Sign in

Stefano Teso

@looselycorrect.bsky.social
577 followers 112 following 9 posts

Senior assistant prof at University of Trento. I dig Explainable AI, Neuro-Symbolic AI, Interactive ML, Constraints & Circuits. stefanoteso.github.io . I "maintain" github.com/stefanoteso/awesome-expl… .

PostsRepliesMedia
Reposted by Stefano Teso
Workshop on Unifying Concept Representation Learning @ucrl-iclr26.bsky.social · 22/12/2025
📣 Announcing the Workshop on **Unifying Concept Representation Learning** (UCRL) at ICLR’26 (@iclr-conf.bsky.social ). When? 26 or 27 April 2026 Where? Rio de Janeiro, Brazil Call for papers, schedule, invited speakers & more: ucrl-iclr26.github.io Looking forward to your submissions!
ucrl-iclr26.github.io
Home
Workshop on Unifying Concept Representation Learning (ICLR 2026)
151
Reposted by Stefano Teso
Steve Azzolin @steveazzolin.bsky.social · 17/04/2025
Faithfulness of GNN explanations isn’t one-size-fits-all🧢 Our last @iclr-conf.bsky.social paper breaks it down across: 1. Evaluation metrics 2. Model implementations 3. OOD generalisation w: Antonio L. @looselycorrect.bsky.social @andreapasserini.bsky.social 1/5
163
Reposted by Stefano Teso
Pasquale Minervini @neuralnoise.com · 26/03/2025
is this AGI?
2142
Reposted by Stefano Teso
Marcus Klasson @marcusklasson.bsky.social · 17/03/2025
Submission deadline is extended to March 20 for submitting your paper to our #CVPR2025 workshop on Uncertainty Quantification for Computer Vision. Looking forward to see your submissions on recognizing failure scenarios and enabling robust vision systems! More info: uncertainty-cv.github.io/2025/
uncertainty-cv.github.io
UNCV Workshop @ CVPR 2025
CVPR 2025 Workshop on Uncertainty Quantification for Computer Vision.
0105
Reposted by Stefano Teso
Lorenzo Loconte @loreloc.bsky.social · 25/02/2025
Are you at AAAI in Philadelphia and interested about #tensor-factorizations or #circuits or even both? Then join us today at our tutorial: "From tensor factorizations to circuits (and back!)" Details and materials here april-tools.github.io/aaai25-tf-pc... Time 4:15pm - 6:00pm, Room 117
april-tools.github.io
Home | AAAI'25 tutorial
The AAAI'25 tutorial on Tensor Factorizations + Probabilistic Circuits
03111
Reposted by Stefano Teso
Diego Calanzone @diadochus.bsky.social · 29/01/2025
Finally, LOgically COnsistent (LoCo) LLaMas can outperform solver-based baselines and SFT! I thank @nolovedeeplearning.bsky.social and @looselycorrect.bsky.social for the guidance in realizing this project, get in touch or come to chat in Singapore! arxiv.org/abs/2409.13724
arxiv.org
Logically Consistent Language Models via Neuro-Symbolic Integration
Large language models (LLMs) are a promising venue for natural language understanding and generation. However, current LLMs are far from reliable: they are prone to generating non-factual information ...
072
Reposted by Stefano Teso
Joey Bose @joeybose.bsky.social · 18/12/2024
🔊 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 @iclr-conf.bsky.social! 🔗 website: sites.google.com/view/fpiwork... 🔥 Call for papers: sites.google.com/view/fpiwork... more details in thread below👇 🧵
28519
Reposted by Stefano Teso
Melanie Mitchell @melaniemitchell.bsky.social · 08/01/2025
An incredible opportunity for the right person: The Santa Fe Institute is seeking applications for full-time resident faculty positions at all academic levels For me, this has been the best possible job ever. More info here: santafe.edu/about/jobs/r...
santafe.edu
sfiscience
SFI seeks applications for full-time, 12-month resident faculty positions at all academic levels.
9378206
Reposted by Stefano Teso
Wellcome Sanger Institute @sangerinstitute.bsky.social · 09/01/2025
Protein instability is the main driver of inherited genetic conditions, according to the largest map of protein variants to date − Human Domainome 1.0 🔎 This dataset can help predict how proteins behave, paving the way for new treatments 💊 www.sanger.ac.uk/news_item/hu...
24713
Reposted by Stefano Teso
Eleonora Giunchiglia @e-giunchiglia.bsky.social · 10/01/2025
🦕 Special track at NeSy dedicated to KGs and Ontologies!! Have a look 🙌
0134
Reposted by Stefano Teso
Francis Bach @bachfrancis.bsky.social · 21/12/2024
My book is (at last) out, just in time for Christmas! A blog post to celebrate and present it: francisbach.com/my-book-is-o...
