Finn Sinclair 🥽
498 posts

Finn Sinclair 🥽
@FNS_Developer
Vision Products Group @ Apple, ex-HoloLens, Qualcomm XR, MRTK. let’s go build the spatial future :)







Another gem for the size comparison fans out there. Mt Everest is tiny in comparison to Olympus Mons on Mars. HT @curiosityonx

wait now I really have to know



Wow, language models can talk without words. A new framework, Cache-to-Cache (C2C), lets multiple LLMs communicate directly through their KV-caches instead of text, transferring deep semantics without token-by-token generation. It fuses cache representations via a neural projector and gating mechanism for efficient inter-model exchange. The payoff: up to 10% higher accuracy, 3–5% gains over text-based communication, and 2× faster responses. Cache-to-Cache: Direct Semantic Communication Between Large Language Models Code: github.com/thu-nics/C2C Project: github.com/thu-nics Paper: arxiv.org/abs/2510.03215 Our report: mp.weixin.qq.com/s/tjDq99VrEbo0… 📬 #PapersAccepted by Jiqizhixin

Keep thinking.

Regular iPhone Evolution









