Levi Lelis

Associate Professor - University of Alberta - Canada CIFAR AI Chair (he/him, ele/dele).

Machine learning as program search.

[Levi Lelis @levilelis]

I recently spoke at IPAM's Naturalistic Approaches to Artificial Intelligence Workshop, and shared some of the programmatic perspectives we're exploring in reinforcement learning research.

https://t.co/uZCrJupBA2

[Levi Lelis @levilelis]

@DimitrisPapail 15%

[Csaba Szepesvari @CsabaSzepesvari]

I can nominate one Canada Impact+ postdoc candidate at UAlberta. Please reach out only if you have a strong theory track record (learning theory/bandits-RL theory/LLM reasoning). Deadline: May 10 (23:59 MT. Email: CV + best papers + brief pitch. Pls RT https://t.co/pnRmnxPyCi

[matt @MattVMacfarlane]

I'm in Brazil for ICLR! 🇧🇷

Presenting our paper "Gradient-Based Program Synthesis with Neurally Interpreted Languages" (https://t.co/a9Kkz7OUQQ) on Thursday, April 23rd, 10:30 AM – 1:00 PM at Pavilion 3, P3-#215.

If you want to chat about world models, test-time adaptation or continual learning lets set up a chat or come say hi!

[Levi Lelis @levilelis]

I’m headed to Brazil for #ICLR2026 and looking forward to seeing old friends and making new ones. Please drop me a line if you’d like to chat about program synthesis, programmatic reinforcement learning, or programmatic representations more broadly.

[Marlos C. Machado @MarlosCMachado]

A couple of months ago, we released a preprint of one of my favourite papers I’ve ever written. It lies at the intersection of representation learning and neuroscience. I have now written a blog post about it.

Preprint: https://t.co/vtDeBzvjsq

Blog post: https://t.co/d5rPZHoGaC

[Amii @AmiiThinks]

Amii is hiring a Machine Learning Resident (1-year term) to work with ConeTec! Help solve critical safety challenges in geocharacterization using LLMs, OCR, and Deep Learning.

📍 Edmonton (Hybrid)
📅 Apply by March 4, 2026
🔗 https://t.co/0uUbzh65PG

[Amii @AmiiThinks]

Amii is hiring a Machine Learning Scientist to lead our ML Educators and scale AI literacy across Canada.

If you have a background in ML research, people leadership, and a passion for AI for good, apply now: https://t.co/nntmTsPYIa

[Clem Bonnet @ClementBonnet16]

Insightful thread about world models with ideas that very few people in the industry understand!

Building static, giant world models is a dead end for achieving human-level adaptation to new tasks. Instead, it's all about efficiently adapting local models of the world. The community should develop systems that produce world models (a la program synthesis) rather than static models.

[Amjad Masad @amasad]

To make a bit of an excuse for Microsoft: the world is just waking up to the fact that coding agents are general agents.

It’s bitter lesson adjacent: Writing and executing code will likely outperform years of handcrafting vertical-specific agents with expert knowledge.

Actually it might exactly map in bitter lesson: Program synthesis is a form of scalable search.

[Levi Lelis @levilelis]

@SakanaAILabs We also studied how to make the self-play process more computationally efficient and how to speed up search using LLM-constructed program libraries.

If useful, here is a good entry point:
https://t.co/j45QkYOwKO

Happy to chat privately!

[Levi Lelis @levilelis]

Interesting work!

We observed similar behavior in our work on programmatic strategies applied to an RTS game. In particular, training an agent to defeat all previous versions of itself is an implementation of fictitious play, which we found leads to more robust programs than iterated best response (which only plays with the latest version of the agent).

[Marlos C. Machado @MarlosCMachado]

The Department of Computing Science at the University of Alberta at the University of Alberta has an opening for another tenure-track faculty in robotics. Please, spread the word.

I can attest to how awesome @UAlbertaCS and @AmiiThinks are!

(Official job posting coming soon.)

[Levi Lelis @levilelis]

@risi1979 @MelMitchell1 Congratulations, Sebastian, I’m looking forward to reading it!

[Levi Lelis @levilelis]

@lucasvegi Parabéns Lucas!

[Cohere Labs @Cohere_Labs]

Join our Reinforcement Learning Group next week on Monday, September 29th for a session with Esraa Elelimy on "Deep Reinforcement Learning with Gradient Eligibility Traces."

Thanks to @rahul_narava for organizing this event ✨

Learn more: https://t.co/RR9nRvYI1r

[matt @MattVMacfarlane]

Happy to share that Searching Latent Program Spaces has been accepted as a Spotlight at #NeurIPS2025 ✨

It's been a pleasure to work with @ClementBonnet16 on this!

See you all in San Diego 🌴 👋,

https://t.co/lnIQvRbzyK

[Alona Fyshe (she/her) @alonamarie]

I am hiring a post doc at @UAlberta , affiliated with @AmiiThinks ! We study language processing in the brain using LLMs and neuroimaging. Looking for someone with experience with ideally both neuroimaging and LLMs, or a willingness to learn. Email me Qs
https://t.co/kYcuUfTfZT

[Richard Sutton @RichardSSutton]

My acceptance speech at the Turing award ceremony:

Good evening ladies and gentlemen.
The main idea of reinforcement learning is that a machine might discover what to do on its own, without being told, from its own experience, by trial and error. As far as I know, the first person to propose this was Alan Turing in 1947, which makes it particularly gratifying and humbling to receive this award in his name for reviving this essential but still nascent idea.
I have three people that I would like to particularly thank.
First, Andy Barto. As my PhD supervisor he taught me my whole approach to science, and in particular instilled in me an appreciation of scholarship and craft, and of the great breath of prior work.
Second, I would like to thank Oliver Selfridge, my other main mentor; sadly, now deceased. Oliver taught me how keeping ideas simple can be the boldest of all ambitions.
Third, I want to thank Martha Steenstrup, my life partner and intellectual sparring partner. She keeps me honest and grounded.
Finally, I also want to thank the University of Alberta, which has been an ideal environment for me and for reinforcement learning research these past 22 years.
These three people and my university have reinforced in me the ambition to have ideas that matter, without getting too full of myself about it. They taught me that the quest for better ideas is serious, but is best approached playfully, with humility, kindness, and optimism. For this I am eternally grateful.
I would also like to thank all of you for being here and for celebrating the pursuit of intellectual excellence.
Thank you very much.

[Levi Lelis @levilelis]

Rina’s work has inspired me since my early days as a PhD student. I’m so happy to see her receive this very well-deserved award. Congratulations, Rina!

[IJCAIconf @IJCAIconf]

#IJCAI2025 What inspires her research? Rina Dechter, 2025 IJCAI Research Excellence Award recipient, takes us on a journey in her #Invited talk: Graphical Models Meet Heuristic Search: A Personal Journey into Automated Reasoning
📆 22 August, 2 PM
🌐 https://t.co/Edx4Ig2AcU

[Subbarao Kambhampati (కంభంపాటి సుబ్బారావు) @rao2z]

@DimitrisPapail Test Time Compute was "invented" the same way America was "discovered"..

https://t.co/a2KGDXrJKH