Swetha Sirnam

I'm an applied scientist at Amazon. I completed my PhD at Center for Research in Computer Vision (CRCV), University of Central Florida advised by Prof. Mubarak Shah. Most of my research focuses on self-supervised learning, multi-modal learning, covering MLLMs, Spatial and Temporal Reasoning in VideoLLMs, Visual Preference Alignment, Safety and Bias analysis. I have done multiple research internships at Amazon, where I worked on improving the visual perception capabilities of MLLMs and video understanding. Previously, I graduated with Bachelor in Technology (B.Tech) with Honors and MS by research from International Institute of Information Technology, Hyderabad (IIIT-H), where I was advised by Prof. C. V. Jawahar (Center for Visual Information Technology [CVIT], IIIT-H) and Prof. Vineeth N Balasubramanian, IIT-H.

Email / Scholar / Twitter / Github

Updates

Jun'26: 2 papers accepted at ECCV 2026 💥
Jun'26: Organized Second Workshop on VideoLLMs at CVPR 2026 💥
Apr'26: TimeLogic is accepted as a challenge track at CVPR 2026 Workshop on VideoLLMs 💥💥
Apr'26: VRR-QA is accepted as a challenge track at CVPR 2026 Workshop on VideoLLMs 💥💥
Apr'26: VRR-QA accepted as CVPR 2026 Highlight paper 💥💥
Feb'26: 3 papers (2 First author papers) accepted at CVPR 2026 💥💥
Dec'25: Our Second Workshop on VideoLLMs accepted at CVPR 2026 💥💥
Nov'25: A First author paper "SMPRO" accepted at AAAI 2026 💥
Oct'25: A paper accepted at ICCV 2025, Oral presentation! (Top 0.6% papers)💥💥
Jun'25: Co-oranized Workshop on VideoLLMs at CVPR 2025 💥💥
Jun'25: Area Chair for Workshop on VideoLLMs at CVPR 2025 💥
Mar'25: Organized Challenges on VideoLLMs at CVPR 2025
Sep'24: Third place - Perception Challenge at ECCV 2024
Jul'24: A First author paper "X-Former" accepted at ECCV 2024 💥
May'24: Started summer internship at Amazon, Palo Alto, CA
May'23: Started summer internship at Amazon, Palo Alto, CA
Jul'23: A First author paper "Multi-Sinkhorn Knopp" accepted at ICCV 2023 💥
May'22: Started summer internship at Amazon, Seattle, CA
Jun'21: UDE paper Oral presentation at CVPR L2ID 2021 💥
May'21: A First author paper "UDE" accepted at ICIP 2021

Work Experience

PhD Applied Scientist Intern
Amazon, Palo Alto, California, USA. May 2024

Enhanced visual preference alignment for improving general MLLM understanding.
Proposed Self-Supervised Flexible Multi-Group Preference Alignment framework without relying on any external experts models or human annotators.
Outperformed state-of-the-art methods using our novel approach, achieving superior results.

PhD Applied Scientist Intern
Amazon, Palo Alto, California, USA. May 2023

Enhanced the fine-grained visual perception capabilities of MLLMs, outperforming BLIP-2 & Flamingo.
Performed large-scale multi-modal training with millions of samples.
Our X-Former achieved state-of-the-art performance on both fine-grained and general tasks, paper accepted at ECCV 2024.

PhD Applied Scientist Intern
Amazon, Seattle, Washington, USA. May 2022

Developed a detailed video description framework that employs VideoSwin Transformer for long-form videos.
Proposed to spatio-temporally match each textual concept to a visual concept for fine-grained representation learning.
Demonstrated improved performance on captioning task with detailed error analysis

Analyst
Goldman Sachs, Bengaluru, Karnataka, India.

Worked with Investment Banking Team primarily.

Intern
Goldman Sachs, Bengaluru, Karnataka, India.

Interned with Investment Banking Team.

Featured Research

My current research interest lies in the field of self-supervised learning for video and image understanding, including multi-modal learning.

	VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues Sirnam Swetha, Rohit Gupta, Parth Parag Kulkarni, David G Shatwell, Jeffrey A Chan Santiago, Nyle Siddiqui, Joseph Fioresi, Mubarak Shah CVPR (Highlight), 2026 paper / Data / arxiv / code / project page / bibtex
	TIGeR: A Unified Framework for Time, Images and Geo-location Retrieval David G Shatwell, Sirnam Swetha, Mubarak Shah CVPR, 2026 paper / supp / arxiv / project page / bibtex
	Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety Younggun Kim, Sirnam Swetha, Fazil Kagdi, Mubarak Shah (equally contributing first author) CVPR*, 2026 paper / Data / arxiv / code / project page / bibtex
	SMPRO: Self-Supervised Visual Preference Alignment via Differentiable Multi-Preference Multi-Group Ranking Sirnam Swetha, Rui Meng, Shwetha Ram, Tal Neiman, Son Tran, Mubarak Shah AAAI, 2026 paper / project page / bibtex
	GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space David G Shatwell, Ishan Rajendrakumar Dave, Sirnam Swetha, Mubarak Shah ICCV (Oral), 2025 paper / supp / arxiv / code / project page / bibtex
	TimeLogic: A Temporal Logic Benchmark for Video QA Sirnam Swetha, Hilde Kuehne, Mubarak Shah arxiv, 2025 paper / arxiv / project page / bibtex
	The Telephone Game: Evaluating Semantic Drift in Unified Models Sabbir Mollah, Rohit Gupta, Sirnam Swetha, Qingyang Liu^, Ahnaf Munir^, Mubarak Shah (equal contribution) arxiv*, 2025 paper / Data / arxiv / code / project page / bibtex
	StretchySnake: Flexible SSM Training Unlocks Action Recognition Across Spatio-Temporal Scales Nyle Siddiqui, Rohit Gupta, Sirnam Swetha, Mubarak Shah arxiv, 2025 arxiv / bibtex
	SB-Bench: Stereotype Bias Benchmark for Large Multimodal Models Vishal Narnaware, Ashmal Vayani, Rohit Gupta♠, Sirnam Swetha♠, Mubarak Shah (equally contributing first author, ♠equally contributing second author) arxiv*, 2025 paper / Data / arxiv / code / project page / bibtex
	X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs Sirnam Swetha, Jinyu Yang, Tal Neiman, Mamshad Nayeem Rizve, Son Tran, Benjamin Yao, Trishul Chilimbi, Mubarak Shah ECCV, 2024 paper / supplement / arxiv / project page / bibtex
	Multi-SK: Preserving Modality Structure Improves Multi-Modal Learning Sirnam Swetha, Mamshad Nayeem Rizve, Nina Shvetsova, Hilde Kuehne, Mubarak Shah ICCV, 2023 paper / supplement / arxiv / code / project page / bibtex
	Unsupervised Discriminative Embedding for Action Learning in Complex Activities Sirnam Swetha, Hilde Kuehne, Yogesh S Rawat, Mubarak Shah ICIP, CVPR L2ID (Oral), 2021 paper / arxiv / project page / bibtex
	Sequence-to-Sequence Learning for Human Pose Correction in Videos Sirnam Swetha, Vineeth N Balasubramanian, CV Jawahar ACPR, 2017 paper / project page / bibtex
	Efficient Object Annotation for Surveillance and Automotive Applications Sirnam Swetha, Anand Mishra, Guruprasad M Hegde, CV Jawahar WACVW, 2016 paper / project page / bibtex
	Online handwriting recognition using depth sensors Rajat Aggarwal, Sirnam Swetha, Anoop M Namboodiri, Jayanthi Sivaswamy, CV Jawahar (equally contributing first author) ICDAR*, 2015 paper / project page / bibtex

Miscellanea

Micropapers	Wildlife Action Recognition using Deep Learning
Academic Service	Co-Organizer, CVPR Workshop on VideoLLMs 2025 Area Chair, CVPR Workshop on VideoLLMs 2025 Reviewer: CVPR, ICLR, NeurIPS, AAAI, WACV

Feel free to steal this website's source code. Also, consider using Leonid Keselman's Jekyll fork of this page.

Updates

Work Experience

Featured Research

Miscellanea

Micropapers

Academic Service