Guy Van den Broeck
@guyvdb.bsky.social
🎓 CS Prof at UCLA 🧠 Researching reasoning and learning in artificial intelligence: tactable deep generative models, probabilistic circuits, probabilistic programming, neurosymbolic AI https://web.cs.ucla.edu/~guyvdb/
We just implemented trai (try + AI) (github.com/binpash/trai), a Claude plugin that can help you isolate 🫷 changes done in your file system by tool calls (like pip install), and only commit them if they are intended ☺️. Try it out (pun intended) and share your feedback!
GitHub - binpash/trai: A claude plugin for sandboxing tool calls
A claude plugin for sandboxing tool calls. Contribute to binpash/trai development by creating an account on GitHub.
github.com
🚀 Excited to present our paper "Rethinking Probabilistic Circuit Parameter Learning" at AISTATS tomorrow! What are the key bottlenecks in optimizing 𝒕𝒓𝒂𝒄𝒕𝒂𝒃𝒍𝒆 probabilistic models like Probabilistic Circuits? Can we design "Adam-equivalent" optimizers for these structures?
🛠️ The #uai2026 workshop lineup is out! Check out the full list of accepted workshops 👉auai.org/uai2026/workshops Don't forget to register and see you in Amsterdam 🇳🇱 on August 21!
Uncertainty in Artificial Intelligence
Amsterdam, Netherlands | 17-21 August
auai.org
We put probabilistic circuits into diffusion language models and got a big boost in reasoning performance!
Ian Li@ianli18.bsky.social · 6mo ago"He is from [MASK] [MASK]" → "San York"? dLLMs fail because they ignore token dependencies. This Factorization Barrier arises from a structural misspecification: models are restricted to fully factorized outputs. We break this barrier with CoDD, enabling coherent parallel generation. 🚀
"He is from [MASK] [MASK]" → "San York"? dLLMs fail because they ignore token dependencies. This Factorization Barrier arises from a structural misspecification: models are restricted to fully factorized outputs. We break this barrier with CoDD, enabling coherent parallel generation. 🚀
For those on hiring committees: do you push back against this? What do you do?
Jessica Hullman@jessicahullman.bsky.social · 6mo agoHow horrible to be a CS grad student under pressure to submit multiple first author papers to every conference deadline, whether they feel ready or not. This serves no one’s best interests in long run (science included). But lots of students appear to being getting advice it’s necessary to compete
What is wild to me is the defense, BY THE NEURIPS BOARD, that fabricated citations do not mean "the content of the papers themselves [is] necessarily invalidated" It does. It very much does. What do you think citing other work is for? What do you think writing a paper is for? What do you *think*?
Sharon Goldman@sharongoldman.bsky.social · 7mo agoNEW: NeurIPS,one of the world’s top academic AI conferences, accepted research papers with 100+ AI-hallucinated citations, new report claims fortune.com/2026/01/21/n...
🚨🚨🚨 I have a #postdoc (1+1 yrs) at the School of Informatics, The University of Edinburgh to work on 💥 #reliable #LLM #agents with #neurosymbolic #nesy layers 💥 with Huawei Trustworthy Technology and Engineering Laboratory Munich 👉 elxw.fa.em3.oraclecloud.com/hcmUI/Candid... 🙏 please share!
Research Associate
The School of Informatics, University of Edinburgh invites applications for a 1-year Post-Doctoral Research Associate (PDRA), to do research on reliable large language agents via neuro-symbolic integr...
elxw.fa.em3.oraclecloud.com
Recordings of the NeSy 2025 keynotes are now available! 🎥 Check out insightful talks from @guyvdb.bsky.social, @tkipf.bsky.social and D McGuinness on our new Youtube channel www.youtube.com/@NeSyconfere... Topics include using symbolic reasoning for LLM, and object-centric representations!
NeSy conference
The NeSy conference studies the integration of deep learning and symbolic AI, combining neural network-based statistical machine learning with knowledge representation and reasoning from symbolic appr...
youtube.com
I gave a keynote at @nesyconf.org on "Symbolic Reasoning in the Age of Large Language Models" Check out the recording if you are curious about neurosymbolic generative AI: www.youtube.com/watch?v=Otmi...
Guy Van den Broeck - Symbolic Reasoning in the Age of Large Language Models
YouTube video by NeSy conference
youtube.com
Now, @guyvdb.bsky.social is giving the opening keynote arguing why symbolic AI is still relevant in the age of LLMs... With the help of Shrek!
How can reverend Bayes help us to incorporate constraints? With NeSy of course 👀 With applications in non-toxic LLM generation and safe AI driving! @guyvdb.bsky.social
Did you know Neurosymbolic methods can beat 'the other's turf'? Just use a 100x smaller LM with symbolic constraints integrated via Ctrl-G to wipe the floor with GPT!🧹 arxiv.org/abs/2406.13892 @guyvdb.bsky.social
It is almost time to welcome you all in Santa Cruz! 🦕 We will start with an exciting and timely keynote by @guyvdb.bsky.social on "Symbolic Reasoning in the Age of Large Language Models" 👀 📆 Full conference schedule: 2025.nesyconf.org/schedule/
Grants, awards, fellowships, etc. should really be upfront about their acceptance rate. Some of them are just abundantly not worth the effort
If you've seen recent claims on genAI doing well at math exams read the commentary by the greatest living mathematician, who uses tech a lot in math. (Tao & I graduated from the same math dept & had the same profs. He is way younger than me and way, way, way better!!!) mathstodon.xyz/@tao/1148814...
