[HN Gopher] Janus: Decoupling visual encoding for multimodal und...
___________________________________________________________________
Janus: Decoupling visual encoding for multimodal understanding and
generation
Author : jinqueeny
Score : 31 points
Date : 2024-10-20 23:46 UTC (23 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| jadbox wrote:
| Does anyone know how Janus compares with rhymes-ai Aria model?
| josh-sematic wrote:
| Interesting! It seems to be that there would be a tradeoff
| between specialist subsystems (which allow you to excel at the
| specialized tasks, but which can't handle things outside the
| specialization well) and generalized subsystems (which allow you
| to integrate information across multiple specializations but
| which may not be great at any of them). Ultimately you likely
| need a mix of both, but it's not obvious to me how you would
| identify when it will be beneficial to "hard code" separations
| for different subsystems (as is done here for image generation &
| encoding) vs when the model should be left to "figure it out"
| during training and implicitly develop the appropriate subsystems
| within the network.
| wiz21c wrote:
| The online demo returns "Error" :-( My prompt was a picture and
| the question was "what is written on that screenshot" ?
___________________________________________________________________
(page generated 2024-10-21 23:02 UTC)