Presented Generative Action Tell-Tales: Assessing human motion in synthesized videos at the ML Collective DLCT reading group.
👋 Hi! I’m currently a Grad Student at Boston University. I completed my undergrad at Manipal Institute of Technology, India, and had developed a keen interest in all things ML during my first year and was fortunate to gain research experience along the way. Prior to joining BU, I worked with the Content and User Understanding team at ShareChat, and was fortunate to work on projects with the Serre Lab (Brown University), Human Dynamics Group (MIT Media Lab, Massachusetts Institute of Technology), ETS, Montreal and FOR.ai (now Cohere for AI).
At BU, I am fortunate to be advised by Prof. Deepti Ghadiyaram, and I’m currently exploring topics in computer vision, with a broad interest in representation learning and generative models.
CV / Email MeEducation
Ph.D. in Computer Science 2025 – Present
M.S. in Artificial Intelligence 2023 – 2025
Boston University
B.Tech. in Electronics and Instrumentation 2018 – 2022
Manipal Institute of Technology · Minor in Computational Intelligence
News
Generative Action Tell-Tales: Assessing human motion in synthesized videos accepted as an oral at VGBE and PhysHuman workshops, CVPR 2026.
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs accepted to CVPR 2026 Findings.
Presented Generative Action Tell-Tales: Assessing human motion in synthesized videos at NECV 2025 (oral).
Started my PhD at Boston University, advised by Prof. Deepti Ghadiyaram.
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization and Revelio: Interpreting and leveraging semantic information in diffusion models accepted at ICCV 2025.
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization accepted at the VisCon Workshop, CVPR 2025.
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models accepted as an oral at the AI4CC Workshop, CVPR 2025.
Revelio: Interpreting and leveraging semantic information in diffusion models accepted as an oral at the MIV Workshop, CVPR 2025.
Research
Semantic Richness or Geometric Reasoning? The Fragility of VLM’s Visual Invariance
Generative Action Tell-Tales: Assessing human motion in synthesized videos
Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
Revelio: Interpreting and leveraging semantic information in diffusion models
Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
Diversity vs. Recognizability: Human-like generalization in one-shot generative models
Adaptive Methods for Aggregated Domain Generalization
MAViC: Multimodal Active Learning for Video Captioning
For more see Google Scholar
Experience
Graduate Researcher
Boston University
Jun 2024 – Present
- Vision in Multimodal Large Language Models (MLLMs): Investigating limitations of visual understanding in MLLMs and developing methods to improve cross-modal alignment for robust multimodal reasoning.
- Evaluation of Video Generation Models: Designing and implementing novel evaluation metrics to assess human action fidelity, temporal consistency, and motion coherence in generative video models.
- Internal Representations of Diffusion Models: Analyzing diffusion models as representation learners by probing their intermediate states; demonstrating their effectiveness for downstream tasks such as classification, multi-modal reasoning, and domain generalization.
Advisor: Prof. Deepti Ghadiyaram
Machine Learning Engineer
ShareChat | Content and User Understanding Team
Jul 2022 – Jun 2023
Integrated advanced computer vision pipelines into production, improving content classification and moderation capabilities on ShareChat (180M+ MAUs) and Moj (160M+ MAUs). Contributed to MAViC, a Multimodal Active Learning algorithm for Video Captioning that reduces annotation effort by integrating semantic similarity and uncertainty from visual and language modalities.
Research Intern
Serre Lab, Brown University
Sep 2021 – May 2022
Developed a novel evaluation framework for one-shot generative models, introducing new metrics for recognizability (human interpretability) and diversity (concept coverage) to enable systematic comparisons. Benchmarked 4 representative generative architectures against human performance on the Omniglot dataset.
Advisors: Dr. Victor Boutin, Prof. Thomas Serre
Research Assistant
MIT Media Lab
Jan 2021 – Nov 2021
Created a novel algorithm for privacy-preserving domain generalization that recovers domain information by removing class-specific noise from latent features, enabling the training of robust, domain-adaptive classifiers. Outperformed state-of-the-art methods that require domain supervision on multiple benchmarks.
Advisor: Dr. Abhimanyu Dubey
Mitacs Globalink Research Intern
École de technologie supérieure (ÉTS), Montréal
Jul 2021 – Sep 2021
Extended sub-category exploration methods for Weakly Supervised Semantic Segmentation by clustering image features to generate more accurate pseudo-labels. Designed novel constraint-based refinements to enhance object localization in Class Activation Maps (CAMs), improving mIoU scores on PASCAL VOC 2012.
Advisor: Dr. Jose Dolz
Researcher
FOR.ai (now Cohere For AI)
Oct 2020 – Aug 2021
Contributed to a large-scale benchmarking study of Out-of-Distribution (OOD) detection in computer vision models, establishing baselines for evaluating robustness under distribution shifts. Collaborated with researchers from Google Brain, University of Oxford, and Vector Institute.
Advisor: Sheldon Huang