Skip to page content
SAVRN
Search Plan a project

Independent publisher

Alex Pospekhov

alexpospekhov

#TECH: Swift 6 · Apple Core AI · Core ML · Apple Neural Engine · Metal Performance Shaders · Accelerate AMX · Synthetic Aperture Radar · Radar Physics · Sensor Fusion · Data Fusion · Signal Processing #ML: Video-LLM · SlowFast Video Networks · Multimodal Video Tokenization · Audio-Visual Cross-Attention · Perceiver Resampler · Point Trajectory Tracking · VideoMamba · FastViT · Temporal Action…

Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers3

Compare the published evidence

This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Other.

Reported licenses: apache-2.0. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Reference Machine: Apple M3 Max (16 CPU cores, 40 Metal GPU cores, 16 Apple Neural Engine cores, 48 GB Unified Memory) - Unlocking the Apple Neural Engine for Physical AI: While Apple's 16-Core NPU (38 TOPS) was designed primarily for vision and speech, physical PDE operators historically failed to run on it due to unsupported tensor primitives. By algebraically reformulating complex Fourier spectral convolutions and dynamic graph scatter into native Apple Machine Intermediate Language (MIL) representations, all 8 foundation networks achieve up to 98.4% ANE execution with 0 CPU fallbacks. - Extreme Energy Efficiency (0.071 J / step for ANE aerodynamic solver to 10.8 J for global weather at…

Open weights apache-2.0 coreml