Stefano Teso 🦋 NeurIPS
@looselycorrect.bsky.social
Senior assistant prof at University of Trento. I dig Explainable AI, Neuro-Symbolic AI, Interactive ML, Constraints & Circuits.
https://stefanoteso.github.io/ . I "maintain" https://github.com/stefanoteso/awesome-explanatory-supervision .
https://stefanoteso.github.io/ . I "maintain" https://github.com/stefanoteso/awesome-explanatory-supervision .
Reposted by Stefano Teso 🦋 NeurIPS
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
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
April 17, 2025 at 1:44 PM
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
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
Reposted by Stefano Teso 🦋 NeurIPS
Reposted by Stefano Teso 🦋 NeurIPS
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/
Looking forward to see your submissions on recognizing failure scenarios and enabling robust vision systems!
More info: uncertainty-cv.github.io/2025/
UNCV Workshop @ CVPR 2025
CVPR 2025 Workshop on Uncertainty Quantification for Computer Vision.
uncertainty-cv.github.io
March 17, 2025 at 5:29 PM
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/
Looking forward to see your submissions on recognizing failure scenarios and enabling robust vision systems!
More info: uncertainty-cv.github.io/2025/
Reposted by Stefano Teso 🦋 NeurIPS
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
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
Home | AAAI'25 tutorial
The AAAI'25 tutorial on Tensor Factorizations + Probabilistic Circuits
april-tools.github.io
February 25, 2025 at 5:38 PM
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
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
Reposted by Stefano Teso 🦋 NeurIPS
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/abs/2409.13724
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 ...
arxiv.org
January 29, 2025 at 11:41 PM
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/abs/2409.13724
Reposted by Stefano Teso 🦋 NeurIPS
🔊 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👇 🧵
🔗 website: sites.google.com/view/fpiwork...
🔥 Call for papers: sites.google.com/view/fpiwork...
more details in thread below👇 🧵
December 18, 2024 at 7:09 PM
🔊 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👇 🧵
🔗 website: sites.google.com/view/fpiwork...
🔥 Call for papers: sites.google.com/view/fpiwork...
more details in thread below👇 🧵
Reposted by Stefano Teso 🦋 NeurIPS
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...
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...
sfiscience
SFI seeks applications for full-time, 12-month resident faculty positions at all academic levels.
santafe.edu
January 8, 2025 at 7:39 PM
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...
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...
Reposted by Stefano Teso 🦋 NeurIPS
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...
This dataset can help predict how proteins behave, paving the way for new treatments 💊
www.sanger.ac.uk/news_item/hu...
January 9, 2025 at 9:40 AM
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...
This dataset can help predict how proteins behave, paving the way for new treatments 💊
www.sanger.ac.uk/news_item/hu...
Reposted by Stefano Teso 🦋 NeurIPS
🦕 Special track at NeSy dedicated to KGs and Ontologies!! Have a look 🙌
Time to announce the second special track at the NeSy 2025 conference:
Knowledge Graphs, Ontologies and Neurosymbolic AI 📖
Chaired by Cogan Shimizu.
Check out the Call for Papers!
2025.nesyconf.org/kgs-ontologi...
Knowledge Graphs, Ontologies and Neurosymbolic AI 📖
Chaired by Cogan Shimizu.
Check out the Call for Papers!
2025.nesyconf.org/kgs-ontologi...
Knowledge Graphs, Ontologies and Neurosymbolic AI
19th International Conference on Neurosymbolic Learning and Reasoning (NeSy 2025, 8-10 September 2025, Santa Cruz, CA, USA)
2025.nesyconf.org
January 10, 2025 at 10:57 AM
🦕 Special track at NeSy dedicated to KGs and Ontologies!! Have a look 🙌
Reposted by Stefano Teso 🦋 NeurIPS
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...
A blog post to celebrate and present it: francisbach.com/my-book-is-o...
December 21, 2024 at 3:23 PM
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...
A blog post to celebrate and present it: francisbach.com/my-book-is-o...
