PeopleofSuperintelligence

Researcher

Yash Goyal

Yash Goyal is a vision-and-language researcher who co-organized the VQA Challenge and was credited with the VQA Series of Challenges, winner of the 2025 PAMI Mark Everingham Prize. They received a PhD in 2020 from the School of Interactive Computing at Georgia Tech, advised by Dhruv Batra, and wrote "Making the V in VQA Matter" for CVPR 2017 with Tejas Khot, Douglas Summers-Stay, Batra and Devi Parikh. In 2019, they introduced counterfactual visual explanations at ICML, and they worked as a Research Scientist at Samsung AI Lab Montreal within Mila. Recent papers study bias in unconditional image generators and cultural alignment in text-to-image models. They are an independent visiting researcher at Mila with Samsung SAIT, supervised by Simon Lacoste-Julien.

Now at
Mila

Timeline

  1. 2014–2020

    PhD under Dhruv Batra

    They join Dhruv Batra's Machine Learning and Perception Lab as a PhD student in 2014. In 2020, they receive their PhD from the School of Interactive Computing at Georgia Tech, advised by Batra.

  2. 2016

    Yin and Yang at CVPR

    In 2016, they share first authorship with Peng Zhang on "Yin and Yang: Balancing and Answering Binary Visual Questions" at CVPR, which balances the VQA dataset so that models have to understand the image. Their paper "Towards Transparent AI Systems: Interpreting Visual Question Answering Models" is a Best Student Paper at the ICML Workshop on Visualization for Deep Learning.

  3. 2017

    Making the V in VQA Matter

    At CVPR 2017, they publish "Making the V in VQA Matter" with Tejas Khot, Douglas Summers-Stay, Dhruv Batra and Devi Parikh. The paper balances the VQA dataset by pairing each question with two similar images that have different answers, and the full VQA v2.0 release follows in April 2017.

  4. 2017–2018

    Co-organizing the VQA Challenge

    As a co-organizer of the annual VQA Challenge, they present the dataset, the winners and an analysis of results at the CVPR challenge workshops in 2017 and 2018.

  5. 2019

    Counterfactual visual explanations

    They are first author of the ICML 2019 paper "Counterfactual Visual Explanations" with Ziyan Wu, Jan Ernst, Dhruv Batra, Devi Parikh and Stefan Lee. The technique shows how a query image would have to change for a vision system to predict a different class.

  6. 2025

    The Mark Everingham Prize

    The PAMI Mark Everingham Prize for 2025 goes to the VQA Series of Challenges, credited to Aishwarya Agrawal, Yash Goyal, Ayush Shrivastava, Dhruv Batra, Devi Parikh and collaborators, for stimulating a new strand of vision and language research. The prize is awarded at ICCV 2025.

  7. 2025

    Bias and culture in image generators

    In 2025, they coauthor "Bias Analysis in Unconditional Image Generative Models" with Xiaofeng Zhang, Michelle Lin, Simon Lacoste-Julien and Aaron Courville, which finds small attribute shifts that are sensitive to the attribute classifier used for labeling. They also coauthor CulturalFrames, a benchmark of 983 prompts across 10 countries for cultural expectations in text-to-image models, published in EMNLP Findings in 2025.

  8. As of October 2026

    Visiting researcher at Mila

    A former Research Scientist at Samsung AI Lab Montreal within Mila, they are an independent visiting researcher at Mila with Samsung SAIT, supervised by Simon Lacoste-Julien. Their research topics are explainable AI, generative models, and vision and language.

Career

  1. NowMilaResearch Scientist, Visiting Researcher

Education

  1. 2020Georgia Institute of TechnologyPhD Student

From the biography.

  1. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Mila. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.
  2. Companies supply the most prior-work hires at 7 of the 9 frontier AI labsIncludes Mila. 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 Mila. 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. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Mila. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

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 Yash Goyal yet. Send us a free-licensed photo.

  1. Yash Goyal yash-goyal.github.io. Checked 20 October 2026.
  2. Georgia Tech MLP Lab mlp.cc.gatech.edu. Checked 20 October 2026.
  3. [1612.00837] Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering arxiv.org. Checked 20 October 2026.
  4. VQA: Visual Question Answering visualqa.org. Checked 20 October 2026.
  5. Counterfactual Visual Explanations proceedings.mlr.press. Checked 20 October 2026.
  6. Aishwarya Agrawal awarded Everingham Prize 2025 | Mila mila.quebec. Checked 20 October 2026.
  7. [2506.09106] Bias Analysis in Unconditional Image Generative Models arxiv.org. Checked 20 October 2026.
  8. Yash Goyal | Mila mila.quebec. Checked 20 October 2026.