Sign in

Conor Hassan

@conorhassan.bsky.social
55 followers 110 following 11 posts

ML research and engineering conorhassan.com

PostsRepliesMedia
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 23/04/2026
If you are at @iclr-conf.bsky.social, please go and have a chat with Yang Yang, @nasrullohloka.bsky.social or @conorhassan.bsky.social at our posters! (re-posted after fixing the time zone...)
042
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 22/04/2026
7/ Website: conorhassan.com/projects/art... @conorhassan.bsky.social, @nasrullohloka.bsky.social and Yang are at ICLR (Yang with its own poster on PriorGuide, previously spammed); go talk to them!
conorhassan.com
Efficient Autoregressive Inference for Transformer Probabilistic Models
031
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 22/04/2026
6/ Work by @conorhassan.bsky.social & @nasrullohloka.bsky.social (co-first), + Cen-You Li, @huangdaolang.bsky.social, @mummitrollet.bsky.social, Yang Yang, @sfrancesco.bsky.social, @samikaski.bsky.social & yours truly. @univhelsinkics.bsky.social & FCAI & @ellisinstitute.fi
conorhassan.com
Efficient Autoregressive Inference for Transformer Probabilistic Models
141
Reposted by Conor Hassan
Stephan Mandt @stephanmandt.bsky.social · 10/02/2026
Really excited to see this. I’ve been involved since the early AABI days, and it’s been incredible to see the trajectory — from NeurIPS/ICML workshops, to a symposium, and now to a full conference as ProbML. Huge thanks to the program/general chairs and the whole organizing team!
082
Reposted by Conor Hassan
Symposium on Probabilistic Machine Learning @probml.bsky.social · 10/02/2026
ProbML 2026 (formerly AABI) invites submissions on probabilistic ML (both Bayesian and otherwise!), July 5 in Seoul (co-located with ICML). Website: probml.cc. Tracks: proceedings (PMLR), workshop, fast track. New focus includes applications in healthcare and climate! Submit by: 20 March 2026.
12516
Reposted by Conor Hassan
Martin Trapp @trappmartin.eurosky.social · 10/02/2026
If you are interested working with me as a postdoc on probabilistic machine learning, please consider reaching out and applying for the postdoc call by digital futures (link below). 🔗 www.digitalfutures.kth.se/call/up-to-t...
digitalfutures.kth.se
Up to ten postdoc fellows in technologies for digital transformation | Digital Futures
Purpose Digital Futures postdoc fellowships aim to support talented early-career international researchers in pursuing their research ideas within a new research group and institution. As this is a mo...
0105
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 06/02/2026
More info soon; all papers fit our AI4science research agenda within the Finnish Center for Artificial Intelligence & @ellisinstitute.fi -- building efficient methods for inference, uncertainty quantification and decision making, leveraging powerful autoregressive transformers and diffusion models.
141
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 06/02/2026
A bit of a delayed celebration, but happy that our three submitted papers were accepted at @iclr-conf.bsky.social 2026! This was a... complicated year for ICLR, but hopefully now we can focus on the science.
1154
Reposted by Conor Hassan
David Rügamer @davidruegamer.bsky.social · 06/12/2025
After yesterday's Salon de Refusés paper presentation and today's EIML workshop paper presentation with @jkobialka.bsky.social, we will conclude with an oral by @erpel.bsky.social at the MedEurIPS workshop tomorrow 🔥 Very happy that we had so many great opportunities to present our research! ❤️EurIPS
062
Reposted by Conor Hassan
David Rügamer @davidruegamer.bsky.social · 06/12/2025
EurIPS was pretty fun! Thanks to @lacerbi.bsky.social , @conorhassan.bsky.social , and all organizers of the Amortized ProbML team for the great workshop and for inviting me as a speaker! 🙌 Also great to be able to present our spotlight paper on sparsity on the main stage 😍
1185
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 27/11/2025
If you are at ELLIS UnConference on Dec 2 (pre @euripsconf.bsky.social ), join us at our Amortized ProbML workshop! Come for our great speakers: @paulbuerkner.com Yingzhen Li @davidruegamer.bsky.social @liza-semenova.bsky.social & poster session; stay for our hot takes on amortized probML!
Amortized ProbML workshop page snapshot
1186
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 27/11/2025
Updated website: sites.google.com/view/amortiz... Co-organized with Cen-You (Scott) Li, @conorhassan.bsky.social, @desirivanova.bsky.social as well as @samikaski.bsky.social & FCAI
052
Reposted by Conor Hassan
Benjamin Warner @benjaminwarner.dev · 27/10/2025
Some personal news: I've joined sophont.med to help build the next generation of open medical foundation models. We've relaunched medarc.ai, our open science research community. Join us if you want to help advance open medical AI. And we are hiring.
131
Reposted by Conor Hassan
Emtiyaz Khan @emtiyaz.mastodon.social.ap.brid.gy · 20/10/2025
I have not announced it widely but I will be starting a professorship in TU Darmstadt (Germany) next year. I will start accepting PhD students from Sep 2026 (but I will keep my group and position in Tokyo as well). Here is a first call for PhD positions at our new Center of Excellence at TUDa […]
mastodon.social
Original post on mastodon.social
042
Conor Hassan @conorhassan.bsky.social · 17/10/2025
The abstract submission deadline for the ELLIS Workshop on Amortized Probabilistic ML has been extended to October 25th! You still have time to submit a short abstract on your work in: Amortized Inference, Neural processes, Prior-fitted networks, Sequential Decision-Making, and Foundation models.
186
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 17/10/2025
**Submission DL extended to Oct 25!** You are still in time to submit a short abstract on amortized (simulator-based) inference (SBI), neural processes, prior-fitted networks (PFNs), amortized experimental design, foundation models, and related applications. Call: sites.google.com/view/amortiz...
sites.google.com
Amortized ProbML 2025 - Call for Papers
Accepted papers will be presented as posters during the workshop poster session on 2nd December, 2025. Please be aware that this is not the same as the ELLIS UnConference poster session.
041
Reposted by Conor Hassan
Vincent Fortuin @vincefort.eurosky.social · 14/10/2025
Looks like an awesome workshop!
062
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 14/10/2025
Reminder that Amortized inference Workshop submissions at the ELLIS Unconference are still open until **Oct 16, 2025**. Only a short abstract (½ page), so go ahead! Workshop: Dec 2, 2025, co-located with EurIPS. Website: sites.google.com/view/amortiz...
lnkd.in
LinkedIn
This link will take you to a page that’s not on LinkedIn
0133
Reposted by Conor Hassan
ELLIS @ellis.eu · 07/10/2025
🔸 Organizers: Cen-You Li, @conorhassan.bsky.social, Desi R. Ivanova, Luigi Acerbi (+ @samikaski.bsky.social as Advisory Member) 📣 Call for contributions open until Oct 10 👉 Details: eurips.cc/ellis
eurips.cc
ELLIS UnConference - A NeurIPS-endorsed conference in Europe
A NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark
021
Reposted by Conor Hassan
Conor Hassan @conorhassan.bsky.social · 01/10/2025
submit your posters and attend this exciting workshop!
031
Reposted by Conor Hassan
Martin Trapp @trappmartin.eurosky.social · 02/10/2025
Want to work on Trustworthy AI? 🚀 I'm seeking exceptional candidates to apply for the Digital Futures Postdoctoral Fellowship to work with me on Uncertainty Quantification, Bayesian Deep Learning, and Reliability of ML Systems. The position will be co-advised by Hossein Azizpour or Henrik Boström.
trappmartin.github.io
Home
Martin Trapp - Assistant Professor in Machine Learning at KTH Royal Institute of Technology.
1114
Reposted by Conor Hassan
Martin Trapp @trappmartin.eurosky.social · 01/10/2025
EurIPS workshop on AmOrTIzED InfErENcE!!!1!
1145
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 01/10/2025
Do you like to train neural networks to solve all your nasty probabilistic inference and sequential design problems? Do you love letter salads such as NPs, PFNs, NPE, SBI, BED? Then no place is better than the Amortized ProbML workshop we are organizing at #ELLIS UnConference.
Amortized ProbML:
Unlocking Probabilistic Machine Learning for Real-world Inference & Design (🇩🇰)
ELLIS UnConference Workshop
Copenhagen | 2 December, 2025
1216
Conor Hassan @conorhassan.bsky.social · 01/10/2025
submit your posters and attend this exciting workshop!
031
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 01/10/2025
We'll discuss tricky questions such as: • When does amortization fail badly even though it's rarely talked about? • Which applications can these neat methods actually work for? • Can we really deploy these methods in the real world? • ... and more!
141
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 01/10/2025
Short abstract submission is open (DL Oct 16, 2025 AoE) Accepted abstracts will be presented as posters. 🌍 Location: Copenhagen (co-located with #EurIPS) 📅 Date: 2 Dec, 2025 🔗 Website: sites.google.com/view/amortiz... 📝Call for abstracts: sites.google.com/view/amortiz...
sites.google.com
Amortized ProbML 2025 - Call for Papers
Accepted papers will be presented as posters during the workshop poster session on 2nd December, 2025. Please be aware that this is not the same as the ELLIS UnConference poster session.
