Ishan Misra

Computer Science · Physical Sciences

38h-index15.0kcitations116works10.92yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Domain Adaptation and Few-Shot Learning(56), Multimodal Machine Learning Applications(44), Advanced Image and Video Retrieval Techniques(33), Advanced Neural Network Applications(27), Human Pose and Action Recognition(18)

Publications116 total

Generating Multi-Image Synthetic Data for Text-to-Image Customization
arXiv (Cornell University)·2025Open Access
Diffusion Autoencoders are Scalable Image Tokenizers
arXiv (Cornell University)·2025Open Access
LLMs can see and hear without any training
arXiv (Cornell University)·2025Open Access
CAT: Content-Adaptive Image Tokenization
2025Open Access
CAT: Content-Adaptive Image Tokenization
arXiv (Cornell University)·2025Open Access
Factorizing Text-to-Video Generation by Explicit Image Conditioning
Lecture notes in computer science·2024· 47 cited
Movie Gen: A Cast of Media Foundation Models
arXiv (Cornell University)·2024· 7 citedOpen Access
Dynamics of a magnetic particle in an oscillating magnetic field
Physical Review Fluids·2024· 4 cited
Microfluidic mixing by magnetic particles: Progress and prospects
Biomicrofluidics·2024· 5 citedOpen Access
InstanceDiffusion: Instance-Level Control for Image Generation
2024· 60 cited
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
2024· 23 cited
VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
2024· 13 cited
Generating Illustrated Instructions
2024· 1 cited
Dynamics of a magnetic particle in an oscillating magnetic field subject to a shear flow
Journal of Fluid Mechanics·2024· 3 citedOpen Access
InstanceDiffusion: Instance-level Control for Image Generation
arXiv (Cornell University)·2024Open Access
FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis
arXiv (Cornell University)·2023· 2 citedOpen Access
Generating Illustrated Instructions
arXiv (Cornell University)·2023Open Access
On Bringing Robots Home
arXiv (Cornell University)·2023· 3 citedOpen Access
Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning
arXiv (Cornell University)·2023· 16 citedOpen Access
SelfEval: Leveraging the discriminative nature of generative models for evaluation
arXiv (Cornell University)·2023Open Access
page 1 of 6Next →

Frequent Co-authors

Armand Joulin(13), Rohit Girdhar(13), Piotr Bojanowski(9), Martial Hebert(9), Mathilde Caron(7), Mannat Singh(7), C. Lawrence Zitnick(6), Laurens van der Maaten(5), Julien Mairal(4), Priya Goyal(4), Mahmoud Assran(4), Nicolas Ballas(4), Quentin Duval(4), Ross Girshick(4), Margaret Mitchell(4), Abhinav Shrivastava(4), Alaaeldin El-Nouby(3), Michael Rabbat(3), Yann LeCun(3), Kalyan Vasudev Alwala(3)