Alessandro Betti

[Matteo Tiezzi @TiezziMatteo]

#LOT Spring school

@biggiobattista presenting the lecture "Machine Learning Security: Lessons Learned and Future Challenges"

@Cossu94 @v_lomonaco @StefanoMelacci @aleitteb

[Matteo Tiezzi @TiezziMatteo]

🚀 Learning Over Time (LOT) Spring School 📅 24-27 March 2025 | 📍 Siena, Italy
🔗https://t.co/9FYi3vZAgR

Organizers: @StefanoMelacci ,@v_lomonaco @Cossu94 ,@aleitteb @TiezziMatteo

#ContinualLearning #CL #LifelongLearning #CollectionlessAI

[Stefano Melacci @StefanoMelacci]

🚀 We’ve launched a new site for Collectionless AI, sharing our take on next-gen AI/ML! 🚀 Explore our papers, events, and more!

https://t.co/WJQxqlj25t

#CollectionlessAI #ContinualLearning #LifelongLearning #MachineLearning #AI 🌐

@StefanoMelacci @KleineBottleM @TiezziMatteo

[CoLLAs 2026 @CoLLAs_Conf]

#CoLLas2024 folks 🐨
Temperature rising for the coming sessions 🔥🐨

[Matteo Tiezzi @TiezziMatteo]

Hurry up for @CoLLAs_Conf registration!

[Matteo Tiezzi @TiezziMatteo]

📢 "State-space Modeling in Long Sequence Processing: A Survey on Recurrence in the Transformer Era"
https://t.co/VaUfp3LZnl

a joint work by @TiezziMatteo , M. Casoni, @aleitteb , M.Gori (@KleineBottleM) and @StefanoMelacci

[Matteo Tiezzi @TiezziMatteo]

We also summarized the most common #benchmarks and settings for long sequence processing and #longrange dependencies https://t.co/VaUfp3LZnl

[Matteo Tiezzi @TiezziMatteo]

3⃣ RNNs evolutions, such as xLSTMs (@gklambauer), ODE-inspired RNNs (Neural Oscillators - @tk_rusch)
as well as novel paths for
4⃣ Learning in RNNs, such as modern evolutions of RTRL (@KhurramJaved_96) or bio-inspired methods (@BerenMillidge)
https://t.co/VaUfp3LZnl

[Matteo Tiezzi @TiezziMatteo]

2️⃣ Deep State-space Models #SSMs such as #S4, #S5, #Mamba, #Griffin etc.
a line of work by @_albertgu @tri_dao @SamuelMLSmith, @orvieto_antonio and many others

https://t.co/VaUfp3LZnl

[Matteo Tiezzi @TiezziMatteo]

We described several trends:
1️⃣ #Transformers embraced Recurrence exploiting a stateful recurrent representation:
*️⃣ all the latest models RWKV4/5/6 by @BlinkDL_AI
*️⃣ #RetNet by @donglixp et al.
are competitive with quadratic self-attention!

https://t.co/VaUfp3LZnl

[Matteo Tiezzi @TiezziMatteo]

Goal: efficiently 𝐩𝐫𝐨𝐜𝐞𝐬𝐬 𝐥𝐨𝐧𝐠 𝐬𝐞𝐪𝐮𝐞𝐧𝐜𝐞𝐬 + 𝐩𝐫𝐞𝐬𝐞𝐫𝐯𝐞 𝐥𝐨𝐧𝐠 𝐭𝐞𝐫𝐦 𝐝𝐞𝐩𝐞𝐧𝐝𝐞𝐧𝐜𝐢𝐞𝐬
TL;DR #Transformers + #RNNs, #DeepStatespace models ➡️ progressive confluence of previously disjoint architectures

https://t.co/VaUfp3LZnl

[Matteo Tiezzi @TiezziMatteo]

🧐Interested in the details of the latest SOTA architectures (#RWKV , #RetNet, #Mamba, #Griffin) for long sequences?

📢 "State-space Modeling in Long Sequence Processing: A Survey on Recurrence in the Transformer Era" https://t.co/VaUfp3LZnl

[Matteo Tiezzi @TiezziMatteo]

📢Jay McClelland, co-author of the seminal 'Parallel Distributed Processing' book 📚, is set to be our keynote speaker at #CoLLas2024! 🎉

[Matteo Tiezzi @TiezziMatteo]

‼️Short survey paper‼️

📢"On the Resurgence of Recurrent Models for Long Sequences: Survey and Research Opportunities in the Transformer Era"

by @TiezziMatteo M.Casoni @aleitteb @_masaccio_ @KleineBottleM @StefanoMelacci

#Transformers #SSMs

https://t.co/KYLdy4TXNR

[CoLLAs 2026 @CoLLAs_Conf]

🚨1 month left until the #CoLLAs2024 paper submission deadline!🚨

Don’t miss your opportunity to contribute to the field of lifelong learning. Finalize your research and submit by 15 Feb 2024!

📄 Prepare your submission: https://t.co/xLC1mbEJrS
🗓️ Abstract deadline: 09 Feb 2024

[Richard Sutton @RichardSSutton]

It is sad to lose the DeepMind office in Edmonton to the Tech layoffs and looming recession. But AI is not going away, and I am more focused than ever on the Alberta Plan for AI research.
https://t.co/DQBl7vmGaO

[Matteo Tiezzi @TiezziMatteo]

📣 Last week I presented "Foveated Neural Computation" @ECMLPKDD
➡️ Paper: https://t.co/3cOHoXxLzR
➡️ Code: https://t.co/qxL3EEnOBC

A thread👇🧵
In some visual tasks, such as image classification, salient information is distributed in regions of limited size 🧐
1/n

[Dario Zanca @dariozanca]

(8/n) @TiezziMatteo, @MarulloSimone, Lapo Faggi, @enricomeloni_ai, @aleitteb and @StefanoMelacci investigated the effectiveness of gravitational models in an open-set class-incremental setting, by imposing stochastic coherence along the visual scanpath. https://t.co/A39BPXgHBT

[Dario Bressanini @DarioBressanini]

Mi raccomando, durante gli incontri parentali delle feste, oltre a stare attenti, non appena lo zio dice “siero speri..” siate saggi 😁

[Alessandro Betti @aleitteb]

My Secret Vault is a CHEF'S DREAM https://t.co/tebtXcBSOa via @YouTube