About News Experience Papers
Deen Dayal Mohan

Deen Dayal Mohan

Staff Researcher
Samsung Research America

Working on |

I am a Staff Researcher in the Vision Intelligence Team at the AI Center, Samsung Research America, where I lead the effort in Multi-Modal Reasoning and Long-Horizon Planning for intelligent device experiences. I did my Ph.D. in Computer Science from University at Buffalo, where I was advised by Prof. Venu Govindaraju. My doctoral research primarily focused on Deep Metric Learning, Multi-Modal Fusion, Retrieval and Understanding. My work was supported by IARPA JANUS, NSF CITeR, IARPA BRIAR Programs. Prior to joining Samsung, I was a Research Scientist at Yahoo Research working on multi-modal content understanding in the Knowledge Graphs Science Team.

Education

Ph.D. in Computer Science University at Buffalo
M.S. in Computer Science University at Buffalo
B.Tech in Electronics and Communication Engineering Federal Institute of Science and Technology, MG University, Kerala

Research Interests

Computer Vision Multi-Modal LLMs Agentic Reasoning Multi-Modal Memory Long Horizon Plannning Efficient AI Vision Language Action Models
01

News

March 2026 New

Promoted to Staff Researcher, Vision Intelligence Team, AI Center, Samsung Research America

Nov 2024

Joined, Vision Intelligence Team, AI Center, Samsung Research America as a Senior Researcher

October 2024

Our Paper 'ProxyFusion: Face Feature Aggregation Through Sparse Experts' accepted at NeurIPS 2024

September 2024

Serving as Tutorial Chair for IJCB 2024, Buffalo, NY

August 2024

Our paper 'SCOT: Self-Supervised Contrastive Pre-training For Zero-Shot Compositional Retrieval' accepted at WACV 2025

July 2023

Joined, Knowledge Graphs Science Team, Yahoo Research, as a Research Scientist

July 2023

Our Paper 'CoNAN - Conditional Neural Aggregation Network for Unconstrained face recognition' accepted at IJCB 2023

June 2023

Graduated Ph.D. in Computer Science from University at Buffalo

January 2023

Two our Papers 'NapReg' and 'Hear the Flow' accepted at WACV 2023

02

Experience

November 2024 — Present

Mountain View, California

  • Staff Researcher

    March 2026 — Present

    • Leading research and development on multi-modal reasoning and long-horizon planning for next-generation AI experiences.

  • Senior Researcher

    November 2024 — March 2026

    • Developed efficient multi-modal understanding systems optimized for on-device and mobile intelligence scenarios.

Research Scientist

Yahoo Research
June 2023 — November 2024

Mountain View , California

Worked on multi-modal content understanding and extraction within the Knowledge Graphs Science Team.

Sep 2021 — May 2023

Buffalo, New York

Worked on Deep Metric Learning and Multi-Modal Fusion for Biometric Systems.

Research Scientist Intern

Yahoo Research
May 2022 — August 2022

San Jose, California

Worked on extracting structured content from product pages to enhance knowledge graphs

Research Scientist Intern

Verizon Media
May 2021 — August 2021

San Jose, California

Worked on Multi-Model Content Extraction and Understanding in the Knowledge Graphs Science Team.

Aug 2018 — May 2023

Buffalo, New York

Teaching Assistant in the department of Computer Science and Engineering, University at Buffalo.

Assistant System Engineer

Tata Consultancy Services
January 2015 — August 2016

Kochi, India

Worked on machine learning models for anomaly detection in television viewership data.

03

Selected Publications

ProxyFusion paper figure
NeurIPS 2024 · Conference on Neural Information Processing Systems

ProxyFusion: Face Feature Aggregation Through Sparse Experts

Bhavin Jawade, Alexander Stone, Deen Dayal Mohan, Xiao Wang, Srirangaraj Setlur, Venu Govindaraju

PDF
SCOT paper figure
WACV 2025 · IEEE/CVF Winter Conference on Applications of Computer Vision

SCOT: Self-Supervised Contrastive Pre-training For Zero-Shot Compositional Retrieval

Bhavin Jawade, Joao V. B. Soares, Kapil Thadani, Deen Dayal Mohan, Amir Erfan Eshratifar, Benjamin Culpepper, Paloma de Juan, Srirangaraj Setlur, Venu Govindaraju

PDF
CoNAN paper figure
IJCB 2023 · IEEE International Joint Conference on Biometrics ★ Oral, Best Paper Award

CoNAN: Conditional Neural Aggregation Network for Unconstrained Face Recognition

Deen Dayal Mohan, Bhavin Jawade, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju

PDF
NapReg paper figure
WACV 2023 · IEEE/CVF Winter Conference on Applications of Computer Vision

NAPReg: Nouns as Proxies Regularization for Deep Metric Learning

Deen Dayal Mohan, Bhavin Jawade, Naji Mohammed, Srirangaraj Setlur, Venu Govindaraju

PDF
Hear the Flow paper figure
WACV 2023 · IEEE/CVF Winter Conference on Applications of Computer Vision

Hear the Flow: Optical Flow-Based Self-Supervised Visual Sound Source Localization

Deen Dayal Mohan, Dennis Fedorishin, Bhavin Jawade, Srirangaraj Setlur, Venu Govindaraju

PDF
DML figure
Book Chapter 2023 · Handbook of Statistics, Edition 48 ★ Invited

Deep metric learning for computer vision: A brief overview

Deen Dayal Mohan, Bhavin Jawade, Srirangaraj Setlur, Venu Govindaraju

PDF
TADPool figure
FG 2021 · IEEE International Conference on Face and Gesture ★ Oral, Best Student Paper Award (Runner Up)

TADPool: Target Adaptive Pooling for Set Based Face Recognition

Deen Dayal Mohan, Nishant Sankaran, Sergey Tulyakov, Srirangaraj Setlur, Venu Govindaraju

PDF
cvpr figure
CVPR 2020 · IEEE/CVF Conference on Computer Vision and Pattern Recognition

Moving in the right direction: A Regularization for Deep Metric Learning

Deen Dayal Mohan, Nishant Sankaran, Dennis Fedorishin, Srirangaraj Setlur, Venu Govindaraju

PDF
View all on Google Scholar →

Let's Connect

I'm always interested in discussing research, collaborations, or just chatting about Computer Vision and Multi-Modal Understanding. Feel free to reach out!

deendayalmohan@gmail.com
Twitter LinkedIn