Talmo Pereira.

Talmo Pereira

Assistant professor, Salk Institute for Biological Studies
Director, Center for AI and Research Computing

Talmo Pereira is assistant professor at the Salk Institute for Biological Studies, where he directs the Center for AI and Research Computing and leads a lab working at the intersection of computer vision, machine learning and neuroscience. He is a pioneer of computational ethology—the use of deep learning and computer vision to quantify complex animal behavior—and the creator of SLEAP, a widely used open-source tool for multi-animal pose tracking. SLEAP and its predecessor LEAP have together amassed more than 1,900 citations and 150,000 downloads, with some 45,000 users across 90 countries.

Pereira’s lab develops computational methods for measuring and modeling behavior from movement, with applications spanning motor control, neuromechanical simulation, neurodegenerative disease, cancer biology, plant biology and the humanities. He started his lab as a Salk Fellow in 2021 after earning a Ph.D. in neuroscience at Princeton University, where he held the NSF Graduate Research Fellowship and the Porter Ogden Jacobus Fellowship, Princeton’s highest graduate honor. His work, recognized with the Harold M. Weintraub Graduate Student Award, has appeared in journals including Nature Methods and Nature Neuroscience and is supported by the U.S. National Institutes of Health, the National Science Foundation, NASA and private funders.

Explore more from The Transmitter

Research image of mitochondrial activity in the mouse amygdala and hippocampus.

The fast-expanding repertoire of mitochondria in the brain

More than cellular powerhouses, these organelles also seem to help synapses communicate, support memory formation and even shape behavior.

By Giorgia Guglielmi
3 July 2026 | 7 min read
Two fingers turning a small dial.

When autistic kids grow up, Chapter 5: The war dial

“You have to reshape the whole system.” Tempest McDonald earns a measure of peace.

By Brady Huggett
2 July 2026 | 42 min listen
Red note stuck in a stack of paper.

Scientists decry conference’s use of hidden prompts to snare AI peer reviews

The invisible messages, which instruct large language models to use telltale phrases in a peer-review report, are effective in catching artificial-intelligence misuse but also erode trust, some say.

By Dalmeet Singh Chawla
1 July 2026 | 4 min read