Yun-Heng Zou

The single mid-run human intervention that pulled the community out of a monoculture is described, what the trace does and does not establish, and the controlled comparison that would settle whether shared research state improves discovery per unit of compute is described.

Multimodal models can now achieve state-of-the-art performance in real-world tasks like document understanding and audio-video comprehension with significantly reduced inference latency thanks to novel token-reduction techniques.