[HN Gopher] Liquid: Language models are scalable and unified mul...
___________________________________________________________________
Liquid: Language models are scalable and unified multi-modal
generators
Author : pr337h4m
Score : 41 points
Date : 2025-04-15 19:46 UTC (3 hours ago)
(HTM) web link (foundationvision.github.io)
(TXT) w3m dump (foundationvision.github.io)
| Centigonal wrote:
| I love the website for this paper! Each section asks a question,
| and immediately answers it with a figure and a few sentences of
| discussion. It's less tech-demo heavy than a lot of other paper
| websites (those are cool, too, in their own way), and instead
| focuses on characterizing multimodal model behavior in a nice,
| clean, disciplined way.
| swyx wrote:
| hmm this is a tough name - conflicts with Liquid AI
| https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
| gwern wrote:
| > For the first time, Liquid uncovers a scaling law that
| performance drop unavoidably brought by the unified training of
| visual and language tasks diminishes as the model size
| increases...No prior work has explored whether LLMs retain the
| power-law scaling laws observed in language tasks when extended
| to visual generation tasks. We prove this alignment and further
| show that vision can be effectively learned by LLMs as a form of
| language.
|
| Does this really show much that
| https://arxiv.org/abs/2301.03728#facebook (uncited) and other
| earlier work did not?
| Nijikokun wrote:
| it performs well with composition, however it seems SD and SDXL
| excels in capability and quality when intermixed with pipelines
| and workflows, this doesn't do much to talk about that comparison
| and whenever i see things like this i think about the overall
| workflow, like cool you do good composition but you don't fit
| within the workflow or ecosystem that surrounds that tool and
| thus i have low expectations around adoption
___________________________________________________________________
(page generated 2025-04-15 23:00 UTC)