🚀 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?

Check out our recent work offering a principled way to perform parallel prediction (few-step generation) in Diffusion LLMs with minimal performance degradation!

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. 🚀

🎓 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

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

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 👇

@vinhtong.bsky.social · 2y ago

🚀 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).

🚀 Fully funded PhD in Neurosymbolic AI for Finance 💰🤖 🔍 Work at Imperial College London on cutting-edge AI for financial applications! [1/3]