Xinlei Chen

papers

20,445

total citations

papers (19)

KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

CVPR 2021arXiv

231

citations

Test-Time Training with Masked Autoencoders

NEURIPS 2022arXiv

228

citations

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

ICCV 2025arXiv

150

citations

Transformers without Normalization

CVPR 2025arXiv

103

citations

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

ICCV 2023arXiv

citations

Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

ECCV 2020arXiv

citations

On the Importance of Asymmetry for Siamese Representation Learning

CVPR 2022arXiv

citations

Point-Level Region Contrast for Object Detection Pre-Training

CVPR 2022arXiv

citations

Scaling Language-Free Visual Representation Learning

ICCV 2025arXiv

citations

Improving Selective Visual Question Answering by Learning From Your Peers

CVPR 2023arXiv

citations

R-MAE: Regions Meet Masked Autoencoders

ICLR 2024arXiv

citations

PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining

ICCV 2025arXiv

citations

LLMs can see and hear without any training

ICML 2025arXiv

citations

Xinlei Chen

papers (19)

Masked Autoencoders Are Scalable Vision Learners

Exploring Simple Siamese Representation Learning

An Empirical Study of Training Self-Supervised Vision Transformers

ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders

In Defense of Grid Features for Visual Question Answering

ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes

KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

Test-Time Training with Masked Autoencoders

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Transformers without Normalization

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

On the Importance of Asymmetry for Siamese Representation Learning

Point-Level Region Contrast for Object Detection Pre-Training

Scaling Language-Free Visual Representation Learning

Improving Selective Visual Question Answering by Learning From Your Peers

R-MAE: Regions Meet Masked Autoencoders

PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining

LLMs can see and hear without any training

papers (19)

Masked Autoencoders Are Scalable Vision Learners

Exploring Simple Siamese Representation Learning

An Empirical Study of Training Self-Supervised Vision Transformers

ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders

In Defense of Grid Features for Visual Question Answering

ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes

KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

Test-Time Training with Masked Autoencoders

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Transformers without Normalization

UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding

Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation

On the Importance of Asymmetry for Siamese Representation Learning

Point-Level Region Contrast for Object Detection Pre-Training

Scaling Language-Free Visual Representation Learning

Improving Selective Visual Question Answering by Learning From Your Peers

R-MAE: Regions Meet Masked Autoencoders

PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining

LLMs can see and hear without any training