Simple Self-Distillation
AI & ML interests
None defined yet.
Recent Activity
Papers
Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents
Team members 45 private
Efficient Vision Encoding for Vision Language Models
Benchmark for the design of efficient continual learning of image-text models over years.
-
apple/coreml-stable-diffusion-mixed-bit-palettization
Updated • 11 • 30 -
apple/coreml-stable-diffusion-xl-base
Text-to-Image • Updated • 11 • 70 -
apple/coreml-stable-diffusion-2-1-base
Text-to-Image • Updated • 46 • 58 -
apple/coreml-stable-diffusion-2-1-base-palettized
Text-to-Image • Updated • 14 • 20
AIM: Autoregressive Image Models
CLaRa models
MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B
A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint.
-
apple/aimv2-large-patch14-224
Image Feature Extraction • 0.3B • Updated • 1.01k • 62 -
apple/aimv2-huge-patch14-224
Image Feature Extraction • 0.7B • Updated • 118 • 13 -
apple/aimv2-1B-patch14-224
Image Feature Extraction • 1B • Updated • 107 • 9 -
apple/aimv2-3B-patch14-224
Image Feature Extraction • 3B • Updated • 69 • 4
MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities.
DataCompDR: Improved datasets for training image-text SOTA models.
-
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
Paper • 2311.17049 • Published • 8 -
apple/mobileclip_s0_timm
Image Classification • Updated • 1.93k • 12 -
apple/mobileclip_s1_timm
Image Classification • Updated • 320 • 3 -
apple/mobileclip_s2_timm
Image Classification • Updated • 599 • 6
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
CLIP Models trained using DFN-2B/DFN-5B datasets
DCLM Models + Datasets
Simple Self-Distillation
CLaRa models
Efficient Vision Encoding for Vision Language Models
MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B
A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint.
-
apple/aimv2-large-patch14-224
Image Feature Extraction • 0.3B • Updated • 1.01k • 62 -
apple/aimv2-huge-patch14-224
Image Feature Extraction • 0.7B • Updated • 118 • 13 -
apple/aimv2-1B-patch14-224
Image Feature Extraction • 1B • Updated • 107 • 9 -
apple/aimv2-3B-patch14-224
Image Feature Extraction • 3B • Updated • 69 • 4
MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities.
DataCompDR: Improved datasets for training image-text SOTA models.
-
MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
Paper • 2311.17049 • Published • 8 -
apple/mobileclip_s0_timm
Image Classification • Updated • 1.93k • 12 -
apple/mobileclip_s1_timm
Image Classification • Updated • 320 • 3 -
apple/mobileclip_s2_timm
Image Classification • Updated • 599 • 6
Benchmark for the design of efficient continual learning of image-text models over years.
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
-
apple/coreml-stable-diffusion-mixed-bit-palettization
Updated • 11 • 30 -
apple/coreml-stable-diffusion-xl-base
Text-to-Image • Updated • 11 • 70 -
apple/coreml-stable-diffusion-2-1-base
Text-to-Image • Updated • 46 • 58 -
apple/coreml-stable-diffusion-2-1-base-palettized
Text-to-Image • Updated • 14 • 20
CLIP Models trained using DFN-2B/DFN-5B datasets
AIM: Autoregressive Image Models
DCLM Models + Datasets