Benjie Wang

Assistant Professor at @UUtah | Previously @UCLA @UCBerkeley @UniofOxford

[Benjie Wang @benjiewang_cs]

Also check out the awesome paper "Sum of Squares Circuits" (https://t.co/nRKVQOOy03) by @loreloc_, Stefan Mengel, and @tetraduzione, which concurrently showed the separation between monotone and squared circuits. Also at AAAI 2025 today poster #840!

[Benjie Wang @benjiewang_cs]

Circuits 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.

[Benjie Wang @benjiewang_cs]

Inception PCs strictly subsume monotone and squared PCs, and are strictly more expressive than both. We show this leads to improved downstream modeling performance when normalizing for FLOPS:

[Daniel Israel @danielmisrael]

“That’s one small [MASK] for [MASK], a giant [MASK] for mankind.” – [MASK] Armstrong

Can autoregressive models predict the next [MASK]? It turns out yes, and quite easily…
Introducing MARIA (Masked and Autoregressive Infilling Architecture)
https://t.co/h8H9l5pOnK

[Benjie Wang @benjiewang_cs]

Thanks to my amazing co-authors Denis Mauá, @guyvdb, and YooJung Choi. Hope to see you at the poster session!

[Benjie Wang @benjiewang_cs]

You have some model/knowledge (e.g. Bayes Net, 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: https://t.co/JHnGbM2MV9

[Benjie Wang @benjiewang_cs]

Along the way we also show a bunch of other cool results, like:

- More efficient algorithms for causal inference on circuits
- New circuit properties
- Separation/hardness results

[Honghua Zhang @HonghuaZhang2]

So excited to present Ctrl-G **Adaptable Logical Control for Large Language Models** TODAY at #NeurIPS2024 West Ballroom 4:30 - 7:30 pm.

Ctrl-G is THE solution to LLM fill-in-the-middle generation, numerical planning and structured output. Stop by to discuss more!

[Zhe Zeng @zhezeng0908]

📢 I’m recruiting PhD students @CS_UVA for Fall 2025!
🎯 Neurosymbolic AI, probabilistic ML, trustworthiness, AI for science. See my website for more details: https://t.co/LDOPjISmBo
📬 If you're interested, apply and mention my name in your application: https://t.co/xU1w98Rycv

[Benjie Wang @benjiewang_cs]

@loreloc_ Awesome work Lorenzo!

[Eleonora Giunchiglia @e_giunchiglia]

🚨 Exciting Opportunity! 🚨

I’m looking for PhD students to join my team @ImperialEEE and @ImperialX_AI! 🌍🔍

Research Topic: Neuro-symbolic AI with a focus on making AI safer. 💡🤖

Full scholarships available! 🎓💰

Interested? Email me at: [email protected] [1/2]

[Benjie Wang @benjiewang_cs]

Excited to share our work on LLM tokenization, led by the awesome @renatogeh. We find significant boosts in downstream performance, by probabilistically interpreting the space of tokenizations of a text. A bit of probabilistic reasoning goes a long way!

[Renato Lui Geh @renatogeh]

Where is the signal in LLM tokenization space?

Does it only come from the canonical (default) tokenization?

The answer is no! By looking at other ways to tokenize the same text, we get a consistent boost to LLM performance!

https://t.co/bbUBlotNVj

1/5

[Benjie Wang @benjiewang_cs]

Super cool work on discretizing probability distributions with *exponential* gains in succinctness! Recommended reading for probabilistic inference folks

[Poorva Garg @PoorvaGarg11]

Are you looking for an inference algorithm that supports your discrete-continuous probabilistic program? Look no further! We have developed a new probabilistic programming language (PPL) called HyBit that provides scalable support for discrete-continuous probabilistic programs.