PeopleofSuperintelligence

Researcher

Ishaan Javali

Ishaan Javali is a Princeton computer science student whose research covers reinforcement learning and robot policies. In 2025, they were second author of "1000 Layer Networks for Self-Supervised RL," which reported that scaling network depth up to 1024 layers can significantly boost performance and was named one of the four NeurIPS 2025 Best Papers. The work grew out of undergraduate research seminars at Princeton, and the team included Kevin Wang, Michał Bortkiewicz, Tomasz Trzciński and Benjamin Eysenbach. In July 2026, they co-authored a paper on Mixture-of-Experts action heads for robot policies with Dhruv Shah and four other Princeton coauthors. Javali serves as Workshops Chair of AI@Princeton.

Now at
AI@Princeton

Timeline

  1. March 2025

    A 1000-layer RL preprint

    The preprint "1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities" appears on arXiv in March 2025, with Javali as second author after Kevin Wang and ahead of Michał Bortkiewicz, Tomasz Trzciński and Benjamin Eysenbach. It reports that increasing network depth up to 1024 layers can significantly boost performance in self-supervised reinforcement learning.

  2. 2025

    NeurIPS 2025 Best Paper

    The paper is one of four NeurIPS 2025 Best Papers, announced in November 2025. The selection committee describes the work as a novel and easy-to-implement RL paradigm for training very deep neural networks, using self-supervised and contrastive RL.

  3. December 2025

    An oral in San Diego

    The paper is an oral at NeurIPS 2025, held in San Diego from December 2 to December 7, 2025. Princeton's AI research blog lists it under Best Paper Award among the university's work at the conference.

  4. January 2026

    The Latent Space podcast

    The Latent Space podcast publishes an episode in January 2026 on the paper, tracing it from undergraduate research seminars at Princeton to the NeurIPS 2025 Best Paper award.

  5. July 2026

    Mixture-of-experts robot policies

    Javali co-authors "Emergent Compositional Skills in Mixture-of-Experts VLAs" with Shlok Shah, Rhiaan Jhaveri, Tharun Kumar Tiruppali Kalidoss, Chirayu Nimonkar and Dhruv Shah, posted to arXiv in July 2026 from Princeton's Department of Computer Science. The paper asks whether a vision-language-action model with a Mixture-of-Experts action head can learn reusable, interpretable primitives, and it is accepted to the 2nd Workshop on Compositional Learning at ICML 2026.

  6. As of October 2026

    Workshops Chair at AI@Princeton

    Javali serves as Workshops Chair of AI@Princeton, alongside Kevin Wang, who holds the same title. The page for the current officers places both in Princeton's Class of 2026 in computer science.

Career

  1. NowAI@PrincetonWorkshops Chair

Education

  1. Princeton UniversityComputer science student

From the biography.

  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 Ishaan Javali yet. Send us a free-licensed photo.

  1. 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities arxiv.org. Checked 21 October 2026.
  2. NeurIPS 2025 Awards neurips.cc. Checked 21 October 2026.
  3. Princeton University at NeurIPS 2025 blog.ai.princeton.edu. Checked 21 October 2026.
  4. Announcing the NeurIPS 2025 Best Paper Awards blog.neurips.cc. Checked 21 October 2026.
  5. NeurIPS Oral 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities neurips.cc. Checked 21 October 2026.
  6. 1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities - Princeton University collaborate.princeton.edu. Checked 21 October 2026.
  7. [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised RL — Kevin Wang et al, Princeton latent.space. Checked 21 October 2026.
  8. Emergent Compositional Skills in Mixture-of-Experts VLAs arxiv.org. Checked 21 October 2026.
  9. Emergent Compositional Skills in Mixture-of-Experts VLAs (HTML version) arxiv.org. Checked 21 October 2026.
  10. Officers - AI@Princeton aiatprinceton.com. Checked 21 October 2026.