Chenguang Zhu

papers

1,311

total citations

papers (11)

An Empirical Study of Training End-to-End Vision-and-Language Transformers

CVPR 2022arXiv

439

citations

Any-to-Any Generation via Composable Diffusion

NEURIPS 2023arXiv

249

citations

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

NEURIPS 2022arXiv

164

citations

Unifying Vision, Text, and Layout for Universal Document Processing

CVPR 2023arXiv

157

citations

CLIP-Event: Connecting Text and Images With Event Structures

CVPR 2022arXiv

145

citations

REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering

NEURIPS 2022arXiv

101

citations

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

CVPR 2025arXiv

citations

CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation

CVPR 2024

citations

Chenguang Zhu

papers (11)

An Empirical Study of Training End-to-End Vision-and-Language Transformers

Any-to-Any Generation via Composable Diffusion

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

Unifying Vision, Text, and Layout for Universal Document Processing

CLIP-Event: Connecting Text and Images With Event Structures

REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering

Sparse Modular Activation for Efficient Sequence Modeling

Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles

Law of the Weakest Link: Cross Capabilities of Large Language Models

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation

papers (11)

An Empirical Study of Training End-to-End Vision-and-Language Transformers

Any-to-Any Generation via Composable Diffusion

Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

Unifying Vision, Text, and Layout for Universal Document Processing

CLIP-Event: Connecting Text and Images With Event Structures

REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering

Sparse Modular Activation for Efficient Sequence Modeling

Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles

Law of the Weakest Link: Cross Capabilities of Large Language Models

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation

CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation