Tokenization has been the final barrier to truly end-to-end language models. We developed the H-Net: a hierarchical network that replaces tokenization with a dynamic chunking process directly inside the model, automatically discovering and operating over meaningful units of data

There’s been a lot of work on unlearning in LLMs, trying to erase memorization without hurting capabilities — but we haven’t seen much success. ❓What if unlearning is actually doomed from the start? 👇This thread explains why and how *memorization sinks* offer a new way forward.

💡Can we trust synthetic data for statistical inference? We show that synthetic data (e.g. LLM simulations) can significantly improve the performance of inference tasks. The key intuition lies in the interactions between the moments of synthetic data and those of real data

Does synthetic data always help text-embedder models? Not quite. The gains are sparse and come with trade-offs. We open-source data + code to make research on synthetic data for embeddings more rigorous. 1/

I'm teaching a diffusion & flow matching class at CMU in Spring 2026 where students can use ChatGPT, Cursor, or any AI tool they want. No exams. Just build with open internet. 139 students signed up for 20 spots. Here's what's happening: 🧵 kellyyutonghe.github.io/10799S26/

I feel like the worst part about the AI Era is that it’s impossible to get any human customer support agents on the line 😭😭