PeopleofSuperintelligence

Researcher

Ramakrishna Vedantam

Also known as Rama Vedantam, Shanmukha Ramakrishna Vedantam

Ramakrishna Vedantam is an AI researcher and venture builder whose papers include CIDEr, a metric for scoring image descriptions, and Grad-CAM, a method for explaining the predictions of convolutional networks. He earned a B.Tech at IIIT Hyderabad, began as a graduate research assistant at Virginia Tech in 2014, and earned his PhD at Georgia Tech, where Google named him a PhD Fellow in 2018. From 2019 to 2023, he was a research scientist at Meta in New York, and in 2023 he coauthored MERU, a hyperbolic image-text model presented at ICML. Since 2024, he is a senior director at Flagship Pioneering, where he leads AI efforts to create and scale new ventures, and in October 2026 he appears on the team of iris labs, a Flagship company.

Now at
Flagship Pioneering
Badges

Timeline

  1. 2009–2013

    B.Tech at IIIT Hyderabad

    He studies for a B.Tech at the International Institute of Information Technology Hyderabad from 2009 to 2013.

  2. 2014–2015

    Virginia Tech and CIDEr

    He starts as a graduate research assistant at Virginia Tech in 2014. In 2015, he, C. Lawrence Zitnick and Devi Parikh present CIDEr at CVPR, a metric that scores image descriptions by human consensus; the CIDEr-D version is available through the MS COCO evaluation server.

  3. 2017

    Grad-CAM visual explanations

    In 2017, he coauthors Grad-CAM at ICCV with Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Devi Parikh and Dhruv Batra. The method uses the gradients of a target concept flowing into the final convolutional layer to produce a coarse map of the image regions that matter for a prediction, and it applies to image classification, captioning and visual question answering models.

  4. 2018

    A Google PhD Fellowship

    As a PhD student at Georgia Tech, he is named a 2018 Google PhD Fellow in Machine Perception, Speech Technology and Computer Vision. He earns his PhD there.

  5. 2019–2023

    Research scientist at Meta

    From February 2019 to February 2023, he is a research scientist at Meta in New York City, working with Facebook AI Research (FAIR) and Meta AI. From February 2023 to November 2023, he is also a visiting faculty member at New York University's Center for Data Science.

  6. 2023

    MERU hyperbolic image-text model

    In 2023, he coauthors Hyperbolic Image-Text Representations at ICML with Karan Desai, Maximilian Nickel, Tanmay Rajpurohit and Justin Johnson. The paper proposes MERU, a contrastive model that yields hyperbolic representations of images and text and stays competitive with CLIP on image classification and image-text retrieval.

  7. Since 2024

    Senior director at Flagship

    He becomes a senior director at Flagship Pioneering in 2024, where he leads AI efforts to create and scale new ventures.

  8. As of October 2026

    AI research at iris labs

    He is senior director, AI research, on the team of iris labs, the Flagship Pioneering spinout that launches its first product, Iris Chat, in October 2026.

Career

  1. Since 2024Flagship PioneeringSenior Director
  2. 2023New York UniversityVisiting Faculty Member
  3. 2019–2023MetaResearch Scientist
  4. 2014–2015Virginia TechGraduate Research Assistant

Education

  1. 2018Georgia Institute of TechnologyPhD
  2. 2013International Institute of Information Technology, HyderabadB.Tech

From the biography.

  1. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes Meta. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  2. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Meta. Our estimates of the organizations where 550 people worked directly before joining 9 frontier AI labs across 620 career transitions, comparing the main feeder organizations per lab.
  3. Of 943 people shaping AI who worked at Google, 446 work there nowIncludes Meta. 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.
  4. 22 of 133 people shaping AI with a former OpenAI role now work at AnthropicIncludes Meta. Our estimates of where OpenAI recruits came from and where 133 people with former OpenAI roles work now, including the companies and labs they founded.

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 Ramakrishna Vedantam yet. Send us a free-licensed photo.

  1. Ramakrishna Vedantam | alphaXiv alphaxiv.org. Checked 22 October 2026.
  2. CVPR 2015 Open Access Repository: CIDEr: Consensus-Based Image Description Evaluation openaccess.thecvf.com. Checked 22 October 2026.
  3. ICCV 2017 Open Access Repository: Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization openaccess.thecvf.com. Checked 22 October 2026.
  4. Announcing the 2018 Google PhD Fellows for North America, Europe and the Middle East research.google. Checked 22 October 2026.
  5. Rama Vedantam ramavedantam.com. Checked 22 October 2026.
  6. Hyperbolic Image-text Representations proceedings.mlr.press. Checked 22 October 2026.
  7. Cambridge firm's latest bet: An 'AI thought partner' for navigating life nbcboston.com. Checked 22 October 2026.