The Third Generation of Apple's Foundation Modelsmachinelearning.apple.com11 points·by 2bit·w zeszłym miesiącu·1 comments
ParaRNN: Large-Scale Nonlinear RNNs, Trainable in Parallelmachinelearning.apple.com2 points·by 2bit·3 miesiące temu·0 comments
Exploring LLMs with MLX and the Neural Accelerators in the M5 GPUmachinelearning.apple.com2 points·by 2bit·8 miesięcy temu·0 comments
FastVLM: Efficient Vision Encoding for Vision Language Modelsmachinelearning.apple.com93 points·by 2bit·12 miesięcy temu·6 comments
Apple Intelligence Foundation Language Models Tech Report 2025machinelearning.apple.com242 points·by 2bit·12 miesięcy temu·204 comments
Updates to Apple's On-Device and Server Foundation Language Modelsmachinelearning.apple.com6 points·by 2bit·w zeszłym roku·1 comments
An LLM-Based Approach to Review Summarization on the App Storemachinelearning.apple.com4 points·by 2bit·w zeszłym roku·0 comments
Controlling Language and Diffusion Models by Transporting Activationsmachinelearning.apple.com90 points·by 2bit·w zeszłym roku·15 comments
Apple Prototypes Tabletop Robot with Lifelike Movementsmacrumors.com3 points·by 2bit·w zeszłym roku·0 comments
2bit·w zeszłym roku·discussYou can find a similar method in zundo, a zustand middleware for undo/redo. It has the concept of pastStates and futureStates.