activity
20192026
most citedReinforcement Learning through Active Inference

58 citations · 116 across the 36 of their papers we have counts for

collaborators
Showing cs.LGShow all

13 papers · 1 filter

cs.LG2026

ZUNA1.1: A more flexible EEG foundation model for Denoising and Super-resolution

Christopher Warner, Jonas Mago, JR Huml +1

We introduce ZUNA1.1, a 380M-parameter diffusion autoencoder for flexible EEG signal reconstruction. ZUNA1.1 is capable of reconstructing variable length sequences of up to 30s, wi…

cs.LG2026

Scaling Adaptive Depth with Norm-Agnostic Residual Networks

Tomás Figliolia, Beren Millidge

Residual architectures are ubiquitous in deep learning, but they suffer from a subtle structural limitation: the norm of the residual stream can grow rapidly with depth. As a resul…

cs.LG2026

Hybrid Associative Memories

Leon Lufkin, Tomás Figliolia, Beren Millidge +1

Recurrent neural networks (RNNs) and self-attention are both widely used sequence-mixing layers that maintain an internal memory. However, this memory is constructed using two orth…

cs.LG2025

Generalising E-prop to Deep Networks

Beren Millidge

Recurrent networks are typically trained with backpropagation through time (BPTT). However, BPTT requires storing the history of all states in the network and then replaying them s…

cs.LG20241 cited

The Zamba2 Suite: Technical Report

Paolo Glorioso, Quentin Anthony, Yury Tokpanov +5

In this technical report, we present the Zamba2 series -- a suite of 1.2B, 2.7B, and 7.4B parameter hybrid Mamba2-transformer models that achieve state of the art performance again…

cs.LG20225 cited

Interpreting Neural Networks through the Polytope Lens

Sid Black, Lee Sharkey, Leo Grinsztajn +8

Mechanistic interpretability aims to explain what a neural network has learned at a nuts-and-bolts level. What are the fundamental primitives of neural network representations? Pre…