Stefano Melacci
@StefanoMelacci
Followers
44
Following
22
Media
1
Statuses
23
RT @TiezziMatteo: The first edition of Learning Over Time (LOT) Spring School is starting!.@StefanoMelacci kicking off the school at the woโฆ.
0
1
0
RT @TiezziMatteo: ๐ Learning Over Time (LOT) Spring School ๐
24-27 March 2025 | ๐ Siena, Italy.๐ Organizers: @Stefaโฆ.
0
3
0
The call for two post-doc positions in #CollectionlessAI is open (University of Siena, Italy)! Have a look at the link in this post ๐. #CollectionlessAI #ContinualLearning #LifelongLearning #MachineLearning #AI. @StefanoMelacci.@KleineBottleM.
cai.diism.unisi.it
Weโre offering two post-doc positions in the CONSTR project, fully oriented toward Collectionless AI topics.
3
1
2
๐ Weโve launched a new site for Collectionless AI, sharing our take on next-gen AI/ML! ๐ Explore our papers, events, and more!. #CollectionlessAI #ContinualLearning #LifelongLearning #MachineLearning #AI ๐. @StefanoMelacci @KleineBottleM @TiezziMatteo
0
2
3
0
2
0
RT @TiezziMatteo: #CoLLAs2024 I will present our novel architectural solution for Continual Learning, Memory Head, at the upcoming @CoLLAsโฆ.
0
10
0
RT @TiezziMatteo: ๐ข "State-space Modeling in Long Sequence Processing: A Survey on Recurrence in the Transformer Era" ..
arxiv.org
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have...
0
3
0
RT @TiezziMatteo: We also summarized the most common #benchmarks and settings for long sequence processing and #longrange dependencies httpโฆ.
0
2
0
RT @TiezziMatteo: 3โฃ RNNs evolutions, such as xLSTMs (@gklambauer), ODE-inspired RNNs (Neural Oscillators - @tk_rusch) .as well as novel pโฆ.
arxiv.org
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have...
0
2
0
RT @TiezziMatteo: We described several trends:.1๏ธโฃ #Transformers embraced Recurrence exploiting a stateful recurrent representation: .*๏ธโฃโฆ.
arxiv.org
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have...
0
2
0
RT @TiezziMatteo: We summarized the key ingredients underlying the current models generation:.*๏ธโฃ linear recurrence.*๏ธโฃ element-wise recurrโฆ.
0
1
0
RT @TiezziMatteo: Goal: efficiently ๐ฉ๐ซ๐จ๐๐๐ฌ๐ฌ ๐ฅ๐จ๐ง๐ ๐ฌ๐๐ช๐ฎ๐๐ง๐๐๐ฌ + ๐ฉ๐ซ๐๐ฌ๐๐ซ๐ฏ๐ ๐ฅ๐จ๐ง๐ ๐ญ๐๐ซ๐ฆ ๐๐๐ฉ๐๐ง๐๐๐ง๐๐ข๐๐ฌ .TL;DR #Transformers + #RNNs, #DeepStatespaceโฆ.
0
2
0
RT @TiezziMatteo: ๐งInterested in the details of the latest SOTA architectures (#RWKV , #RetNet, #Mamba, #Griffin) for long sequences? . ๐ข "โฆ.
arxiv.org
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers have...
0
8
0
RT @TiezziMatteo: โผ๏ธShort survey paperโผ๏ธ . ๐ข"On the Resurgence of Recurrent Models for Long Sequences: Survey and Research Opportunities iโฆ.
0
2
0
RT @CoLLAs_Conf: ๐จ1 month left until the #CoLLAs2024 paper submission deadline!๐จ. Donโt miss your opportunity to contribute to the field ofโฆ.
0
7
0
See you all in Pisa ๐ !!!!!! (July 2024).
The third international Conference on Lifelong Learning Agents (CoLLAs) will happen in Pisa, Italy from 29 July to 01 Aug 2024 (right after ICML in Europe!). Abstract deadline: 09 Feb 2024.Submission deadline: 15 Feb 2024.Full CFP:
0
0
1
RT @TiezziMatteo: ๐ฃ Last week I presented "Foveated Neural Computation" @ECMLPKDD.โก๏ธ Paper: โก๏ธ Code: https://t.co/โฆ.
0
3
0
RT @CiraGabriele: It's with enormous pleasure that I tell you that our last paper has been accepted for publication in the IEEE TPAMI, theโฆ.
0
5
0