CRONOS introduces scalable convex optimization for two-layer neural networks reaching ImageNet scale, with CRONOS-AM extending to arbitrary multi-layer architectures while matching tuned deep learning performance.
JAX : composable transformations of P ython+ N um P y programs
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
PaLI jointly scales a 4B-parameter vision transformer with language models on a new 10B multilingual image-text dataset to reach state-of-the-art results on vision-language tasks while keeping a simple modular design.
Perceiver IO is a general architecture that processes arbitrary structured inputs and outputs with linear scaling and achieves strong results on GLUE, Sintel optical flow, multi-task reasoning, and StarCraft II without task-specific components.
ActNet is a new KST-based neural network that outperforms KANs and competes with MLPs in PINN benchmarks for PDE simulation tasks.
Gemini Ultra reaches human-expert performance on MMLU for the first time and sets new state-of-the-art results on 30 of 32 benchmarks, including all 20 multimodal ones tested.