Liang-Chieh Chen

Computer Science · Physical Sciences

39h-index86.5kcitations100works3.92yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(61), Advanced Image and Video Retrieval Techniques(45), Domain Adaptation and Few-Shot Learning(31), Multimodal Machine Learning Applications(21), Video Surveillance and Tracking Methods(20)

Publications100 total

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
arXiv (Cornell University)·2025Open Access
FlowTok: Flowing Seamlessly Across Text and Image Tokens
arXiv (Cornell University)·2025Open Access
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
arXiv (Cornell University)·2025Open Access
1.58-bit FLUX
arXiv (Cornell University)·2024Open Access
FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
arXiv (Cornell University)·2024Open Access
Towards Open-Ended Visual Recognition with Large Language Models
Lecture notes in computer science·2024· 3 cited
Randomized Autoregressive Visual Generation
arXiv (Cornell University)·2024· 1 citedOpen Access
MaskBit: Embedding-free Image Generation via Bit Tokens
arXiv (Cornell University)·2024Open Access
COCONut: Modernizing COCO Segmentation
2024· 9 cited
ViTamin: Designing Scalable Vision Models in the Vision-Language Era
2024· 21 cited
An Image is Worth 32 Tokens for Reconstruction and Generation
arXiv (Cornell University)·2024· 4 citedOpen Access
Enhancing Temporal Consistency in Video Editing by Reconstructing Videos with 3D Gaussian Splatting
arXiv (Cornell University)·2024Open Access
COCONut: Modernizing COCO Segmentation
arXiv (Cornell University)·2024Open Access
ViTamin: Designing Scalable Vision Models in the Vision-Language Era
arXiv (Cornell University)·2024· 1 citedOpen Access
SPFormer: Enhancing Vision Transformer with Superpixel Representation
arXiv (Cornell University)·2024· 6 citedOpen Access
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation
2024· 6 cited
PolyMaX: General Dense Prediction with Mask Transformer
2024· 16 cited
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation
2024· 11 cited
DeepLab
TIB Data Manager·2024Open Access
An Image is Worth 32 Tokens for Reconstruction and Generation
2024
page 1 of 5Next →

Frequent Co-authors

Hartwig Adam(24), Alan Yuille(23), Yukun Zhu(17), George Papandreou(15), Florian Schroff(12), Maxwell D. Collins(10), Huiyu Wang(9), Siyuan Qiao(8), Kevin Murphy(7), Qihang Yu(5), Mark Sandler(4), Andrew Howard(4), Bowen Cheng(4), Menglong Zhu(3), Andrey Zhmoginov(3), Jiang Wang(3), Wei Xu(3), Ting Liu(3), Thomas S. Huang(3), Barret Zoph(3)