Jun Huang

papers

431

total citations

papers (11)

Scale-Aware Modulation Meet Transformer

ICCV 2023arXiv

136

citations

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

CVPR 2024arXiv

128

citations

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

CVPR 2025arXiv

citations

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

ICLR 2025arXiv

citations

Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis

CVPR 2025arXiv

citations

Fingerprinting Deep Image Restoration Models

ICCV 2023

citations

M2SD:Multiple Mixing Self-Distillation for Few-Shot Class-Incremental Learning

AAAI 2024

citations

Fingerprinting Denoising Diffusion Probabilistic Models

CVPR 2025

citations

Jun Huang

papers (11)

Scale-Aware Modulation Meet Transformer

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

SwapText: Image Based Texts Transfer in Scenes

Detection Transformer with Stable Matching

M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis

Fingerprinting Deep Image Restoration Models

M2SD:Multiple Mixing Self-Distillation for Few-Shot Class-Incremental Learning

Fingerprinting Denoising Diffusion Probabilistic Models

papers (11)

Scale-Aware Modulation Meet Transformer

Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing

SwapText: Image Based Texts Transfer in Scenes

Detection Transformer with Stable Matching

M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis

DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective

Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis

Fingerprinting Deep Image Restoration Models

M2SD:Multiple Mixing Self-Distillation for Few-Shot Class-Incremental Learning

Fingerprinting Denoising Diffusion Probabilistic Models