Jiuxiang Gu

26

Papers

171

Total Citations

Papers (26)

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

ImageFolder: Autoregressive Image Generation with Folded Tokens

Numerical Pruning for Efficient Autoregressive Models

Customization Assistant for Text-to-Image Generation

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

Refer to Any Segmentation Mask Group With Vision-Language Prompts

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

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models

LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers

TRINS: Towards Multimodal Language Models that Can Read

Category-Aware Active Domain Adaptation

Exploiting Semantic Embedding and Visual Feature for Facial Action Unit Detection

Multi-Scale Aligned Distillation for Low-Resolution Detection

SelfDoc: Self-Supervised Document Representation Learning

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

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

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

High Quality Entity Segmentation

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

Improving the Reliability for Confidence Estimation

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

Self-Supervised Relationship Probing

UniDoc: Unified Pretraining Framework for Document Understanding

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

NeurIPS 2022arXiv

AIMS: All-Inclusive Multi-Level Segmentation for Anything