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]
🤖 + 👁️ -> 🧠 = 🥀 but 🤖 + 👁️ -> ✍️ -> 🧠 = 🌹
... = spotlight NeurIPS paper :)
Come say hi at our poster this week <3
#NeurIPS2025
I couldn't find anything online showing how to use the new FlexAttention methods from torch>=2.5 to handle causal attention masking of padded inputs.
So I made a tutorial...
github.com/lucasmgomez/...
medium.com/@lucasmgomez...
🌟 New Research Alert! 🌟
Excited to share our latest work (accepted to NeurIPS2024) on understanding working memory in multi-task RNN models using naturalistic stimuli!: with @takuito.bsky.social and @bashivan.bsky.social
#tweeprint below:
1/ I work in #NeuroAI, a growing field of research, which many people have only the haziest conception of...
As way of introduction to this research approach, I'll provide here a very short thread outlining the definition of the field I gave recently at our BRAIN NeuroAI workshop at the NIH.
🧠📈
