by Leveraging Training Dynamics

Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Understanding Programmatic Weak Supervision via Source-aware Influence Function

Token Activation Map to Visually Explain Multimodal LLMs

Model-enhanced Vector Index

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene

TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking

The Stronger the Diffusion Model, the Easier the Backdoor: Data Poisoning to Induce Copyright BreachesWithout Adjusting Finetuning Pipeline

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding