PeopleofSuperintelligence

Researcher

Nicolas Carion

Nicolas Carion is a computer vision researcher whose work spans cooperative reinforcement learning, object detection and visual segmentation. He coauthored DETR, which frames object detection as direct set prediction, and SAM 2 and SAM 3, models for promptable segmentation in images and video. After completing a PhD at Paris Dauphine University and Facebook AI Research in Paris, he held a postdoctoral position at NYU Courant under Yann LeCun and later coauthored FlowWM, a stochastic world model that uses flow matching in pretrained feature space. By June 2026, he is at a stealth startup with no public name.

Works
22
Citations
19,293
h-index
9
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2019

    Agent coordination through assignment

    In 2019, he coauthors a structured-prediction approach that assigns agents to tasks in cooperative multi-agent reinforcement learning.

  2. 2020

    DETR for object detection

    In 2020, computer vision researcher Nicolas Carion coauthors DETR, which treats object detection as direct set prediction.

  3. By 2022

    A PhD and NYU postdoc

    He completes a PhD at Paris Dauphine University and Facebook AI Research in Paris. He works as a postdoctoral researcher at NYU Courant under Yann LeCun from 2020 to 2022.

  4. 2024

    SAM 2 for video segmentation

    In 2024, he coauthors SAM 2, a foundation model for promptable segmentation in images and videos.

  5. 2025

    An ICLR honorable mention

    In 2025, ICLR gives SAM 2 an Outstanding Paper Honorable Mention.

  6. 2025

    Concept prompts in SAM 3

    In 2025, he coauthors SAM 3, which detects, segments and tracks objects in images and videos from noun-phrase or image-exemplar prompts.

  7. June 2026

    World modeling in feature space

    In June 2026, he coauthors Flow Matching in Feature Space for Stochastic World Modeling, which proposes FlowWM, a stochastic model that performs flow matching in pretrained feature space.

  8. June 2026

    A stealth startup

    By June 2026, he is at a stealth startup with no public name, after years as a research scientist at Meta’s FAIR lab.

Career

  1. 2021–2023New York University
  2. 2020–2022Courant Institute of Mathematical SciencesPostdoctoral researcher
  3. 2018–2022Meta
  4. 2016–2018ETH Zurich
  5. FAIR (Meta)Research scientist

Education

  1. Paris Dauphine UniversityPhD
  2. FAIR (Meta)PhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. End-to-End Object Detection with Transformers2020 · Lecture notes in computer science · 18,100 citations
  2. MDETR - Modulated Detection for End-to-End Multi-Modal Understanding2021 · IEEE/CVF International Conference on Computer Vision (ICCV) · 748 citationsWith Yann LeCun
  3. SAM 2: Segment Anything in Images and Videos2024 · 292 citationsWith Christoph Feichtenhofer, Piotr Dollár and Ross Girshick
  4. Constrained Bayesian Optimization with Particle Swarms for Safe Adaptive Controller Tuning2017 · IFAC-PapersOnLine · 41 citationsWith Andreas Krause and Angela Schoellig
  5. GeneCIS: A Benchmark for General Conditional Image Similarity2023 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 30 citationsWith Sagar Vaze

From OpenAlex, as of 21 October 2026.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes New York University. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes New York University. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  3. 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.
  4. 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.

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 Nicolas Carion yet. Send us a free-licensed photo.

  1. A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning arxiv.org. Checked 20 October 2026.
  2. End-to-End Object Detection with Transformers arxiv.org. Checked 20 October 2026.
  3. About me - Nicolas Carion nicolascarion.com. Checked 20 October 2026.
  4. Yann LeCun's Home Page cs.nyu.edu. Checked 20 October 2026.
  5. SAM 2: Segment Anything in Images and Videos arxiv.org. Checked 20 October 2026.
  6. Announcing the Outstanding Paper Awards at ICLR 2025 – ICLR Blog blog.iclr.cc. Checked 20 October 2026.
  7. SAM 3: Segment Anything with Concepts arxiv.org. Checked 20 October 2026.
  8. Flow Matching in Feature Space for Stochastic World Modeling arxiv.org. Checked 20 October 2026.
  9. Investor Day (004) investorday.substack.com. Checked 20 October 2026.