PeopleofSuperintelligence

Researcher

Kartik Narayan

Kartik Narayan is a computer vision and multimodal AI researcher whose work spans deepfake datasets, face analysis and search agents. Before his doctorate, he researched deepfake video generation at IIT Jodhpur and coauthored the DF-Platter dataset in 2023. He joined Johns Hopkins University in August 2023, coauthored FaceXFormer and PETALface in 2025, and worked on DeepMMSearch-R1 during an Apple research internship. In 2026, he developed a visual search benchmark at Apple and agentic search methods at Salesforce, and coauthored a paper on tree-structured reinforcement learning. As of October 2026, he is a final-year PhD student in Johns Hopkins University's VIU Lab, where he studies multimodal LLMs, agents, long-horizon tool calling and agentic search.

Badges

Timeline

  1. By 2023

    Undergraduate research at IIT Jodhpur

    Before joining Johns Hopkins University as a PhD student in August 2023, he works as an undergraduate researcher with Richa Singh and Mayank Vatsa at IIT Jodhpur's Image Analysis and Biometrics Lab, studying deepfake video generation.

  2. 2023

    The DF-Platter dataset

    At CVPR in 2023, he coauthors DF-Platter, a dataset of low- and high-resolution deepfakes that covers single and multiple subjects.

  3. August 2023

    A PhD at Johns Hopkins

    In August 2023, he joins Johns Hopkins University's Computer Science department as a PhD student in the VIU Lab, advised by Vishal Patel.

  4. 2025

    Facial analysis and face recognition

    He coauthors FaceXFormer at ICCV in 2025, a single transformer for ten facial-analysis tasks. At WACV in 2025, he coauthors PETALface, a parameter-efficient transfer-learning method for low-resolution face recognition.

  5. 2025–2026

    Apple's multimodal web search

    During his Summer 2025 Apple research internship, he works on DeepMMSearch-R1, which Apple publishes in January 2026. The model performs multi-turn web searches and creates queries for image and text search tools.

  6. 2026

    A multi-image search benchmark

    During his Apple Spring 2026 internship, he develops a multi-image, vision-centric benchmark for multimodal agentic search and analyzes failure modes when models search across several visual entities.

  7. 2026

    Agentic search at Salesforce

    At Salesforce AI Research in Summer 2026, he develops efficient multimodal agentic-search methods and explores tree-style branching rollouts. In September 2026, he coauthors Fork Where the Model Changes Its Mind, a paper on choosing branch points to estimate the value of reasoning steps.

  8. As of October 2026

    Final-year PhD at Johns Hopkins

    As of October 2026, he is a final-year PhD student in Johns Hopkins University's Computer Science department and a member of the VIU Lab, advised by Vishal Patel. His current interests include multimodal LLMs, agents, long-horizon tool calling, agentic post-training, agentic search, reasoning and video generation.

Career

  1. 2026AppleResearch Intern
  2. 2026Salesforce
  3. Until 2023Indian Institute of Technology JodhpurUndergraduate researcher

Education

  1. From 2023Johns Hopkins UniversityPhD student

From the biography.

  1. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Apple. Our estimates of where the 943 people shaping AI who worked at Google and Google DeepMind work now: 446 at Google and 452 across 278 other organizations.
  2. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Apple. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  3. Among employers with 30+ full-time cases, OpenAI leads primary technical role H-1B pay at $310,000, and Amazon, Google and Microsoft file 57% of all casesIncludes Apple. Across 440,669 certified US H-1B filings from 44 employers (FY2020–FY2026), OpenAI leads primary technical role base pay at $310,000 and xAI leads overall base pay at $290,000.
  4. The top 10 organizations employed 22% of people shaping AI in 2025: 51% of company researchers and 21% of university researchersIncludes Apple. We estimate the share of people shaping AI who worked at the top 10 organizations each year from 1955 to 2025, comparing concentration across companies, universities, and institutes and labs.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Kartik Narayan yet. Send us a free-licensed photo.

  1. Kartik Narayan kartik-3004.github.io. Checked 21 October 2026.
  2. DF-Platter: Multi-Face Heterogeneous Deepfake Dataset openaccess.thecvf.com. Checked 21 October 2026.
  3. FaceXFormer: A Unified Transformer for Facial Analysis openaccess.thecvf.com. Checked 21 October 2026.
  4. PETALface: Parameter Efficient Transfer Learning for Low-Resolution Face Recognition openaccess.thecvf.com. Checked 21 October 2026.
  5. DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search machinelearning.apple.com. Checked 21 October 2026.
  6. [2510.12801] DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search arxiv.org. Checked 21 October 2026.
  7. [2609.11061] Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning arxiv.org. Checked 21 October 2026.
  8. PhD Students - Department of Computer Science cs.jhu.edu. Checked 21 October 2026.