133
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 17/07/2025
Superlative initiative! Massive kudos to the organisation team for getting this going in such a short time!
061
Reposted by Conor Hassan
NeurIPS Conference @neuripsconf.bsky.social · 16/07/2025
NeurIPS is endorsing EurIPS, an independently-organized meeting which will offer researchers an opportunity to additionally present NeurIPS work in Europe concurrently with NeurIPS. Read more in our blog post and on the EurIPS website: blog.neurips.cc/2025/07/16/n... eurips.cc
eurips.cc
eurips.cc
A NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark
112439
Reposted by Conor Hassan
Christian A. Naesseth @canaesseth.bsky.social · 30/06/2025
Tomorrow, Tuesday (July 1st) from 4pm to 5pm (UK time). “SDE Matching: Scalable and Simulation-Free Training of Latent Stochastic Differential Equations" (arxiv.org/abs/2502.02472) 🚀 Join via Zoom 🔥 t.co/N1C3UFukxd
t.co
https://us05web.zoom.us/j/7780256206?pwd=flsq8weBOvaZgAsr3ThNiHq9d1mXMS.1&omn=89044077993
031
Reposted by Conor Hassan
Christian A. Naesseth @canaesseth.bsky.social · 30/06/2025
🚨🚀 Come hear @gbarto.bsky.social talk about SDE Matching tomorrow! SDE Matching is a highly efficient and scalable training framework for Latent/Neural SDEs. You no longer have to discretize or simulate your SDE models when fitting them to data. #SDE #Diffusion #FlowMatching #ML
191
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 26/06/2025
Blog post: lacerbi.github.io/blog/2025/ju...
lacerbi.github.io
You can just predict the optimum | Luigi Acerbi
instant Bayesian optimization! (kind of)
051
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 26/06/2025
New blog post! You can train a neural network to *just do things* -- such as *predict the optimum of a function*. But how do you get a big training dataset of "functions with known optima"? Read the blog post to find out! (link 👇)
Screenshot of blog post titled "You can just predict the optimum"
3214
Reposted by Conor Hassan
Andreas Kirsch @blackhc.bsky.social · 17/05/2025
I want to share my latest (very short) blog post: "Active Learning vs. Data Filtering: Selection vs. Rejection." What is the fundamental difference between active learning and data filtering? Well, obviously, the difference is that: 1/11
14011
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 02/05/2025
Website for more info: acerbilab.github.io/amortized-co...
acerbilab.github.io
Amortized Probabilistic Conditioning for Optimization, Simulation and Inference
This website contains information about the ACE framework, a transformer-based meta-learning model that provides a unified approach for probabilistic conditioning and prediction across various machine...
011
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 02/05/2025
@huangdaolang.bsky.social will be presenting our work tomorrow on pretrained/amortized transformers for all sorts of inference tasks, go say hi! #AISTATS2025 Poster session 1 Place: Hall A-E Time: Sat 3 May 3 p.m. — 6 p.m. Poster number: 23
192
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 22/04/2025
11/10 This work is part of ongoing research at our group @univhelsinkics.bsky.social & FCAI on efficient & robust probabilistic methods for science. Interested in surrogate based and amortized inference? We often have open PhD/postdoc positions! Check us out: www.helsinki.fi/en/researchg...
helsinki.fi
Machine and Human Intelligence | University of Helsinki
142
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 22/04/2025
10/10 Read the full paper #AABI2025 Proceedings Track! Work by @chengkunli.bsky.social, @abacabadabacaba.bsky.social, Petrus Mikkola, & yours truly. 📜 Paper: arxiv.org/abs/2504.11554 💻 Code: github.com/acerbilab/no... 📄 Overview: acerbilab.github.io/normalizing-... Let us know what you think!
151
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 22/04/2025
1/10🔥 New paper alert in #AABI2025 Proceedings! Normalizing Flow Regression (NFR) — an offline Bayesian inference method. What if you could get a full posterior using *only* the evaluations you *already* have, maybe from optimization runs?
1236
Reposted by Conor Hassan
Arno Solin @arnosolin.bsky.social · 21/04/2025
Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models Najwa Laabid · Severi Rissanen · Markus Heinonen · Arno Solin · Vikas Garg Hall 3 + Hall 2B #194 🗓️ Fri 25 Apr 3 p.m. +08 — 5:30 p.m. +08 📄 arxiv.org/abs/2405.17656
arxiv.org
Alignment is Key for Applying Diffusion Models to Retrosynthesis
Retrosynthesis, the task of identifying precursors for a given molecule, can be naturally framed as a conditional graph generation task. Diffusion models are a particularly promising modelling approac...
