Lavisha Aggarwal

Hi! I'm a Senior Applied Scientist at Amazon Research (Prime Video), where I work on multimodal learning, computer vision, and long-form video understanding.

Previously, I was a CV/ML Engineer at Google, working on AI Interfaces within the Augmented Reality organization with Dr. Andrea Colaco. Before Google, I was an Applied Scientist at Amazon One, where I worked with Dr. Manoj Aggarwal and Prof. Gerard Medioni.

I graduated with a Master's in Computer Science from University of Illinois at Urbana-Champaign (UIUC). Prior to UIUC, I completed my Bachelor's in Electrical Engineering from IIT Kanpur, India.

I have also been fortunate to intern with the Amazon Alexa Automatic Speech Recognition team in Summer 2018, at EPFL Switzerland with Prof. Elisa Celis in Summer 2016, and at MIPS Lab, IIT Kanpur with Prof. Rajesh M. Hegde in Summer 2015.

Email | Google Scholar | LinkedIn | Github |

Research

	ESAM++: Efficient Online 3D Perception on the Edge Qin Liu, Lavisha Aggarwal, Saptarashmi Bandyopadhyay, Vikas Bahirwani, Marc Niethammer, Ehsan Adeli, Andrea Colaco CVPR 2026 Paper \| Code
	From Videos to Conversations: Egocentric Instructions for Task Assistance Lavisha Aggarwal, Vikas Bahirwani, Andrea Colaco ICPR 2026 Paper · Project Page^[NEW!] · Code
	Generating Dialogues from Egocentric Instructional Videos for Task Assistance: Dataset, Method and Benchmark Lavisha Aggarwal, Vikas Bahirwani, Lin Li, Andrea Colaco, arXiv 2025 Paper \| Data \| Code \| Site
	EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart Glasses Akshay Paruchuri, Sinan Hersek, Lavisha Aggarwal, Qiao Yang, Xin Liu, Achin Kulshrestha, Andrea Colaco, Henry Fuchs, Ishan Chatterjee ISMAR 2025 Paper \| Website \| Code
	YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks Saptarashmi Bandyopadhyay, Vikas Bahirwani, Lavisha Aggarwal, Bhanu Guda, Lin Li, Andrea Colaco arXiv 2025 Paper
	Diffuse, Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion Junjiao Tian, Lavisha Aggarwal, Andrea Colaco, Zsolt Kira, Mar Gonzalez-Franco CVPR 2024 Paper \| Website \| Code
	Identity preserving loss for learned image compression Jiuhong Xiao, Lavisha Aggarwal, Prithviraj Banerjee, Manoj Aggarwal, Gerard Medioni CVPRW 2022 Paper \| Website \| Poster
	Fairness in AI Systems: Mitigating gender bias from language-vision models Lavisha Aggarwal, Shruti Bhargava arXiv 2018 Paper
	Binaural source localization using a HRTF data model with enhanced frequency diversity C Sandeep Reddy, Rishika Agarwal, Lavisha Aggarwal, Rajesh M Hegde EUSIPCO 2016 Paper

Awards

Outstanding Reviewer, CVPR 2026 · IEEE/CVF Conference on Computer Vision and Pattern Recognition · Top 5% of 17,000+ reviewers
Outstanding Reviewer, ICMI 2025 · ACM International Conference on Multimodal Interaction · Top 20 reviewers

Community Service

Reviewer

Conferences: CVPR 2026 · ICCV 2025 · NeurIPS 2026 · ICMI 2025–26 · WACV 2026–27 · BMVC 2026 · AAAI 2027
Journals: IEEE Transactions on Information Forensics and Security (TIFS), 2019
Workshops: CV4MR 2025 · SynGen 2025, both at CVPR

Organized:

Multi-Agent AI in the Real World Workshop at AAAI 2025 as a Steering Committee Member

Teaching

I have been a teaching assistant for the following courses:

Cloned from here!