Brokoslaw Laschowski
@drlaschowski.bsky.social
Assistant Professor @University of Toronto. Machine learning research scientist. Computational neuroscientist. https://discover.research.utoronto.ca/33310-brokoslaw-laschowski/
Version 2 of Theory of Contravariance w/ @dyamins.bsky.social is out! New material on contravariance for Transformers, and the theory of Representational Similarity Analysis (RSA) and centered kernel analysis (CKA)/Procrustes.
Aran Nayebi@anayebi.bsky.social · 3w ago1/6 Why have deep neural networks aligned so strongly with brains for the past 15 years? What explains it? @dyamins.bsky.social & I make progress on this question in our new paper👇 In a nutshell, we *prove* that for sufficiently hard tasks, the choice of alignment metric does *not* matter.
Introducing our framework for interpreting reward functions recovered by inverse reinforcement learning. www.biorxiv.org/content/10.6... @utoronto.ca @laschowski-lab.bsky.social
The Neuroscience Department at UC Berkeley is hiring an Asst Professor in Computational Neuro. All areas of computational/theoretical neuro are welcome. Deadline Oct 30. Join our neuroscience community! aprecruit.berkeley.edu/JPF05446 #AcademicJobs #Neuroscience #NeuroJobs
Assistant Professor - Computational Neuroscience - Department of Neuroscience
University of California, Berkeley is hiring. Apply now!
aprecruit.berkeley.edu
Applications are now open for the Vector Distinguished Postdoctoral Fellowships. Come join our world-class machine learning research community. Apply by August 31: vectorinstitute.ai/research-tal...
Postdoctoral Fellowships | AI Research | Vector Institute
Join Vector Institute's Distinguished Postdoctoral Fellowship program. Advance your AI research career with world-class faculty mentorship.
vectorinstitute.ai
Exclusive: Nvidia is investing in former OpenAI Chief Scientist Ilya Sutskever’s secretive artificial-intelligence lab, part of a long-term partnership that could boost the startup’s access to computing power while helping the chip giant fend off a rival wsj.visitlink.me/UseU5L
wsj.visitlink.me
Come join us in Toronto. UofT is hiring an Associate Professor/Professor and endowed Hinton Chair in Artificial Intelligence. @utoronto.ca @uoftcompsci.bsky.social jobs.utoronto.ca/job/Toronto-...
Associate Professor/Professor - Artificial Intelligence
Associate Professor/Professor - Artificial Intelligence
jobs.utoronto.ca
Aditya Rajeev presenting his research on valence-driven memory prioritization in machines. @utoronto.ca @uoftcompsci.bsky.social
Brandon Wong presenting his research on diffusion latent representations for brain-machine interface decoding. @utoronto.ca @uoftcompsci.bsky.social
Building computational models of learning, memory, and representation to better understand intelligence in brains and machines. Congratulations to Aditya Rajeev, Brandon Wong, and Samuel Kostousov. @utoronto.ca
Valence-driven memory prioritization in machines by Aditya Rajeev, Sofiya Zbaranska, Sheena Josselyn, and Brokoslaw Laschowski. @utoronto.ca
Bidirectional representational alignment between brains and machines by Samuel Kostousov, Abhin Kaushik, and Brokoslaw Laschowski. @utoronto.ca
Inverse reinforcement learning of multi-agent interactions by Justin Chow, Yunran Yang, and Brokoslaw Laschowski. @utoronto.ca
Diffusion latent representations for brain-machine interface decoding by Brandon Wong and Brokoslaw Laschowski. @utoronto.ca
@utoronto.ca has announced a new, multi-year partnership with @cohere.com, which was founded in 2019 by former U of T computer science students and has become the world's leading sovereign AI company. www.utoronto.ca/news/u-t-par...
U of T partnership with Cohere sets the stage for responsible AI adoption at scale
The University of Toronto is advancing its commitment to responsible artificial intelligence adoption at scale through an ambitious multi-year partnership with Cohere, a Canadian-founded, Toronto-base...
utoronto.ca
New paper: We introduce a framework for studying how intermediate representation choice affects downstream learning and reconstruction, with an initial demonstration in neural speech decoding using diffusion latents. www.biorxiv.org/content/10.6... @compneurolab.bsky.social @utoronto.ca
A brain-inspired framework for memory prioritization in neural networks based on valence https://www.biorxiv.org/content/10.64898/2026.05.05.723022v1
Interpreting Rewards from Inverse Reinforcement Learning https://www.biorxiv.org/content/10.64898/2026.07.08.736783v1
Diffusion Latent Representations for Neural Decoding https://www.biorxiv.org/content/10.64898/2026.07.08.737343v1
1/6 Why have deep neural networks aligned so strongly with brains for the past 15 years? What explains it? @dyamins.bsky.social & I make progress on this question in our new paper👇 In a nutshell, we *prove* that for sufficiently hard tasks, the choice of alignment metric does *not* matter.
📢 Just announced! Join us for the #KempnerInstitute workshop “Learning Dynamics in Natural and Artificial Intelligence: Evolution, Adaptation, and the Foundations of Efficient Learning.” Learn more, register, or submit an abstract 👉 bit.ly/3QwJlHR
Learning Dynamics in Natural and Artificial Intelligence - Kempner Institute
This workshop will convene researchers from artificial intelligence, neuroscience, cognitive science, and related disciplines to examine the principles governing learning and training dynamics across ...
bit.ly
#UofT ranked first in Canada, 20th globally in latest U.S. News & World Report university rankings 🌎 uoft.me/cv3
🧠 Imagine being able to control machines by thinking. @drlaschowski.bsky.social (MIE) and his Computational Neuroscience Lab are working to make it possible. They've developed a new algorithm that could make brain decoding more accurate and efficient. Read the story: uofteng.ca/25h7c8
![U of T Engineering News
Brains, minds & machines: A new algorithm for decoding intelligence [photo of Laschowski in a lab with a machine and a whiteboard with formulas]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:dhvtfzwixsh4hqcey3nzqmff/bafkreigfjkryxn2lp4f2omj2hclhoejujlrcncg76y37rrmeothdycm2li)
We've updated the preprint of our Naturalistic Computational Cognitive Science paper (arxiv.org/abs/2502.20349) — we've tried to clarify and streamline the arguments, and added some new examples: 1/5
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior
How can cognitive science build generalizable theories that span the full scope of natural situations and behaviors? We argue that progress in Artificial Intelligence (AI) offers timely opportunities ...
arxiv.org
www.amacad.org/publication/... my new article in the American academy of arts and sciences journal Daedalus. Part of a special issue in AI+Science lead by James Manyika.
Toward a Science of Intelligence: Unifying Physics, Neuroscience & AI
Artificial intelligence stands poised to transform our society, yet we hardly understand how it works. A synthesis of physics, neuroscience, and AI can fulfill an urgent need: to build a new, unified ...
amacad.org
This week, #FlatironCCN hosted a three-day workshop that brought together researchers in theoretical #neuroscience and control theory to foster collaboration. #science
Thanks to Tatiana Engel (@engeltatiana.bsky.social) from @princeton.edu for a great talk on Friday! She presented modeling approaches that leverage low-dimensional structure in neural population activity to design effective stimulation patterns. Watch the talk ➡️ youtu.be/rYvZoshNUVk
Blake Richards now : Why Artificial Intelligence needs literal synapses. - how modern AI and neuroscience research converge today
