Liang-Chieh Chen

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens

arXiv 2026

Autoregressive Image Generation with Masked Bit Modeling

arXiv 2026

FlowTok: Flowing Seamlessly Across Text and Image Tokens

ICCV 2025

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation

arXiv 2025

Deeply Supervised Flow-Based Generative Models

ICCV 2025

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching

arXiv 2024

ViTamin: Designing Scalable Vision Models in the Vision-Language Era

CVPR 2024 1

MaskBit: Embedding-free Image Generation via Bit Tokens

arXiv 2024

Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization

arXiv 2024

PolyMaX: General Dense Prediction with Mask Transformer

arXiv 2023

Towards Open-Ended Visual Recognition with Large Language Model

arXiv 2023

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories

arXiv 2023

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

convolutions-die-hard-open-vocabulary

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

detectors-detecting-objects-with-recursive

Qihang Yu

Ju He

Xiaohui Shen

Alan Yuille

Qihao Liu

Xueqing Deng

Inkyu Shin

Siyuan Qiao

Sucheng Ren

Astuti Sharma