Matteo Tiezzi
@TiezziMatteo
Followers
292
Following
523
Media
85
Statuses
259
PostDoctoral Researcher @Pavis_iit @IITalk | Continual/Lifelong Learning and Graph Representation Learning | @CoLLAs_conf Local Chair
Genova, Italy
Joined May 2020
🧐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"
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...
1
8
11
A great thread that showcases the main intuitions behind our #FovEx paper. Paper: 🔗 .Technical Report: 🔗 Github: 📷
github.com
Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks - mahadev1995/FovEx
Can we explain AI's decisions in a way that's as intuitive as human vision?. This is the core question addressed in our recently paper, "FovEx: Human-inspired Explanations for Vision Transformers and Convolutional Neural Networks," published in #IJCV by @SpringerNature . (1/N)
0
1
2
🚨 Our #survey "Back to recurrent processing at the crossroad of #transformers and state-space models" is out in Nature Machine Intelligence!. 🔗 Read it here: @StefanoMelacci @KleineBottleM (M. Gori).
nature.com
Nature Machine Intelligence - While transformers and large language models excel at efficiently processing long sequences, new approaches have been proposed that incorporate recurrence to overcome...
0
0
2
RT @riccardograzzi: @julien_siems @leloykun @jyo_pari In our DeltaProduct work we also add a bit of theory to DeltaNet, showing that it can….
0
5
0
RT @julien_siems: 1/9 There is a fundamental tradeoff between parallelizability and expressivity of Large Language Models. We propose a new….
0
34
0
#LOT startup day with @Continual_IST (@v_lomonaco), Motus ML (@GiacomoZiffer ) and @FocoosAI (@fcdl94). @Cossu94.@StefanoMelacci @aleitteb
0
0
3
#LOT very interesting interactive lecture by @claudiogallicc1 ."Reservoir Computing Methods for Time Series Classification".@Cossu94.@v_lomonaco @StefanoMelacci
0
1
2
#LOT Spring School.@eliricci_ on "Beyond Zero-Shot Generalization: Strengthening Vision-Language Models with Adaptation & Personalization". @StefanoMelacci @v_lomonaco @Cossu94
0
1
5
#LOT Spring school . @biggiobattista presenting the lecture "Machine Learning Security: Lessons Learned and Future Challenges". @Cossu94 @v_lomonaco @StefanoMelacci @aleitteb
0
2
2
#LOT Spring school .Extremely honoured to introduce the second talk of the day, by the great @orvieto_antonio, on "New Avenues in Long-Sequence Processing without Attention". @StefanoMelacci @Cossu94 @v_lomonaco @aleitteb
0
0
2
#LOT spring school .we continue our incredible lineup of speakers with Alexei Efros and the talk titled "Test-Time Training: Toward a Post-Dataset World",. @StefanoMelacci @Cossu94 @v_lomonaco @aleitteb.
0
1
2
RT @Cossu94: Art, nature and Artificial Intelligence at LoT Spring school which just started. With 50+ students, we are fully booked and ea….
0
3
0
The first edition of Learning Over Time (LOT) Spring School is starting!.@StefanoMelacci kicking off the school at the wonderful Certosa di Pontignano, Italy.Organized by @StefanoMelacci, @v_lomonaco , @Cossu94 , @aleitteb , and myself .
0
1
6
RT @Fede_Becat: Working in #Multimedia, #ComputerVision, #AI? The Deadline for #ACMMM2025 is approaching fast! Don't forget to follow the n….
x.com
The world's premier conference dedicated to advancing research and applications across diverse #multimedia fields.
0
4
0
RT @apsarathchandar: If you want to achieve AGI, you need to solve continual learning! @CoLLAs_Conf is the premier venue for continual lear….
0
4
0
RT @SonglinYang4: 🚀 Announcing ASAP: . A fully virtual seminar bridging theory, algorithms, and systems to tackle f….
0
55
0
RT @behrouz_ali: Attention has been the key component for most advances in LLMs, but it can’t scale to long context. Does this mean we need….
0
600
0
🚀 Learning Over Time (LOT) Spring School 📅 24-27 March 2025 | 📍 Siena, Italy.🔗 Organizers: @StefanoMelacci ,@v_lomonaco @Cossu94 ,@aleitteb @TiezziMatteo . #ContinualLearning #CL #LifelongLearning #CollectionlessAI
0
3
2
😸 Join the LOT Spring School with an incredible speaker lineup: @biggiobattista , @NicoloCB, @eliricci_, @orvieto_antonio , @KleineBottleM , Tinne Tuytelaars. 🔗 🔗 Pre-registrations are now open, secure your spot today:
sites.google.com
PRE-REGISTRATION IS REQUIRED! Fill the form at the bottom of the page to pre-register now! Payment procedures will be activated in january 2025.
1
0
0
🚀 Learning Over Time (LOT) Spring School.📅 24-27 March 2025 | 📍 Siena, Italy. 💡 Are you considering models that continuously adapt over time instead of learning "offline" from pre-designed-huge collections of data? 🚀. 🔗
sites.google.com
Inspired by Collectionless AI https://cai.diism.unisi.it/
1
1
4
RT @PAVIS_IIT: PAVIS and former members celebrating the coming holidays and a year full of successes! Well done people, you are an amazin….
0
4
0