Levi Lelis
@levilelis
Artificial Intelligence Researcher - Associate Professor - University of Alberta - Canada CIFAR AI Chair (he/him, ele/dele).
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. youtu.be/UNpg05yxc3o?si…
Are programmatic policies really better at generalizing OOD than neural policies, or are the benchmarks biased? This position paper revisits 4 prior studies and finds neural policies can match programmatic ones - if you adjust training (sparse observation, reward shaping, etc.)
👉 We are hiring!! How will AI agents interact with you, learn from you and empower you in the future? Reward signals will not always be clearly defined… Breakthroughs are needed in multi turn RL, self-evaluation and self-improvement - if you are excited by this, join us! 👇
Do you have a PhD (or equivalent) or will have one in the coming months (i.e. 2-3 months away from graduating)? Do you want to help build open-ended agents that help humans do humans things better, rather than replace them? We're hiring 1-2 Research Scientists! Check the 🧵👇
Sparsity can also be used to partially explain some of the successes of programmatic representations, such as FlashFill. DSLs and the way we search over the space of programs naturally give us sparse representations, which favor sample efficiency and OOD generalization.
After studying the mathematics and computation of Sparsity for nearly 20 years, I have just realized that it is much more important than I ever realized before. It truly serves as *the* model problem to understand deep networks and even intelligence to a large extent, from a…
Attending #ICML2025 and interested in programmatic representations in ML? This workshop is for you. :-)
Our #ICML2025 Programmatic Representations for Agent Learning workshop will take place tomorrow, July 18th, at the West Meeting Room 301-305, exploring how programmatic representations can make agent learning more interpretable, generalizable, efficient, and safe! Come join us!
Catch Jake at #ICML2025! He’s presenting “Subgoal-Guided Heuristic Search with Learned Subgoals” in Poster Session 2 West — tomorrow, 4:30–7:00 pm. arxiv.org/abs/2506.07255
🛬 Vancouver for #icml, I’ll be presenting our work on Subgoal Guided Heuristic Search with Learned Subgoals on Tuesday from 4:30-7:00pm. Come stop by and say hello 👋
🛬 Vancouver for #icml, I’ll be presenting our work on Subgoal Guided Heuristic Search with Learned Subgoals on Tuesday from 4:30-7:00pm. Come stop by and say hello 👋
Conferences should welcome refutations and critiques in their main track. Unfortunately, they often don't. We had a critique accepted once to a leading conference, but all three reviewers recommended rejection—thank you, AC! A special track for this type of work is a good start.
New position paper! Machine Learning Conferences Should Establish a “Refutations and Critiques” Track Joint w/ @sanmikoyejo @JoshuaK92829 @yegordb @bremen79 @koustuvsinha @in4dmatics @JesseDodge @suchenzang @BrandoHablando @MGerstgrasser @is_h_a @ObbadElyas 1/6
Some great work from @AmirhoseinRj and @levilelis on neural policies vs programmatic policies for OOD generalization. I'm looking forward to discussing such topics further at the Workshop on Programmatic Representations for Agent Learning @icmlconf, which Levi is co-organising.
Previous work has shown that programmatic policies—computer programs written in a domain-specific language—generalize to out-of-distribution problems more easily than neural policies. Is this really the case? 🧵
Passionate about frontier AI models, classical symbolic reasoning, and safe/secure software? Consider applying for this position on AI-aided code analysis in my team at @GoogleDeepmind: job-boards.greenhouse.io/deepmind/jobs/…. The job is London-based, and the application deadline is July 14.
This was a great long-term effort from @MartinKlissarov, @akhil_bagaria, and @RayZiyan41307, and it led to a great overview of the ideas behind leveraging temporal abstractions in AI. If anything, I think this is very useful resource for anyone interested in this field!
As AI agents face increasingly long and complex tasks, decomposing them into subtasks becomes increasingly appealing. But how do we discover such temporal structure? Hierarchical RL provides a natural formalism-yet many questions remain open. Here's our overview of the field🧵