"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. 🚀
Many thanks for the best paper award for our Deep Polynomial Chaos Expansion (DeepPCE), received from the #UAI workshop #tractable #probabilistic #modeling #TPM! Many congrats to the team, especially leading author Johannes Exenberger!
The workshop paper:
arxiv.org/abs/2507.21273
likely one of the best editions of #TPM ever!
big thanks to @poorvagarg.bsky.social @jsleland.bsky.social @javaloyml.bsky.social @zzhe.bsky.social @lennertds.bsky.social Lingyun Yao and Christoph Staudt for organizing it
and to everyone who attended it!
The workshop continues with another amazing talk by Efi Tsamoura.
@auai.org #TPM2025
Got to know about interesting ways to tractably control output of language models. Great start to the workshop.
@auai.org, #TPM2025
A great start to TPM 2025! @auai.org
#UAI2025 #TPM
Some more exciting news! This year we had not one, but two(!) dissertations receiving the SIGPLAN John C. Reynolds Doctoral Dissertation Award at PLDI!
The awardees are: Harrison Goldstein from the University of Pennsylvania and Rachit Nigam from Cornell University. More info ⬇️
If you are considering applying for a PhD this Fall, please get in touch. I’m looking for students who are interested in PL, SE, and/or HCI — and ideally all three! You can find more information about me and my work on my website: harrisongoldste.in
24 hours more to submit your latest papers on #TPMs!
We have extended the submission deadline for TPM to the 2nd of June!
Remember that **we accept recently accepted works that fit in topic,** so if you want to travel to Rio and share your work it's a no brainer imho 🌴🌴
🗓️ 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 🙏
Rio is looking forward to seeing all your works on #fast #reliable #tractable #models #circuits #tensor #networks #flows!
please share!
🎓 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!
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
🧵👇
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/
But that general sense of dread when approaching any port of entry, that questioning of "should I even go", that being put in a box and told to wait indefinitely, etc., are all very, very relatable.
🥇 Accepted workshops are out! www.auai.org/uai2025/work...
Get ready for a day of great talks, panels, and discussions on causality, tractable models, and safe AI.
Don't forget to submit your work, and see you in Rio! 🇧🇷
PLMW@PLDI'25 is now accepting applications: pldi25.sigplan.org/home/PLMW-pl...
Deadline: April 10, 2025
PLMW an excellent place to learn about exciting PL research, from the ground up, and to find your PL friends!
Please apply!
to all reviewers who kindly accepted the invitation to review for #UAI2025 🙏,
you can do it! one more push! 🦾
and if you have trouble submitting your reviews by Monday 24th AoE... please contact ⚡ immediately ⚡ your area chair!
Is conceptual purity the defining aesthetic in academic computer science?
statmodeling.stat.columbia.edu/2025/03/13/i...
What happens if we tokenize cat as [ca, t] rather than [cat]?
LLMs are trained on just one tokenization per word, but they still understand alternative tokenizations. We show that this can be exploited to bypass safety filters without changing the text itself.
#AI #LLMs #tokenization #alignment
Circuits are generative models that use sum-product computation graphs to model probability densities. But how do we ensure the non-negativity of the output?
Check out our poster "On the Relationship between Monotone and Squared Probabilistic Circuits" at AAAI 2025 **today**: 12:30pm-14:30pm #841.
More information on SIGPLAN Research Highlights and the list of previously awarded papers can be found by the links below.
Nominate your favourite papers from 2024 by June 5, 2025 and stay tuned!
* www.sigplan.org/Highlights/
* www.sigplan.org/Highlights/P...
After a long hiatus, SIGPLAN Research Highlights are back!
The highlights committee[*] is thrilled to announce four exceptional PL papers from 2021-2023 awarded in this round! ⇒
[*] Azalea Raad, Stephen Kell, Mike Bond and Erez Petrank, @natefoster.bsky.social, @lorisdanto.bsky.social, and me.
SoCal Programming Languages and Systems is back and will be @ucsd_cse in February!
Submit your abstracts!
socalpls.github.io
@ranjitjhala.bsky.social @manu.sridharan.net @cristalopes.bsky.social
Reposts appreciated!
You have some model/knowledge (e.g. Bayes Net, Probabilistic Circuit, Probabilistic/Logic Program, DB) and some query (e.g. MAP, Causal Adjustment) you want to ask. When can you compute this efficiently?
Find out @ NeurIPS today in Poster Session 6 East, #3801.
Paper: arxiv.org/abs/2412.05481
Excited to give an oral presentation of our work "Controllable Generation via Locally Constrained Resampling" @ #NeurIPS2024 SafeGenAI
TL;DR We fix greedy constrained decoding using an ad hoc LLM approximation that we tractably condition on the constraint and reweighing samples
![Royce Hall, UCLA.
Source: https://commons.wikimedia.org/wiki/File:Royce_Hall_Facade.JPG [Josh Lee, CC BY-SA 3.0]](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:mufeq6pi3d2f4a4qpv32655v/bafkreifjnugenjmduxpmrtud4ov3pejkydmg3kfsbcbecsljar7jwmqymy)
Royce Hall, UCLA. Source: https://commons.wikimedia.org/wiki/File:Royce_Hall_Facade.JPG [Josh Lee, CC BY-SA 3.0]
This admissions cycle, I am recruiting PhD students to join my research group! If you're interested in systems or security (including intersections with cryptography, datacenters, AI, etc.), then please apply to UCLA Computer Science and list me on your application as a potential faculty advisor.
Attention🚨 We are looking for motivated students and researchers to be members of the PLDI 2025 Artifact Evaluation Committee. This year, we are accepting self-nominations (the form is here: forms.gle/2TPmixasDmqM...). Deadline: Dec 23rd, 2024.
For more info: pldi25.sigplan.org/track/pldi-2...
