OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
Paper • 2605.21226 • Published • 8
Demian L. P.
very-cooluser
AI & ML interests
Anything that can run on ~3GB of memory is a instant thumbs up to me
Recent Activity
upvoted a paper 1 day ago
SAME: A Semantically-Aligned Music Autoencoder upvoted a paper 2 days ago
Measuring Maximum Activations in Open Large Language ModelsOrganizations
None yet
upvoted a paper about 1 hour ago
upvoted a paper 1 day ago
upvoted a paper 2 days ago
upvoted an article 4 days ago
Article
Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step
FINAL-Bench
• • 18 upvoted an article 6 days ago
Article
Vocabulary-Augmented Prompting for Sango — Production African Language AI Without a Parallel Corpus
MEYNG
• • 2 upvoted a paper 8 days ago
upvoted a collection 2 months ago
upvoted 3
papers 4 months ago