This blog post was a wonderful read -- it is a rare and precious opportunity to understand the "latent reasoning process" underneath a beautiful idea :)

Heading to Vancouver for #ICML2025 to present our work: Temporal Difference Flows. Make sure to check out the oral to learn how we’re now able to scale this exciting world model framework based on the successor representation! Also, feel free to reach out to discuss anything RL!

Check out Nicolas Espinosa Dice's blog post on how we can enable test-time scaling of policies learned via offline RL! I am particularly impressed by the figures :).

Using OT to define rewards for imitating video demos is popular, but it breaks down when demos are temporally misaligned—a frequent challenge in practice. We present ORCA at #ICML2025 , which defines rewards by aligning sequences, rather than matching individual frames via OT.

This was crystal-clear without losing nuance — highly recommended!