The Third Generation of Apple's Foundation Modelsmachinelearning.apple.com11 points·by 2bit·bulan lalu·1 comments
ParaRNN: Large-Scale Nonlinear RNNs, Trainable in Parallelmachinelearning.apple.com2 points·by 2bit·3 bulan yang lalu·0 comments
Exploring LLMs with MLX and the Neural Accelerators in the M5 GPUmachinelearning.apple.com2 points·by 2bit·8 bulan yang lalu·0 comments
FastVLM: Efficient Vision Encoding for Vision Language Modelsmachinelearning.apple.com93 points·by 2bit·12 bulan yang lalu·6 comments
Apple Intelligence Foundation Language Models Tech Report 2025machinelearning.apple.com242 points·by 2bit·12 bulan yang lalu·204 comments
Updates to Apple's On-Device and Server Foundation Language Modelsmachinelearning.apple.com6 points·by 2bit·tahun lalu·1 comments
An LLM-Based Approach to Review Summarization on the App Storemachinelearning.apple.com4 points·by 2bit·tahun lalu·0 comments
Controlling Language and Diffusion Models by Transporting Activationsmachinelearning.apple.com90 points·by 2bit·tahun lalu·15 comments
Apple Prototypes Tabletop Robot with Lifelike Movementsmacrumors.com3 points·by 2bit·tahun lalu·0 comments
On Device Llama 3.1 with Core MLmachinelearning.apple.com1 points·by 2bit·2 tahun yang lalu·0 comments
2bit·tahun lalu·discussYou can find a similar method in zundo, a zustand middleware for undo/redo. It has the concept of pastStates and futureStates.