Avery Ryoo

168 posts

Avery Ryoo banner
Avery Ryoo

Avery Ryoo

@averyryoo

phd @Mila_Quebec, prev. @UWaterloo i like generative models and toronto sports teams (not necessarily in that order) 🇨🇦🇰🇷

Montréal, Canada Katılım Kasım 2016
749 Takip Edilen260 Takipçiler
Sabitlenmiş Tweet
Avery Ryoo
Avery Ryoo@averyryoo·
Super stoked to share my first first-author paper that introduces a hybrid architecture approach for real-time neural decoding. It's been a lot of work, but happy to showcase some very cool results!
Nanda H Krishna@nandahkrishna

New preprint! 🧠🤖 How do we build neural decoders that are: ⚡️ fast enough for real-time use 🎯 accurate across diverse tasks 🌍 generalizable to new sessions, subjects, and species? We present POSSM, a hybrid SSM architecture that optimizes for all three of these axes! 🧵1/7

English
1
5
33
3.2K
Avery Ryoo retweetledi
Siva Reddy
Siva Reddy@sivareddyg·
Montreal deep tech scene is getting hot!! Many recent hires of Cohere, Mistral, Periodic Labs, Poolside are all based in Montreal. And now, AMI will have an office here 🔥 It's a no-brainer, though. @Mila_Quebec has the highest concentration of deep learning expertise with interdisciplinary connections. Thanks to recent US regulation changes on immigration, no more brain drain! Let's build more in Canada!
Yann LeCun@ylecun

Unveiling our new startup Advanced Machine Intelligence (AMI Labs). We just completed our seed round: $1.03B / 890M€, one the largest seeds ever, probably the largest for a European company. We're hiring! [the background image is the Veil Nebula - a picture I took from my backyard, most appropriate for an unveiling] More details here: techcrunch.com/2026/03/09/yan…