131
Reposted by Conor Hassan
Arno Solin @arnosolin.bsky.social · 21/04/2025
Our #ICLR2025 poster "Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs" (Severi Rissanen, Markus Heinonen, Arno Solin) 🗓️ Hall 3 + Hall 2B #140, Thu 24 Apr 3 p.m. +08 — 5:30 p.m. +08 📄 Preprint: arxiv.org/abs/2410.11149
0101
Reposted by Conor Hassan
Arno Solin @arnosolin.bsky.social · 21/04/2025
Our #ICLR2025 poster "Discrete Codebook World Models for Continuous Control" (Aidan Scannell, Mohammadreza Nakhaeinezhadfard, Kalle Kujanpää, Yi Zhao, Kevin Luck, Arno Solin, Joni Pajarinen) 🗓️ Hall 3 + Hall 2B #415, Thu 24 Apr 10 a.m. +08 — 12:30 p.m. +08 📄 Preprint: arxiv.org/abs/2503.00653
2113
Reposted by Conor Hassan
Paul Chang @mummitrollet.bsky.social · 08/04/2025
This is a new blog looking at the individual optimizations that went into serving the DeepSeek model class in SGLang. I have been observing the SGLang repo for a few months now, and it's crazy how quickly they integrate new optimized features. It's a very cool open-source project!
121
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 08/04/2025
1/ We asked GPT-4.5 -- allegedly the model with the best sense of humor, according to the site we do not talk about here -- to write a comic about our recent AISTATS paper on the Amortized Conditioning Engine (ACE). Then gpt-4o drew it. You judge the result... (text continues 👇)
A comic "Bayes explains everything!"
2175
Reposted by Conor Hassan
Paul Chang @mummitrollet.bsky.social · 09/04/2025
B200 go brrrr! It seems by doubling the TFLOPs you get double the speed. Cool stuff by Antonio and WavespeedAI team to get FLUX-dev inference (SOTA diffusion) in under a second on a B200. datacrunch.io/blog/flux-on...
datacrunch.io
FLUX on B200: Real-Time Image Inference with WaveSpeedAI + DataCrunch Collaboration
How WaveSpeedAI and DataCrunch achieved an up to 6x faster image inference by optimizing FLUX-dev's latency and efficiency: NVIDIA B200 vs. H100 benchmark.
021
Reposted by Conor Hassan
Paul Chang @mummitrollet.bsky.social · 24/03/2025
medium.com/@NoamShazeer... I came across this post from one of the attention GOATs (thnx @conorhassan.bsky.social for term). I know there are more complicated solutions to this but I find this quite a simple solution to implement to keep track of shapes.
medium.com
Shape Suffixes — Good Coding Style
If you code neural networks, I believe that this convention can make your life more pleasant. We keep this pretty religiously at…
011
Reposted by Conor Hassan
Luigi Acerbi @lacerbi.bsky.social · 06/03/2025
1/ Introducing ACE (Amortized Conditioning Engine)! Our new AISTATS 2025 paper presents a transformer framework that unifies tasks from image completion to BayesOpt & simulator-based inference under *one* probabilistic conditioning approach. It's Bayes all the way down!
13514
Reposted by Conor Hassan
Paul Chang @mummitrollet.bsky.social · 12/03/2025
Multi-Head Latent Attention vs Group Query Attention: We break down why MLA is a more expressive memory compression technique AND why naive implementations can backfire. Check it out!
02710
Reposted by Conor Hassan
ELLIS @ellis.eu · 18/02/2025
Registration is open for the following ELLIS Summer Schools: 🇨🇭 Unit Lausanne / @epfl-ai-center.bsky.social on ML & AI for Health 🏴󠁧󠁢󠁥󠁮󠁧󠁿 Unit Manchester on ML for Healthcare & Biology 🇩🇪 @ellisunitjena.bsky.social on AI for Earth & Climate Sciences Get links for more details and registration:
ellis.eu
Travel and study in Europe: 2025 Schedule of ELLIS PhD Winter and Summer Schools announced
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
0165
Reposted by Conor Hassan
Christian A. Naesseth @canaesseth.bsky.social · 12/02/2025
You still have a chance to submit your work to all tracks for AABI. New deadline is February 14 for both Workshop and Proceedings track! #AABI2025 #ML #ICLR2025 #Stats #Bayes
053