Post

I’ll be at #ICML2026 in Seoul all week. If you’re interested in the intersection of cognitive science, mechanistic interpretability, and philosophy -- let’s chat! DMs are open. Check my website for more on what I work on (raphaelmilliere.com), or see below.

Raphaël Millière

@raphaelmilliere.com

I'm broadly interested in the cognitive interpretability of DNNs, see variablescope.org for a good example from last ICML. Some things I'll be discussing at this ICML: Main conf: arxiv.org/abs/2602.20159 Two workshop talks: sites.google.com/view/philmli...

variablescope.orgVariable Scope - ICML 2025Companion website to ICML 2025 paper on how Transformers learn variable binding

4/7/26, 3:06 pm0 reposts5 likes

No replies yet.