PeopleofSuperintelligence

Researcher

Kevin Wang

Kevin Wang is a Princeton graduate and the first author of "1000 Layer Networks for Self-Supervised RL", a reinforcement learning paper that won a Best Paper award at NeurIPS 2025. The work began in an independent work research seminar taught by Benjamin Eysenbach, and he posted it on arXiv in March 2025 with Ishaan Javali, Michał Bortkiewicz, Tomasz Trzciński and Eysenbach. Raising network depth up to 1024 layers lifted contrastive RL performance by 2× to 50× on simulated locomotion and manipulation tasks, with no demonstrations or rewards. In a January 2026 interview with Latent Space, he described himself as a recent Princeton graduate who started and led the project.

Timeline

  1. By March 2025

    A seminar project at Princeton

    As a Princeton undergraduate, he starts a project in an independent work research seminar taught by Benjamin Eysenbach, one of his first experiences in machine learning research. He collaborates with Ishaan Javali, who is in the same seminar. By March 2025, the project is a paper with Javali, Michał Bortkiewicz, Tomasz Trzciński and Eysenbach as coauthors.

  2. March 2025

    A paper on 1024-layer networks

    In March 2025, he posts "1000 Layer Networks for Self-Supervised RL" on arXiv as first author. The paper shows that raising depth up to 1024 layers lifts contrastive RL performance by 2× to 50× on simulated locomotion and manipulation tasks, with no demonstrations or rewards.

  3. 2025

    Project page and open code

    Alongside the NeurIPS 2025 paper, he is the contact for a project page that shows 64-layer networks on humanoid, ant maze and arm tasks and tests the limits of scaling up to 1000 layers. The scaling-crl code on GitHub builds on JaxGCRL.

  4. 2025

    A NeurIPS Best Paper

    The paper is an oral at NeurIPS 2025 in San Diego in December 2025 and receives a Best Paper award. Wang, Javali and Bortkiewicz lead the work, which Eysenbach's Princeton RL group presents at the conference.

  5. January 2026

    A Latent Space interview

    In January 2026, the Latent Space podcast publishes an interview with the team, recorded at NeurIPS. He describes himself as a Princeton undergraduate who has just graduated and says he started and led the project.

  6. October 2026

    A revised arXiv paper

    In October 2026, the fifth version of the paper appears on arXiv with him as first author, listed at Princeton University.

Videos

YouTube videos in which Kevin Wang speaks or appears, newest first. A model chose them from YouTube search results. List updated 22 October 2026.

  1. [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, PrincetonLatent Space · 31 December 2025 · 28 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.

  1. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes Princeton 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.
  2. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorateIncludes Princeton University. 84% of people shaping AI with recorded undergraduate and doctoral schools changed institutions for their doctorate. Across 2,116 people with both an undergraduate degree and a doctorate recorded, we trace which undergraduate schools feed which doctoral programs, how often students stay at the same school, and how paths differ by birth-country region.
  3. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes Princeton University. 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.
  4. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Princeton 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.

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 Kevin Wang yet. Send us a free-licensed photo.

  1. [NeurIPS Best Paper] 1000 Layer Networks… Transcript spoken.md. Checked 22 October 2026.
  2. [2503.14858] 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities arxiv.org. Checked 22 October 2026.
  3. 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities - Princeton University collaborate.princeton.edu. Checked 22 October 2026.
  4. 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities (project page) wang-kevin3290.github.io. Checked 22 October 2026.
  5. GitHub - wang-kevin3290/scaling-crl github.com. Checked 22 October 2026.
  6. NeurIPS 2025 Awards neurips.cc. Checked 22 October 2026.
  7. Princeton University at NeurIPS 2025 – Princeton Artificial Intelligence Research Blog blog.ai.princeton.edu. Checked 22 October 2026.
  8. Benjamin Eysenbach ben-eysenbach.github.io. Checked 22 October 2026.
  9. [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton latent.space. Checked 22 October 2026.
  10. 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities (arXiv HTML, v5) arxiv.org. Checked 22 October 2026.