Medhini Narasimhan

Medhini Narasimhan

Staff Research Scientist · Google DeepMind

Hi! I'm a Staff Research Scientist at Google DeepMind. I currently lead Evals for Veo, our video generation model. In the past, I've worked on Veo's scaling laws, data mixture recipes, image-to-video and other control capabilities, and also post-training. My research interests are in building multimodal models for understanding and generation.

I graduated with a PhD in Computer Science from UC Berkeley in 2023, where I was advised by Prof. Trevor Darrell and was a member of BAIR. Prior to Berkeley, I completed my Master's at UIUC advised by Prof. A. Schwing and Prof. S. Lazebnik, and obtained my Bachelor's from NITK, India.

I am honored to be a Snap Research Scholar (2019) and a Siebel Scholar (2018).

CV

Research

arXiv 2023
Learning and Verification of Task Structure from Instructional Videos
Medhini Narasimhan, Licheng Yu, Sean Bell, Ning Zhang, Trevor Darrell
Paper · Website · Code
ECCV 2022
TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency
Medhini Narasimhan, Arsha Nagrani, Chen Sun, Miki Rubinstein, Trevor Darrell, Anna Rohrbach, Cordelia Schmid
Paper · Website · Code
NeurIPS 2021
CLIP-It! Language-Guided Video Summarization
Medhini Narasimhan, Anna Rohrbach, Trevor Darrell
Paper · Website · Code
WACV 2022
Strumming to the Beat: Audio-Conditioned Contrastive Video Textures
★ Best Paper, Honorable Mention
Medhini Narasimhan, Shiry Ginosar, Andrew Owens, Alyosha Efros, Trevor Darrell
Paper · Website · Code · Video
ECCV 2020
Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigation
Medhini Narasimhan, Erik Wijmans, Xinlei Chen, Trevor Darrell, Dhruv Batra, Devi Parikh, Amanpreet Singh
Paper
NeurIPS 2018
Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering
Medhini Narasimhan, Svetlana Lazebnik, Alexander Schwing
Paper · Poster · Video
ECCV 2018
Straight to the Facts: Learning Knowledge Base Retrieval for Factual Visual Question Answering
Medhini Narasimhan, Alexander Schwing
Paper · Poster
MTAP 2017
Dynamic Video Anomaly Detection and Localization Using Sparse Denoising Autoencoders
Medhini Narasimhan, Sowmya Kamath
Paper · Code
IJBIC 2018
EGA-FMC: Enhanced Genetic Algorithm Based Fuzzy K-Modes Clustering for Categorical Data
Medhini Narasimhan, Balaji Balasubramanian, Suryansh Kumar, Nagamma Patil
Paper · Code
ISMB 2016
Predicting Symptom Severity and Contagiousness of Respiratory Viral Infections
★ Best Poster Award
Medhini Narasimhan, Guiseppe Vietri, Arpit Mehta, Farid Rajabli, Vanessa Aguiar-Pulido, Kalai Mathee, Giri Narasimhan
Poster