iiinova — where your digital self keeps evolving

Riccardo Grazzi

@riccardograzzi.bsky.social

39 followers 261 following 4 posts

Post Doc at IIT in Genoa, working on Optimization for Machine Learning and on the expressivity of LLMs

Posts Replies Media

Riccardo Grazzi @riccardograzzi.bsky.social · 28/03/2025

I also think that the analysis might be further enhanced thanks to the very nice results in the RWKV-7 paper!

000

Riccardo Grazzi @riccardograzzi.bsky.social · 28/03/2025

In our DeltaProduct work we also add a bit of theory to DeltaNet, showing that it can solve Dihedral groups, which are the groups of symmetries of regular polygons, with only two layers. This includes S3 (symmetries of the equilateral triangle).

100

Riccardo Grazzi @riccardograzzi.bsky.social · 09/01/2025

I just had the pleasure of presenting "Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues" at the AutoML Seminars. I also presented some proof sketches :) Here's the recording: t.co/B3TQozvGKX

t.co

https://youtube.com/watch?v=E2qBhMmjspU

030

Riccardo Grazzi @riccardograzzi.bsky.social · 10/12/2024

Excited to present "Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues" at the M3L workshop at #NeurIPS buff.ly/3BlcD4y If interested, you can attend the presentation the 14th at 15:00, pass at the afternoon poster session, or DM me to discuss :)

buff.ly

Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues

Linear Recurrent Neural Networks (LRNNs) such as Mamba, RWKV, GLA, mLSTM, and DeltaNet have emerged as efficient alternatives to Transformers in large language modeling, offering linear scaling with…

093

Reposted by Riccardo Grazzi

CSML IIT Lab @pontilgroup.bsky.social · 10/12/2024

At #NeurIPS2024 🇨🇦 our group will present 7 contributions! These span a diverse array of topics: from theoretical advances in stochastic processes and reinforcement learning to applications in molecular dynamics and uncertainty quantification.

162