iiinova — where your digital self keeps evolving

Benjie Wang

@benjiewang.bsky.social

201 followers 154 following 15 posts

Assistant Professor at University of Utah | Previously @ UCLA, UC Berkeley, University of Oxford

Posts Replies Media

Reposted by Benjie Wang

Anji Liu @anjiliu.bsky.social · 17/05/2025

🎓 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

liuanji.github.io

Anji Liu

Incoming Assistant Professor at NUS working on tractable deep generative models.

0209

Reposted by Benjie Wang

Zilei Shao @zoeshao.bsky.social · 11/03/2025

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

64815

Benjie Wang @benjiewang.bsky.social · 27/02/2025

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.

1213

Reposted by Benjie Wang

Anji Liu @anjiliu.bsky.social · 13/02/2025

Want to turn your state-of-the-art diffusion models into ultra-fast few-step generators? 🚀 Learn how to optimize your time discretization strategy—in just ~10 minutes! ⏳✨ Check out how it's done in our Oral paper at ICLR 2025 👇

0154

Reposted by Benjie Wang

Liza Semenova @liza-semenova.bsky.social · 19/12/2024

If you are interested in doing a #PhD with me at Imperial College London and qualify as a home student, please reach out (before end of 2024)! Potential topics: spatial statistics, applied deep generative models, probabilistic programming and more.

075

Benjie Wang @benjiewang.bsky.social · 13/12/2024

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

1184