Riccardo Zaccone @ NeurIPS

26 posts

Riccardo Zaccone @ NeurIPS

Riccardo Zaccone @ NeurIPS

@RickZack96

Visiting PhD student @ MBZUAI | PhD student in Decentralized Learning @PoliTONews | Alumno IEEE-HKN @HKNPoliTo

Turin, Italy เข้าร่วม Ağustos 2022
67 กำลังติดตาม63 ผู้ติดตาม
ทวีตที่ปักหมุด
Riccardo Zaccone @ NeurIPS
Riccardo Zaccone @ NeurIPS@RickZack96·
🚀 Excited to be at #NeurIPS2025 this week! I’ll be presenting our work on distributed and federated optimization. You'll find me on 6th Dec: - OPT for ML: 20A 10-11 am - Reliable ML: 2, 1:30 2:15 pm If you're working on learning at scale, come find me at — happy to chat 🤝
English
0
2
8
475
Riccardo Zaccone @ NeurIPS
Riccardo Zaccone @ NeurIPS@RickZack96·
@niclane7 @KairouzPeter @gingsmith @konstmish @aaron_defazio @MatharyCharles @Ar_Douillard @sam_hrvth @_arohan_ @samsja19 I'll be presenting both works at NeurIPS, happy to meet and talk more about it if you're around. x.com/RickZack96/sta…
Riccardo Zaccone @ NeurIPS@RickZack96

🚀 Excited to be at #NeurIPS2025 this week! I’ll be presenting our work on distributed and federated optimization. You'll find me on 6th Dec: - OPT for ML: 20A 10-11 am - Reliable ML: 2, 1:30 2:15 pm If you're working on learning at scale, come find me at — happy to chat 🤝

English
0
0
0
112
Riccardo Zaccone @ NeurIPS
Riccardo Zaccone @ NeurIPS@RickZack96·
Do you feel FL research is stuck with methods that do not work well in realistic scenarios? 🤔 🫵We got you! Introducing 🚀Generalized Heavy-Ball Momentum (GHBM)🚀, accepted at TMLR: the FL algorithm with both SOTA theoretical guarantees and much better empirical results. 🧵1/9
Riccardo Zaccone @ NeurIPS tweet media
English
1
6
20
4.1K
Riccardo Zaccone @ NeurIPS รีทวีตแล้ว
Gabriele Trivigno
Gabriele Trivigno@gabTrivv·
🔥 Our paper SANSA is a #NeurIPS2025 Spotlight! We turn #SAM2 into a semantic few-shot segmenter for objects and parts, fully promptable (mask · point · box · scribble); only 10M trainable parameters and 5× faster than competitors. Code, models & demo github.com/ClaudiaCuttano… 👇
English
1
10
22
1.7K
Zachary Charles
Zachary Charles@MatharyCharles·
I'm hiring an intern for our distributed optimization team in Google Research, based in Seattle. If you're interested and have relevant experience in DiLoCo-style things, please apply or let me know you've applied. google.com/about/careers/…
English
13
18
213
24.6K
Riccardo Zaccone @ NeurIPS
Riccardo Zaccone @ NeurIPS@RickZack96·
@AtaeiMe @SametOymac That should be classified as irresponsible reviewing, and it should be easy to prove that mentioned papers were allucinated, as well as published after the submission deadline. Just for curiosity, what is the comment for the "1" score?
English
1
0
0
180
Mehdi Ataei
Mehdi Ataei@AtaeiMe·
@SametOymac My scores went down from 4.25 to 3.25 because one reviewer was asking comparison to two non-existent hallucinated papers, and one asking to compare to one paper that was published late June. I wholeheartedly thank the reviewers for their engagement.
English
3
0
3
3.9K
Samet Oymak
Samet Oymak@SametOymac·
NeurIPS scores before→after rebuttal (my batch of 100 papers): - ≥5.00: 1 → 2 papers - ≥4.50: 6 → 9 papers - ≥4.25: ? → 21 papers - ≥4.00: 11 → 33 papers - ≥3.75: 25 → 45 papers - ≥3.50: 42 → 60 papers Big thanks to the reviewers for listening and engaging 🙂
English
9
2
160
30.4K
Riccardo Zaccone @ NeurIPS
Riccardo Zaccone @ NeurIPS@RickZack96·
@mciccone_AI The only safe choice is to take it in the cabin with you, but it costs an additional ticket... I've done it before for national flights in Italy, not a cheap option though
English
0
0
0
60

ค้นพบ

@niclane7 @KairouzPeter @gingsmith @konstmish @aaron_defazio @MatharyCharles @Ar_Douillard @sam_hrvth