Anil Kag

Snap (United States) — United States

Computer Science · Physical Sciences

5h-index333citations29works0.42yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Neural Networks and Applications(6), Machine Learning and Algorithms(5), Model Reduction and Neural Networks(4), Machine Learning in Healthcare(4), Machine Learning and Data Classification(3)

Publications29 total

Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization
arXiv (Cornell University)·2025Open Access
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
2025
H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models
arXiv (Cornell University)·2025Open Access
Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach
arXiv (Cornell University)·2025Open Access
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
arXiv (Cornell University)·2024Open Access
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
arXiv (Cornell University)·2024Open Access
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
arXiv (Cornell University)·2024Open Access
Scalable Ranked Preference Optimization for Text-to-Image Generation
arXiv (Cornell University)·2024Open Access
TextCraftor: Your Text Encoder can be Image Quality Controller
2024· 4 cited
SF-V: Single Forward Video Generation Model
arXiv (Cornell University)·2024· 1 citedOpen Access
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
arXiv (Cornell University)·2024· 1 citedOpen Access
TextCraftor: Your Text Encoder Can be Image Quality Controller
arXiv (Cornell University)·2024Open Access
SF-V: Single Forward Video Generation Model
2024
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
2024
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
2024
Condensing CNNs with Partial Differential Equations
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 3 cited
Online Selective Classification with Limited Feedback
arXiv (Cornell University)·2021· 1 citedOpen Access
Training Recurrent Neural Networks via Forward Propagation Through Time
2021· 14 cited
Time Adaptive Recurrent Neural Network
2021· 18 cited
Selective Classification via One-Sided Prediction
arXiv (Cornell University)·2020· 1 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Venkatesh Saligrama(10), Sergey Tulyakov(8), Sergey Tulyakov(7), Yanyu Li(6), Hu Ju(6), Willi Menapace(6), Aliaksandr Siarohin(6), Ziming Zhang(5), Yerlan Idelbayev(5), Jun‐Li Cao(5), Dhritiman Sagar(4), Yanzhi Wang(4), Zhixing Zhang(4), Yanyu Li(4), Yushu Wu(4), Yanwu Xu(4), Ivan Skorokhodov(4), Jian Ren(3), Junli Cao(3), Dimitris Metaxas(3)