213735
Reposted by Stefano Teso
Sriraam Natarajan @nsriraam.bsky.social · 21/12/2024
When building human allied AI systems, it is imperative to think of who is in control. In our blue sky paper at #AAAI, we argue that a deeper understanding of whether human is in the loop or if AI is in the loop is essential! arxiv.org/pdf/2412.14232
1167
Reposted by Stefano Teso
Alfredo Canziani @alfcnz.bsky.social · 12/12/2024
Neural Concept Binder @WolfStammer
1184
Reposted by Stefano Teso
Julio Aráuz @jarauz7f.bsky.social · 12/12/2024
Today Google's Gemini asked me if I wanted help with my messages to be a more effective communicator. I clicked on "yes". A button appeared that read "tips for procrastination". Here is what I got... Apparently procrastinating is a great skill to have. Thanks Google!! @garymarcus.bsky.social
1157
Reposted by Stefano Teso
Nicola Branchini @nicolabranchini.bsky.social · 11/12/2024
Interested in estimating posterior predictives in Bayesian inference? Really want to know if your approximate inference "is working"? Come to our poster at the NeurIPS BDU workshop on Saturday - see TL;DR below.
33911
Reposted by Stefano Teso
antonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 10/12/2024
I think one important aspect missing from the current #NeSy papers & talks is that a (#probabilistic) #neuro #symbolic approach to #AI and #ML does not bring full interpretability and trustworthiness but can actually give a false sense of reliability. See all the works on #reasoning shortcuts 1/2
162
Stefano Teso @looselycorrect.bsky.social · 09/12/2024
The #NeurIPS experience is about to start! ✈ Drop me a line if you want to chat about #neurosymbolic reasoning #shortcuts, human-interpretable machine #concepts, logically-consistent #LLMs, or human-in-the-➰ #XAI! See you in Vancouver!
0112
Reposted by Stefano Teso
Emanuele Marconato @ema-ridopoco.bsky.social · 06/12/2024
For those attending #NeurIPS2024 go to UNIREPS @unireps.bsky.social workshop to know more about representations similarity. Nice work led by @beatrixmgn.bsky.social 🌟
0102
Reposted by Stefano Teso
Emile van Krieken @emilevankrieken.com · 11/11/2024
I made a starter pack with the people doing something related to Neurosymbolic AI that I could find. Let me know if I missed you! go.bsky.app/RMJ8q3i
179236
Reposted by Stefano Teso
Jesse Davis @jessejdavis.bsky.social · 21/11/2024
We're doing a deep dive into possession value models. While VAEP, g+, PV & OBV are conceptually identical, they make different design choices. We look at using (no) goal vs. xG as the target variable. w/Lorenzo Cascioli @probberechts.bsky.social Lode Van Tente dtai.cs.kuleuven.be/sports/blog/...
dtai.cs.kuleuven.be
Three key design decisions for possession state value models: an experimental analysis
A fundamental question for anyone interested in soccer is how to evaluate a player’s individual contributions using data. While counting…
2259
Reposted by Stefano Teso
François Fleuret @francois.fleuret.org · 05/12/2024
The best one could be to speed up progress in AI at this moment of history is to shape whatever is the community's reward function so that a fraction of the compute and brain power currently knob-turning GPTs to gain 0.25% on whatever unrealistic benchmark try SOMETHING NEW.
2585
Reposted by Stefano Teso
riccardo @rmassidda.it · 03/12/2024
if you ever wondered how to concisely represent causal models, don’t miss my talk on causal abstraction tomorrow at @ellisamsterdam.bsky.social
2124
Reposted by Stefano Teso
Blake Richards @tyrellturing.bsky.social · 04/12/2024
If you review for a #ML conference like @iclr-conf.bsky.social or @neuripsconf.bsky.social, YOU HAVE A RESPONSIBILITY TO REPLY TO THE AUTHORS. If the rebuttal doesn't address your concerns explain why. But giving a score of 2-3 then ghosting the authors is super rude. I say this as an AC. #MLSky
87913
Reposted by Stefano Teso
Vaishak Belle @vaishakbelle.bsky.social · 04/12/2024
Kush R. Varshney: The AI Alignment Problem, Limits, and Solutions - in case you missed it -
buff.ly
Kush R. Varshney: The AI Alignment Problem, Limits, and Solutions
Abstract:  With the recent rise of large language models (LLMs) and generative AI, we are treating interactions - both helpful and harmful - as behaviors tha...
051
Reposted by Stefano Teso
Paolo Morettin @paolomorettin.bsky.social · 03/12/2024
Is anyone familiar with efficient tools/libraries for over/under-approximating of the volume of convex polytopes (in H-representation)?
331
Reposted by Stefano Teso
David Debot @daviddebot.bsky.social · 04/12/2024
🚨 Interpretable AI often means sacrificing accuracy—but what if we could have both? Most interpretable AI models, like Concept Bottleneck Models, force us to trade accuracy for interpretability. But not anymore, due to Concept-Based Memory Reasoner (CMR)! #NeurIPS2024 (1/7)
2247
Reposted by Stefano Teso
Sara Magliacane hiring PhDs at UvA @smaglia.bsky.social · 03/12/2024
The Uncertainty in Artificial Intelligence conference (UAI) is on 🦋! I'm a bit biased, but this is a fantastic conference for #probabilisticML, #causality, #causalML, #tractable #probabilistic #models, #imprecise probabilities, #reasoning, #neurosymbolic approaches and more. #causalSky #statSky
0295
Reposted by Stefano Teso
Mark Riedl @markriedl.bsky.social · 02/12/2024
The Human-Centered Explainable AI (HCXAI) Workshop will be back for the 5th time in 2025!
0163
Reposted by Stefano Teso
antonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 29/11/2024
@ropeharz.bsky.social forced me to do this starter pack on #tractable #probabilistic modeling and #reasoning in #AI and #ML please write below if you want to be added (and sorry if I did not find you from the beginning). go.bsky.app/DhVNyz5
115115
Reposted by Stefano Teso
Christopher Manning @chrmanning.bsky.social · 02/12/2024
I think we saw this in the AI/ML sphere, not just in politics …
2475
Reposted by Stefano Teso
antonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 30/11/2024
useful also to give you motivation to submit your #ICML papers
062
Reposted by Stefano Teso
Yarin @yaringal.bsky.social · 30/11/2024
I'm looking for PhD applicants who have expertise in Gaussian processes and/or Transformers for an exciting PhD project If this sounds interesting, application deadline for funding is 3/12 Please share with people you think this might be relevant to! oatml.cs.ox.ac.uk/apply.html
1388
Reposted by Stefano Teso
Emile van Krieken @emilevankrieken.com · 29/11/2024
Very proud to be a "paranymph" for my longtime friend Jaap (we're friends since we were 6)! He has done excellent work on Language Model interpretability before it was cool. Go check it out!
0202
Reposted by Stefano Teso
antonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 30/11/2024
🔥🔥** cough cough **🔥🔥 (being summoned in a circle of fire) here is a tutorial for you slideslive.com/38992775/pro... and here is a modern take from the perspective of tensor factorisations arxiv.org/abs/2409.07953 tensor factorisations and circuits give you exact gradients and **any** marginals
slideslive.com
Probabilistic Circuits: Inference Representations Learning Theory
2204
Reposted by Stefano Teso
Emile van Krieken @emilevankrieken.com · 29/11/2024
Yeah, many people miss this: Gumbel softmax is not applicable when you want to branch! You can hack your way around it, but bias compounds very rapidly
5325
Reposted by Stefano Teso
Robert Peharz @ropeharz.bsky.social · 28/11/2024
Amazing opportunity for #Neurosymbolic folks! 🚨🚨🚨 We are looking for a Tenure Track Prof for the 🇦🇹 #FWF Cluster of Excellence Bilateral AI (think #NeSy ++) www.bilateral-ai.net A nice starting pack for fully funded PhDs is included. jobs.tugraz.at/en/jobs/226f...
bilateral-ai.net
BilateralAI – Bilateral AI – Cluster of Excellence
31511
Reposted by Stefano Teso
Robert Peharz @ropeharz.bsky.social · 26/11/2024
What is common knowledge in your field but shocks outsiders? The rigorous definition of probability does not define probabilities as relative frequencies. The frequency nature of probability is hence a theorem (law of large numbers), but not the definition of probability.
192
Reposted by Stefano Teso
Daniel Lowd @dlowd.com · 26/11/2024
Newsweek asked me for thoughts on the safety of chatbots. They published all of them except for one sentence: "I’d rather have kids talking to chatbots than listening to Donald Trump." ...they excluded that one for some reason. Article below. Beware spammy ads. www.newsweek.com/are-ai-chatb...
newsweek.com
Are AI Chatbots Safe for Children? Experts Weigh in After Teen's Suicide
The suicide of 14-year-old Sewell Setzer has intensified concerns over AI chatbot safety, as his mother files a lawsuit against Character.AI.
