[HN Gopher] Dynamic Large Concept Models: Latent Reasoning in an...
___________________________________________________________________
Dynamic Large Concept Models: Latent Reasoning in an Adaptive
Semantic Space
Author : gmays
Score : 47 points
Date : 2026-01-08 16:31 UTC (6 hours ago)
(HTM) web link (arxiv.org)
(TXT) w3m dump (arxiv.org)
| sorenjan wrote:
| Would this enable a model to learn concepts in one language and
| generate answers about it in another, as long as it learns
| general translations between them?
| notrealyme123 wrote:
| My educated guess: Not more than any other LLM. The text-latent
| encoder and latent-text decoder just find am more efficient
| representation of the tokens, but it's more of a compression
| instead of turning words/sentences into abstract concepts.
| There will be residuals of the input language be in there.
| notrealyme123 wrote:
| Broken citations. My inner reviewer gets sad. :(
| miven wrote:
| I'm really glad that these HNet-inspired approaches are getting
| traction, I'm a big fan of that paper.
|
| Though I wonder how much of the gains in this case are actually
| due to 75% extra parameters compared to the baseline, even if the
| inference FLOPs are matched.
|
| Can't help but see this as a just different twist on parameter
| use sparsity idea leveraged by MoE models, as those also gain in
| performance at constant forward pass FLOPs because of extra
| parameters.
___________________________________________________________________
(page generated 2026-01-08 23:01 UTC)