English
18
48
755
71.3K
Avery Ryoo retweetledi
Adam Aaronson
Adam Aaronson@aaaronson·
I made a crossword
Adam Aaronson tweet media
English
38
521
7.3K
145.2K
Avery Ryoo retweetledi
Jake Landau (He/Him) 🇨🇦🇵🇸🇻🇪🇺🇦
Jake Landau (He/Him) 🇨🇦🇵🇸🇻🇪🇺🇦@JakeLandauTO·
Hot Take: Canada should bid for the Summer Olympics with a joint Toronto-Montréal hosting arrangement, and then use this public event in order to create political pressure that will accelerate the completion of the high-speed rail project.
English
113
404
7.6K
164.9K
Avery Ryoo retweetledi
Johnny
Johnny@JohnnyGiunta_·
At 28 years of age I have simply learned that every singular sports moment in my life will be torturous hell win or lose
English
27
160
3.4K
68K
Avery Ryoo retweetledi
Damien Ferbach
Damien Ferbach@damien_ferbach·
1/10 We built ADANA, an optimizer that gets better as you scale. It extends AdamW with log-time schedules for momentum and weight decay — same hyperparameter count, no extra engineering. Scaled from 45M to 2.6B, it saves ~40% compute vs tuned AdamW, and the gap keeps growing.🧵
Damien Ferbach tweet media
English
3
37
184
31.8K
Avery Ryoo retweetledi
Emiliano Penaloza
Emiliano Penaloza@emilianopp_·
Remember all the self-distillation papers that came out last week. Well, we also propose it 😅, but… But alongside something better 😎 π-Distill We show that with this method, you can distill closed-source frontier models even tho their traces are hidden 🔒. Both our methods can reach and even surpass the performance of the industry-standard SFT + RL with access to reasoning traces 🤯. 🔬And we spent ~100,000 hours GPU hours on a comprehensive analysis, not because the method is finicky, but because we wanted to understand why it works so well. 🧵 1/10
English
11
78
428
45.2K
Avery Ryoo retweetledi
Yipeng Zhang
Yipeng Zhang@yipengzz·
How can we predict multiple plausible targets from a single context in joint-embedding self-supervised learning (SSL)? Check out our paper titled “Self-Supervised Learning from Structural Invariance” accepted at #ICLR2026! Previously Best Paper Award at @unireps 2025. arxiv.org/abs/2602.02381 We introduce AdaSSL, which models the target uncertainty and relaxes the standard assumption that the positive pair share the same semantic features. Derived from first principles, we realize @ylecun’s JEPA with a learned latent variable for jointly learning better representations and world models, extending SSL’s utility to a broader range of data types. 1/🧵
English
2
23
80
9.2K
Avery Ryoo retweetledi
oliver
oliver@travellingsoot·
still so crazy to me how park chan-wook's never been nominated for an oscar
oliver tweet mediaoliver tweet mediaoliver tweet mediaoliver tweet media
English
60
1.8K
17.6K
326.6K
Avery Ryoo retweetledi
Bryan Hayes
Bryan Hayes@HayesTSN·
Lots of Leafs/Jays/Bills fans in Southern Ontario that have to think they’re living in a simulation.
English
116
163
3.3K
162.7K
Avery Ryoo retweetledi
Vedant Shah
Vedant Shah@veds_12·
Hi @YouJiacheng. Thanks for going through our paper. Just to clarify, when we refer to "k3-in-loss" (or any estimator in loss) in the paper, we mean using it in the manner GRPO did, i.e. without the importance sampling correction, and we are just pointing out that it is biased. We mention this in Section 3. We are not saying that the estimator is wrong and agree that the correct way to use it is with the importance sampling ratio as pointed out in @yifan_zhang_'s paper.
Vedant Shah tweet media
English
3
8
35
16.8K
Avery Ryoo retweetledi
Jungyoon Lee
Jungyoon Lee@yololulu_·
Excited to present PITA at #NeurIPS2025 Spotlight! 🎉 Catch us tomorrow (Fri, Dec 5) 4:30–7:30pm, poster #1604. Come talk sampling + AI for science and kick off your Friday night right ✨
Kirill Neklyudov@k_neklyudov

(1/n) Sampling from the Boltzmann density better than Molecular Dynamics (MD)? It is possible with PITA 🫓 Progressive Inference Time Annealing! A spotlight @genbio_workshop of @icmlconf 2025! PITA learns from "hot," easy-to-explore molecular states 🔥 and then cleverly "cools" them down ❄️ using a novel diffusion process to efficiently find stable, low-energy configurations. It's the first diffusion-based sampler that successfully scales to peptides like Alanine Dipeptide and Tripeptide in their 3D coordinate representation. With a brilliant team @tara_aksa @yololulu_ @bose_joey @ValentinDeBort1 @ArnaudDoucet1 @mmbronstein @dom_beaini Siamak Ravanbakhsh @AlexanderTong7 Read the thread below 🧵 #AI #Science #ML #ComputationalChemistry

English
0
8
23
2.2K
Avery Ryoo
Avery Ryoo@averyryoo·
how yesterday started vs how today started
Avery Ryoo tweet mediaAvery Ryoo tweet media
English
3
1
11
500
Avery Ryoo retweetledi
Trevaunn Richards
Trevaunn Richards@Trey_Richards·
💔
Trevaunn Richards tweet media
QME
3
836
5.5K
88.4K
Avery Ryoo
Avery Ryoo@averyryoo·
turns out everything in my life can be fixed by the blue jays #WANTITALL
English
0
0
2
403
Dane Malenfant
Dane Malenfant@dvnxmvl_hdf5·
A nice feeling after long long hours
Dane Malenfant tweet media
English
1
0
16
663

Keşfet

@Mila_Quebec @unireps @ylecun @MandT_Bank @YouJiacheng @yifan_zhang_ @nandahkrishna @NeurIPSConf