Reposted by Stefano Teso 🦋 NeurIPS
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
December 21, 2024 at 5:46 PM
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
Reposted by Stefano Teso 🦋 NeurIPS
Neural Concept Binder @WolfStammer
December 12, 2024 at 9:28 PM
Neural Concept Binder @WolfStammer
Reposted by Stefano Teso 🦋 NeurIPS
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
@garymarcus.bsky.social
December 12, 2024 at 3:12 PM
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
@garymarcus.bsky.social
Reposted by Stefano Teso 🦋 NeurIPS
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.
Come to our poster at the NeurIPS BDU workshop on Saturday - see TL;DR below.
December 11, 2024 at 5:25 PM
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.
Come to our poster at the NeurIPS BDU workshop on Saturday - see TL;DR below.
Reposted by Stefano Teso 🦋 NeurIPS
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
See all the works on #reasoning shortcuts 1/2
December 10, 2024 at 3:44 PM
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!
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!
December 9, 2024 at 1:26 AM
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!
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!
Reposted by Stefano Teso 🦋 NeurIPS
For those attending #NeurIPS2024 go to UNIREPS @unireps.bsky.social workshop to know more about representations similarity. Nice work led by @beatrixmgn.bsky.social 🌟
Why do NNs often learn similar representations? Existing identifiability results offer theoretical insights, but applying them in practice poses challenges.
We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉
openreview.net/pdf?id=SQKUZSieVg
1/
We’ll present our new work exploring these challenges next week at @unireps #NeurIPS2024 🇨🇦🎉
openreview.net/pdf?id=SQKUZSieVg
1/
openreview.net
December 6, 2024 at 4:21 PM
For those attending #NeurIPS2024 go to UNIREPS @unireps.bsky.social workshop to know more about representations similarity. Nice work led by @beatrixmgn.bsky.social 🌟
Reposted by Stefano Teso 🦋 NeurIPS
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
Let me know if I missed you!
go.bsky.app/RMJ8q3i
November 11, 2024 at 3:27 PM
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
Let me know if I missed you!
go.bsky.app/RMJ8q3i
Reposted by Stefano Teso 🦋 NeurIPS
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/sports/blog/...
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…
dtai.cs.kuleuven.be
November 21, 2024 at 5:39 PM
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/sports/blog/...
Reposted by Stefano Teso 🦋 NeurIPS
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.
December 5, 2024 at 7:11 AM
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.
Reposted by Stefano Teso 🦋 NeurIPS
if you ever wondered how to concisely represent causal models, don’t miss my talk on causal abstraction tomorrow at @ellisamsterdam.bsky.social
📢 The next Amsterdam Causality Meeting supported by the #ELLISunitAmsterdam will take place on Wednesday!
📅 December 4th
⏰ 14.30-17.30
📍 Lab 42 in L3.36
🔗 amscausality.github.io/upcoming/
Come and join us! 🚀✨
📅 December 4th
⏰ 14.30-17.30
📍 Lab 42 in L3.36
🔗 amscausality.github.io/upcoming/
Come and join us! 🚀✨
Upcoming Meetings
Causality meeting 2023 with VU, UvA, Amsterdam UMC and CWI
amscausality.github.io
December 3, 2024 at 10:43 PM
if you ever wondered how to concisely represent causal models, don’t miss my talk on causal abstraction tomorrow at @ellisamsterdam.bsky.social
Reposted by Stefano Teso 🦋 NeurIPS
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
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
December 4, 2024 at 10:58 PM
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
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
Reposted by Stefano Teso 🦋 NeurIPS
Kush R. Varshney: The AI Alignment Problem, Limits, and Solutions - in case you missed it -
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...
buff.ly
December 4, 2024 at 3:20 PM
Kush R. Varshney: The AI Alignment Problem, Limits, and Solutions - in case you missed it -
Reposted by Stefano Teso 🦋 NeurIPS
Is anyone familiar with efficient tools/libraries for over/under-approximating of the volume of convex polytopes (in H-representation)?
December 3, 2024 at 3:38 PM
Is anyone familiar with efficient tools/libraries for over/under-approximating of the volume of convex polytopes (in H-representation)?