Terence Tao (@tao@mathstodon.xyz)
It is tempting to view the capability of current AI technology as a singular quantity: either a given task X is within the ability of current tools, or it is not. However, there is in fact a very wid...
mathstodon.xyz
Wish LM could plan—not just guess the next word? TRACE lets LM see all endings before each move. – Global control at inference time – Tractable lookahead via an HMM LM-proxy – Linear classifier per constraint Outperform RL, DPO, FUDGE—at just +20% decoding over base LM. #ICML2025 @guyvdb.bsky.social
🚨 First Call for Participation – NeSy 2025 📍 Sept 8–10 | Santa Cruz, CA Join the longest-running conference on neurosymbolic AI! Our keynote speakers: @guyvdb.bsky.social @tkipf.bsky.social Deborah McGuinness @garymarcus.bsky.social More info 👇
Announcing the 2025 IJCAI Computers and Thought Award winner ✨Aditya Grover, InceptionAILabs & UCLA. Dr. Grover is honored for uniting deep generative models, representation learning & RL to advance scientific reasoning. Congratulations! www.ijcai.org/awards
I wrote about @jessejdavis.bsky.social, an American computer science professor running an influential soccer analytics research team at an ancient university in Belgium. Much of the leading data analysis is still being done outside soccer. Why? @theguardian.com www.theguardian.com/football/202...
The Belgian lab shaping modern soccer’s data revolution
A small corner of one of the world’s oldest universities has moved the sport forward, and made the argument for research institutions writ large
theguardian.com
📣 Call for Paper Alert: TokShop @ ICML 2025 TokShop explores tokenization across all data modalities. Topics include: subword NLP techniques, multimodal approaches, multilingual challenges, post-training modification, alternative representations, and statistical perspectives.
ICML 2025 Workshop TokShop
Welcome to the OpenReview homepage for ICML 2025 Workshop TokShop
openreview.net
🗓️ Deadline extended: 💥2nd June 2025!💥 We are looking forward to your works on: 🔌 #circuits and #tensor #networks 🕸️ ⏳ normalizing #flows 💨 ⚖️ scaling #NeSy #AI 🦕 🚅 fast and #reliable inference 🔍 ...& more! please share 🙏
antonio vergari ⚔️ short-circuiting@nolovedeeplearning.bsky.social · last yr.the #TPM ⚡Tractable Probabilistic Modeling ⚡Workshop is back at @auai.org #UAI2025! Submit your works on: - fast and #reliable inference - #circuits and #tensor #networks - normalizing #flows - scaling #NeSy #AI ...& more! 🕓 deadline: 23/05/25 👉 tractable-probabilistic-modeling.github.io/tpm2025/
🎓 Looking for PhD students, postdocs & interns! I’m recruiting for my new lab at NUS School of Computing, focusing on generative modeling, reasoning, and tractable inference. 💡 Interested? Learn more here: liuanji.github.io 🗓️ PhD application deadline: June 15, 2025
Anji Liu
Incoming Assistant Professor at NUS working on tractable deep generative models.
liuanji.github.io
Anji is an amazing mentor and colleague. If I could go for another PhD in CS I would apply!
Anji Liu@anjiliu.bsky.social · last yr.🎓 Looking for PhD students, postdocs & interns! I’m recruiting for my new lab at NUS School of Computing, focusing on generative modeling, reasoning, and tractable inference. 💡 Interested? Learn more here: liuanji.github.io 🗓️ PhD application deadline: June 15, 2025
Just under 10 days left to submit your latest endeavours in #tractable probabilistic models! Join us at TPM @auai.org #UAI2025 and show how to build #neurosymbolic / #probabilistic AI that is both fast and trustworthy!
antonio vergari ⚔️ short-circuiting@nolovedeeplearning.bsky.social · last yr.the #TPM ⚡Tractable Probabilistic Modeling ⚡Workshop is back at @auai.org #UAI2025! Submit your works on: - fast and #reliable inference - #circuits and #tensor #networks - normalizing #flows - scaling #NeSy #AI ...& more! 🕓 deadline: 23/05/25 👉 tractable-probabilistic-modeling.github.io/tpm2025/
This year I am co-organizing the 8th iteration of the Tractable Probabilistic Modeling #TPM workshop at #UAI2025 🌴 Rio de Janeiro edition 🌴 🌐 lnkd.in/dDK8T5Au ⏰ Submission deadline: May 23th AoE 🌴 Date: July 15th 🧵👇
I'll be giving an oral talk at #ICLR2025! 🗓 Session 1C — 🕦 11:30 AM SGT. Title: Learning to Discretize Denoising Diffusion ODEs. Come by if you're into #GenerativeAI / #DiffusionModels
