Alex Pospekhov

alexpospekhov

6 2

P(doom) <0.001%

·

https://hyperfocus.tech

AI & ML interests

#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 Detection

Recent Activity

liked a model about 8 hours ago

google/embeddinggemma-2

liked a model about 9 hours ago

alexpospekhov/coreml-physicsnemo

published a model about 9 hours ago

alexpospekhov/coreml-physicsnemo

View all activity

Organizations

liked a model about 8 hours ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 4 days ago • 45.6k • 1.42k

liked a model about 9 hours ago

alexpospekhov/coreml-physicsnemo

Other • Updated about 9 hours ago • 8 • 1

published a model about 9 hours ago

alexpospekhov/coreml-physicsnemo

Other • Updated about 9 hours ago • 8 • 1

updated a model about 10 hours ago

alexpospekhov/coreml-physicsnemo

Other • Updated about 9 hours ago • 8 • 1

upvoted 2 papers 12 days ago

ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents

Paper • 2609.17523 • Published 26 days ago • 31

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Paper • 2609.24981 • Published 20 days ago • 76

upvoted a paper 26 days ago

AION-1: Omnimodal Foundation Model for Astronomical Sciences

Paper • 2510.17960 • Published Oct 20, 2025 • 33

upvoted a paper 5 months ago

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published Jul 13 • 240

upvoted 2 papers 6 months ago

LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model

Paper • 2604.02097 • Published Apr 2 • 30

Therefore I am. I Think

Paper • 2604.01202 • Published Apr 2 • 32