2197
Reposted by Stefano Teso
Zachary Lipton @zacharylipton.bsky.social · 26/11/2024
Medically adapted foundation models (think Med-*) turn out to be more hot air than hot stuff. Correcting for fatal flaws in evaluation, the current crop are no better on balance than generic foundation models, even on the very tasks for which benefits are claimed. arxiv.org/abs/2411.04118
arxiv.org
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
Several recent works seek to develop foundation models specifically for medical applications, adapting general-purpose large language models (LLMs) and vision-language models (VLMs) via continued pret...
825857
Reposted by Stefano Teso
Vaishak Belle @vaishakbelle.bsky.social · 26/11/2024
Luc De Raedt: How to Make Logics Neurosymbolic - in case you missed it -
buff.ly
Luc De Raedt: How to Make Logics Neurosymbolic
Abstract: Neurosymbolic AI (NeSy) is regarded as the third wave in AI. It aims at combining knowledge representation and reasoning with neural networks. Nume...
0183
Stefano Teso @looselycorrect.bsky.social · 26/11/2024
Neat ICML #XAI paper, with actual user studies! 🎩 "Our theory posits that absent explanation humans expect the AI to make similar decisions to themselves, and that they interpret an explanation by comparison to the explanations they themselves would give." proceedings.mlr.press/v162/yang22c...
080
Reposted by Stefano Teso
antonio vergari ⚔️ short-circuiting @nolovedeeplearning.bsky.social · 26/11/2024
I've seen things you people wouldn't believe. Attacks from reviewers on fire off the shoulders of #OpenReview. I watched logic fallacies glitter in the dark near @iclr-conf.bsky.social All those moments will be lost in time, like tears in the next resubmission.  Time to die. #ML #Ai #PhDlife
2163
Stefano Teso @looselycorrect.bsky.social · 26/11/2024
Writing a rebuttal right now. I'm tempted to reply with this:
Rebuttal to XXXX - Exechiel 25, 17 Edition
1141
Stefano Teso @looselycorrect.bsky.social · 26/11/2024
It used to be just reviewer 2. Now it's reviewers 2, 3, and 4. And we gave them LLMs, for extra giggles. Thank goodness for reviewer 1. Please keep up the good work, we need you!
020
Reposted by Stefano Teso
Ernesto Jiménez-Ruiz @ejimenez-ruiz.bsky.social · 23/11/2024
NeSy is on Bluesky! bsky.app/profile/nesy... Check out the 2025 edition of the NeSy conference: 2025.nesyconf.org General Chair: @lgilpin.bsky.social Programme Chairs: @e-giunchiglia.bsky.social @emilevankrieken.com @pascalhitzler.bsky.social @tarekbesold.bsky.social @arturgarcez.bsky.social
2025.nesyconf.org
NeSy2025
The NeSy series is the longest standing gathering for the presentation and discussion of cutting edge research in neurosymbolic AI. NeSy is the annual meeting of the Neural-Symbolic Learning and Reaso...
22011
Reposted by Stefano Teso
Eleonora Giunchiglia @e-giunchiglia.bsky.social · 24/11/2024
🔥 Follow this page 👉 bsky.app/profile/nesy... to stay updated with the 2025 Neuro-symbolic AI conference 🦕🦕🦕
bsky.app
1146
Reposted by Stefano Teso
Clément Canonne @ccanonne.github.io · 23/11/2024
It's tough to gain visibility as a young researcher, and it's job market season! Are you a theoretical computer science PhD/postdoc on the job market? I don't have a crazy juge audience but I'll try to help a bit: fill this form, and I'll tweet your pitch and info! docs.google.com/forms/d/e/1F...
docs.google.com
Theoretical CS Job Market 2024
210538
Reposted by Stefano Teso
Christoph Molnar @christophmolnar.bsky.social · 22/11/2024
Just realized BlueSky allows sharing valuable stuff cause it doesn't punish links. 🤩 Let's start with "What are embeddings" by @vickiboykis.com The book is a great summary of embeddings, from history to modern approaches. The best part: it's free. Link: vickiboykis.com/what_are_emb...
Book outlineOver the past decade, embeddings — numerical representations of
machine learning features used as input to deep learning models — have
become a foundational data structure in industrial machine learning
systems. TF-IDF, PCA, and one-hot encoding have always been key tools
in machine learning systems as ways to compress and make sense of
large amounts of textual data. However, traditional approaches were
limited in the amount of context they could reason about with increasing
amounts of data. As the volume, velocity, and variety of data captured
by modern applications has exploded, creating approaches specifically
tailored to scale has become increasingly important.
Google’s Word2Vec paper made an important step in moving from
simple statistical representations to semantic meaning of words. The
subsequent rise of the Transformer architecture and transfer learning, as
well as the latest surge in generative methods has enabled the growth
of embeddings as a foundational machine learning data structure. This
survey paper aims to provide a deep dive into what embeddings are,
their history, and usage patterns in industry.Cover image
22647101