565 citations · 663 across the 57 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
The Independence Prior of SAEs Fragments Visual Concepts
Tommaso Mencattini, Giorgos Nikolaou, Donato Crisostomi +4
Sparse Autoencoders (SAEs) decompose model activations into sparse combinations of interpretable dictionary atoms. Although SAEs are grounded in the Linear Representation Hypothesi…
cs.AI2026
Subliminal Clocks: Latent Time Modelling in Diffusion Language Models
Maximo Eduardo Rulli, Thomas Vaitses Fontanari, Simone Petruzzi +9
Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive models. Unlike standard diffusion-based approaches, DLMs are not explicitly cond…