Hacker News new | past | comments | ask | show | jobs | submit login

This was already done in JPEG-LM [0] and it did work.

[0] https://arxiv.org/abs/2408.08459




Cryptomnesia!

Interestingly, they managed to train and inference on JPEG bitstream directly. I thought they'd need to at least build embeddings for those bitstream features or something.




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: