iiinova — where your digital self keeps evolving

Maxime Daigle

@maximemdaigle.bsky.social

220 followers 638 following 1 posts

Ph.D. Student Mila / McGill. Machine learning and Neuroscience, Memory and Hippocampus

Posts Replies Media

Reposted by Maxime Daigle

Herbie(Zizhan) He @herbiehe.bsky.social · 18/03/2026

New paper 🚨 #ICLR26 Most world models predict the future from a past trajectory. But neuroscience suggests that such inference can instead be made from temporally independent experiences. We built the Episodic Spatial World Model (ESWM), a model that does exactly this: Video abstract [1/2]

183

Reposted by Maxime Daigle

Spencer LaVere Smith @spencerlaveresmith.bsky.social · 10/07/2025

Mice learn these tasks and are robust to perturbations like fog. Now, we invite you all to make AI agents to beat mice. We present our #NeurIPS competition. You can learn about it here: robustforaging.github.io (7/n)

A summary figure for a NeurIPS competition where AI agents compete with mice in a visual foraging task.

14410

Maxime Daigle @maximemdaigle.bsky.social · 26/06/2025

Looks fantastic! Exciting that our results seem to converge. We found something similar: from sparse episodic memories, in-context learning in transformer can build spatial maps that adapt on the fly to environmental changes. Here's our take on this: arxiv.org/abs/2505.13696 Would love to discuss!

arxiv.org

Building spatial world models from sparse transitional episodic memories

Many animals possess a remarkable capacity to rapidly construct flexible mental models of their environments. These world models are crucial for ethologically relevant behaviors such as navigation, ex...

340