Representations, infrastructure, and making models work in production.
A quality-adjusted price index built from 21,000 AI pricing observations finds inference costs falling seven times faster than the standard method suggests — and, measured per completed task, not falling at all.
arXiv:2608.29843
Language models shatter numbers into meaningless fragments before they ever reason about them. Fix that one interface — not the model — and forecasting accuracy jumps.
OpenReview preprint
For decades feeds answered one question — of everything that exists, what should we show you? This vision argues the next question is what should we make for you.
arXiv:2304.03516
If the reader is another AI, why write in tidy English at all? A new method compresses text into dense, alien symbols that humans can't read but models still understand.
arXiv:2606.19857
Skip HTML parsing entirely — retrieve and read the web as screenshots, in pixel space, and beat text-based retrieval even on text-only questions.
PixelRAG paper (GitHub)