PhdFit
Resume-aware faculty matching

Find professors who actually fit you

Review faculty evidence in public, then use the workspace to turn your background into a shortlist, outreach, and meeting prep.

Profile-awarePaper evidenceSix agents
Stefano Soatto

Stefano Soatto

· Professor

University of California, Los Angeles · Computer Science

Active 1993–2026

h-index83
Citations32.8k
Papers699220 last 5y
Funding$697k

Academic metrics are sourced from OpenAlex and public funding records; values may differ from Google Scholar.

Faculty page
See your match with Stefano Soatto — sign in to PhdFit.Sign in

About

Stefano Soatto is a professor in the Department of Computer Science and Electrical and Computer Engineering at UCLA Samueli School of Engineering. His research interests include computer vision, machine learning, and robotics. He holds a PhD from the California Institute of Technology, earned in 1996. Dr. Soatto has been recognized as an ACM Fellow in 2023 and an IEEE Fellow in 2013. His contributions to the field have been acknowledged through awards such as the David Marr Prize in 1999. He is actively involved in advancing knowledge in artificial intelligence and visual perception, contributing to the understanding of how humans and machines interpret visual data.

Research topics

  • Computer Science
  • Artificial Intelligence
  • Machine Learning
  • Mathematics
  • Algorithm
  • Computer vision

Selected publications

  • Rethinking the Hyperparameters for Fine-tuning

    arXiv (Cornell University) · 2020 · 62 citations

    Senior authorCorresponding

    Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to values normally used for training from scratch. This paper re-examines several common practices of setting hyperparameters for fine-tuning. Our findings are based on extensive empirical evaluation for fine-tuning on various transfer learning benchmarks. (1) While…

    DOI

  • AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation

    Lecture notes in computer science · 2024-10-30 · 3 citations

    book-chapter
    PublisherDOI

  • Heat Death of Generative Models in Closed-Loop Learning

    2024-12-16 · 2 citations

    article

    Improvement and adoption of generative machine learning models is rapidly accelerating, as exemplified by the popularity of LLMs (Large Language Models) for text, and diffusion models for image generation. As generative models become widespread, data they generate is incorporated into shared content through the public web. This opens the question of what happens when data generated by a model is fed back to the model in subsequent training campaigns. This is a question about the stability of the…

    PublisherDOI

  • On the Viability of Monocular Depth Pre-training for Semantic Segmentation

    Lecture notes in computer science · 2024-12-01 · 1 citations

    book-chapterSenior author
    PublisherDOI

  • Learning When to Attend: Conditional Memory Access for Long-Context LLMs

    ArXiv.org · 2026-03-18

    articleOpen accessSenior author

    Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We observe that most tokens do not require (Global) Attention over the entire sequence and can rely on local context. Based on this, we propose L2A (Learning To Attend), a layer that enables conditional (token-wise) long-range memory access by deciding when to invok…

    PublisherOA PDF

Recent grants

Frequent coauthors

  • S. Shankar Sastry

    102 shared

  • Alessandro Achille

    100 shared

  • Yi Ma

    Shaoyang University

    99 shared

  • Jana Košecká

    98 shared

  • Avinash Ravichandran

    61 shared

  • Alex Wong

    49 shared

  • Pietro Perona

    45 shared

  • Anthony Yezzi

    Georgia Institute of Technology

    38 shared

Education

  • Ph.D., Computer Science

    University of California, Los Angeles

    1995

  • M.S., Computer Science

    University of California, Los Angeles

    1991

  • B.S., Computer Science

    University of Rome 'La Sapienza'

    1987

Awards & honors

  • ACM Fellow, 2023
  • IEEE Fellow, 2013
  • David Marr Prize, 1999

Similar researchers at University of California, Los Angeles

  • Resume-aware match score
  • Save to shortlist
  • AI-drafted outreach

See your match with Stefano Soatto

PhdFit ranks faculty by your research interests, methods, and publications — grounded in their actual work, not templates.

Sign in to PhdFitHow it works
  • Free to start
  • No credit card
  • 30-second signup