Benjie Wang
@benjiewang.bsky.social
Postdoc @ UCLA StarAI Lab, PhD in CS from Oxford. Probabilistic ML, Tractable Models, Causality
Reposted by Benjie Wang
🎓 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
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
May 17, 2025 at 5:26 PM
🎓 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
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
Reposted by Benjie Wang
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
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
March 11, 2025 at 11:13 PM
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
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.
Check out our poster "On the Relationship between Monotone and Squared Probabilistic Circuits" at AAAI 2025 **today**: 12:30pm-14:30pm #841.
February 27, 2025 at 2:57 PM
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.
Check out our poster "On the Relationship between Monotone and Squared Probabilistic Circuits" at AAAI 2025 **today**: 12:30pm-14:30pm #841.
Reposted by Benjie Wang
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 👇
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 👇
🚀 Exciting news! Our paper "Learning to Discretize Diffusion ODEs" has been accepted as an Oral at #ICLR2025! 🎉
[1/n]
We propose LD3, a lightweight framework that learns the optimal time discretization for sampling from pre-trained Diffusion Probabilistic Models (DPMs).
[1/n]
We propose LD3, a lightweight framework that learns the optimal time discretization for sampling from pre-trained Diffusion Probabilistic Models (DPMs).
February 13, 2025 at 8:44 AM
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 👇
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 👇
Reposted by Benjie Wang
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.
December 19, 2024 at 2:21 PM
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.
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
Find out @ NeurIPS today in Poster Session 6 East, #3801.
Paper: arxiv.org/abs/2412.05481
December 13, 2024 at 7:10 PM
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
Find out @ NeurIPS today in Poster Session 6 East, #3801.
Paper: arxiv.org/abs/2412.05481