Matteo Pinna @nennomp

Incoming ELLIS PhD @ Hochreiter’s lab | Formerly CIML @Unipisa nennomp.github.io Pisa, Italy Joined November 2018

Tweets

61
Followers

80
Following

55
Likes

4K

Matteo Pinna @nennomp

3 days ago

@MasonNaka I don't think (1) would help. Unfortunately, there are reviewers that simply do not care about rebuttals, because there is no accountability. I agree on (2) and (3).

0 0 2 256 0

View Details

@thegautamkamath I can't stop thinking about what this means for PIs with very large, talented labs. A limit like this would force them into a difficult position: deciding which of their students' papers get submitted.

1 0 0 67 0

View Details

Matteo Pinna @nennomp

5 days ago

@mabdelhack @thegautamkamath Nope. The second point means that the student won't be able to submit two papers if in both of them none the authors have previously published at major ML conferences. The student can easily circumvent this by having at least one senior co-author (e.g., his/her advisor).

1 0 2 15 0

View Details

Matteo Pinna @nennomp

a month ago

@matteo_achilli Non sapevo che chiedere tre colori fosse una domanda a trabocchetto. Chiedo venia.

0 1 5 285 1

View Details

ELLIS @ELLISforEurope

2 months ago

🎓 We're thrilled to welcome 121 new PhD students to the ELLIS network from our 2025/2026 call — selected from a record-breaking 2,100+ submitted applications, a 43% increase from last year. 👉 Read the full article for more details: bit.ly/4upytcp

1 10 55 5K 23

View Details

Matteo Pinna @nennomp

2 months ago

@Guy_T_Sky @furongh Right, wasn't thinking about that.

0 0 0 13 0

View Details

Matteo Pinna @nennomp

2 months ago

@Guy_T_Sky @furongh Have the same question. The approach is also more (memory-) efficient so, unless I missed something, it cannot be due to compute, no?

1 0 1 25 0

View Details

Matteo Pinna @nennomp

2 months ago

@TaimingLu Cool insights. Do you have any intuition on why the very-strong teacher setting underperforms with respect to the strong teacher one?

0 0 0 477 1

View Details

Andrew Gordon Wilson @andrewgwils

3 months ago

This is your annual reminder that we don’t need to speculate about whether we will have a “theory of deep learning” and what form it might take, because we already have a basic understanding of generalization in deep learning: arxiv.org/abs/2503.02113

5 87 782 73K 967

View Details

Matteo Pinna @nennomp

3 months ago

Great initiative. Hopefully this becomes the norm and many more conferences adopt something similar.

ICML Conference @icmlconf

3 months ago

Reviewers & ACs for #ICML2026 have been recognized for their service! - Reviewers: 4439 Gold (free registration), 4437 Silver. 17749 total reviewers were assigned >= 1 paper - ACs: 1647 receive free registration, out of 1691 who were assigned >= 1 paper TY for your hard work!

8 16 297 45K 25

0 0 0 51 0

View Details

Matteo Pinna @nennomp

3 months ago

@DJiafei Besides, most of the time, AI generated figures look very ugly, no? Also, the first figure of the paper is hands down the most important one.

0 0 3 566 0

View Details

Konstantin Dobler @konstantdobler

3 months ago

A plot of ICLR papers by country is making the rounds, showing no EU + Japan papers and people are drawing all kinds of conclusions. ..but the plot excludes all (!) EU institutions due to a cutoff. China + USA still dominant of course but the full picture looks a bit different.

ℏεsam @Hesamation

3 months ago

someone analyzed all 5000+ accepted papers at ICLR 2026, and it's a good signal who's pushing the research of AI: > China has surpassed the US with 43.7% of the papers > Europe's contribution is surprisingly small (5.3% including UK)

78 371 2K 924K 878

7 61 330 67K 133

View Details

Claudio Gallicchio @claudiogallicc1

3 months ago

🚀 Reservoir Computing is officially back in the Deep Learning game! Thrilled to announce our paper "ParalESN" has been accepted at #ICML2026! 🎉 We resurrected RC for the DL era, finally unlocking parallel processing via associative scan. Preprint: arxiv.org/pdf/2601.22296🧵👇

3 4 9 467 6

View Details

Matteo Pinna @nennomp

3 months ago

@mhrezaeics AI-assisted research does not only generate slop, it also makes good labs more productive (i.e., higher number of good submissions). I would also wait a couple more cycles before judging the acceptance rate trajectory.

0 0 0 63 0

View Details

Matteo Pinna @nennomp

3 months ago

@jgh0sh @ryancjulian Maybe patents? Or, if the idea is exceptional, you go for the startup route. I guess OSS is another option as well.

0 0 1 80 0

View Details

Matteo Pinna @nennomp

3 months ago

@jgh0sh @ryancjulian Imho, good taste means you get published and cited a lot, while personal preference doesn't guarantee the above.

2 0 0 134 0

View Details

Matteo Pinna @nennomp

4 months ago

@shaohua0116 In some cases there may be some fundamental limitation in the paper that does not warrant a higher score. Fine with that, but I would prefer them being explicit about it or tell me exactly what needs to be addressed in order for them to adjust the score.

0 0 0 460 0

View Details

William Merrill @lambdaviking

5 months ago

[1/8] New paper with Hongjian Jiang, @YanhongLi2062, Anthony Lin, @Ashish_S_AI: 📜Why Are Linear RNNs More Parallelizable? We identify expressivity differences between linear/nonlinear RNNs and, conversely, barriers to parallelizing nonlinear RNNs 🧵👇