Rohit Girdhar

Computer Science · Physical Sciences

26h-index5.2kcitations84works7.92yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Human Pose and Action Recognition(31), Multimodal Machine Learning Applications(30), Advanced Neural Network Applications(19), Domain Adaptation and Few-Shot Learning(13), Video Analysis and Summarization(12)

Publications83 total

Human detectors are surprisingly powerful reward models
ArXiv.org·2026Open Access
Human detectors are surprisingly powerful reward models
arXiv (Cornell University)·2026Open Access
Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective
arXiv (Cornell University)·2025Open Access
MotiF: Making Text Count in Image Animation with Motion Focal Loss
2025
Diffusion Autoencoders are Scalable Image Tokenizers
arXiv (Cornell University)·2025Open Access
LLMs can see and hear without any training
arXiv (Cornell University)·2025Open Access
MotiF: Making Text Count in Image Animation with Motion Focal Loss
arXiv (Cornell University)·2024Open Access
Factorizing Text-to-Video Generation by Explicit Image Conditioning
Lecture notes in computer science·2024· 47 cited
Human Action Anticipation: A Survey
arXiv (Cornell University)·2024Open Access
Movie Gen: A Cast of Media Foundation Models
arXiv (Cornell University)·2024· 7 citedOpen Access
Ego4D: Around the World in 3,600 Hours of Egocentric Video
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 7 citedOpen Access
InstanceDiffusion: Instance-Level Control for Image Generation
2024· 60 cited
SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
2024· 7 cited
VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
2024· 13 cited
Generating Illustrated Instructions
2024· 1 cited
SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos
arXiv (Cornell University)·2024Open Access
InstanceDiffusion: Instance-level Control for Image Generation
arXiv (Cornell University)·2024Open Access
Generating Illustrated Instructions
arXiv (Cornell University)·2023Open Access
Motion-Conditioned Image Animation for Video Editing
arXiv (Cornell University)·2023Open Access
Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning
arXiv (Cornell University)·2023· 16 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Ishan Misra(22), Armand Joulin(10), Deva Ramanan(10), Mannat Singh(9), Lorenzo Torresani(8), Kristen Grauman(6), Quentin Duval(6), Kalyan Vasudev Alwala(5), Christoph Feichtenhofer(5), Abhinav Gupta(4), Xudong Wang(4), Alexander G. Schwing(4), Sai Saketh Rambhatla(4), João Carreira(3), Carl Doersch(3), Andrew Zisserman(3), Alaaeldin El-Nouby(3), Andrew Westbury(3), Eugene H. Byrne(3), Zachary Chavis(3)