Jiuxiang Gu

papers

1,876

total citations

papers (28)

Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning

ECCV 2020arXiv

citations

Multi-Scale Aligned Distillation for Low-Resolution Detection

CVPR 2021arXiv

citations

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

AAAI 2025arXiv

citations

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

ECCV 2022arXiv

citations

Numerical Pruning for Efficient Autoregressive Models

AAAI 2025arXiv

citations

Customization Assistant for Text-to-Image Generation

CVPR 2024arXiv

citations

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

ECCV 2022arXiv

citations

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

CVPR 2025arXiv

citations

Improving the Reliability for Confidence Estimation

ECCV 2022arXiv

citations

TRINS: Towards Multimodal Language Models that Can Read

CVPR 2024arXiv

citations

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation

ICCV 2025arXiv

citations

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

CVPR 2025arXiv

citations

SOHES: Self-supervised Open-world Hierarchical Entity Segmentation

ICLR 2024arXiv

citations

Refer to Any Segmentation Mask Group With Vision-Language Prompts

ICCV 2025arXiv

citations

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

ICCV 2025

citations

UniDoc: Unified Pretraining Framework for Document Understanding

NEURIPS 2021

citations

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval

CVPR 2022

citations

Category-Aware Active Domain Adaptation

ICML 2024

citations

AIMS: All-Inclusive Multi-Level Segmentation for Anything

NEURIPS 2023

citations

Self-Supervised Relationship Probing

NEURIPS 2020

citations

Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection

CVPR 2021

citations

Jiuxiang Gu

papers (28)

LRM: Large Reconstruction Model for Single Image to 3D

Delving into Out-of-Distribution Detection with Vision-Language Representations

Towards Language-Free Training for Text-to-Image Generation

SelfDoc: Self-Supervised Document Representation Learning

Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling

High Quality Entity Segmentation

ImageFolder: Autoregressive Image Generation with Folded Tokens

Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning

Multi-Scale Aligned Distillation for Low-Resolution Detection

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Numerical Pruning for Efficient Autoregressive Models

Customization Assistant for Text-to-Image Generation

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Improving the Reliability for Confidence Estimation

TRINS: Towards Multimodal Language Models that Can Read

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

SOHES: Self-supervised Open-world Hierarchical Entity Segmentation

Refer to Any Segmentation Mask Group With Vision-Language Prompts

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

UniDoc: Unified Pretraining Framework for Document Understanding

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval

Category-Aware Active Domain Adaptation

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Self-Supervised Relationship Probing

Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection

papers (28)

LRM: Large Reconstruction Model for Single Image to 3D

Delving into Out-of-Distribution Detection with Vision-Language Representations

Towards Language-Free Training for Text-to-Image Generation

SelfDoc: Self-Supervised Document Representation Learning

Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling

High Quality Entity Segmentation

ImageFolder: Autoregressive Image Generation with Folded Tokens

Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning

Multi-Scale Aligned Distillation for Low-Resolution Detection

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Numerical Pruning for Efficient Autoregressive Models

Customization Assistant for Text-to-Image Generation

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

Improving the Reliability for Confidence Estimation

TRINS: Towards Multimodal Language Models that Can Read

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation

QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge

SOHES: Self-supervised Open-world Hierarchical Entity Segmentation

Refer to Any Segmentation Mask Group With Vision-Language Prompts

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

UniDoc: Unified Pretraining Framework for Document Understanding

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval

Category-Aware Active Domain Adaptation

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Self-Supervised Relationship Probing

Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection