Updated 2 h ago · first seen 11 Sept 2026
company_01M293SNYDKSFZQFER1GB4EXKN
- Country
- US
- T2 · 2 h ago
- Founded
- 1976
- T2 · 2 h ago
- HQ
- Cupertino, California
- T2 · 2 h ago
- Kind
- company
- T2 · 2 h ago
Specification
- Country
- US
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- Domains
- apple.com, machinelearning.apple.com
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- Founded
- 1976
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- GitHub org
- apple
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- Headquarters
- Cupertino, California
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- Hugging Face org
- apple
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- Kind
- company
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
8
Source tiers
T28
Freshest observation
2 h ago
Conflicts
None
Papers 10
published 11 Sept 2026authors 5arXiv 2609.03377
- Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question AnsweringAppleActive
published 11 Sept 2026authors 5arXiv 2609.09973
published 11 Sept 2026authors 5arXiv 2609.02796
published 2 Sept 2026authors 2arXiv 2609.01215
published 28 Aug 2026authors 3arXiv 2608.26133
- LLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic BeliefsAppleActive
published 28 Aug 2026authors 5arXiv 2605.06915
published 27 Aug 2026authors 5arXiv 2608.23812
published 26 Aug 2026authors 5arXiv 2608.23943
- IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model PretrainingAppleActive
published 26 Aug 2026authors 5arXiv 2503.05920
published 26 Aug 2026authors 3arXiv 2608.23911
Repositories 1
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
stars 7,417
| Model | Params | Context | Openness | Released | Status | Quality |
|---|---|---|---|---|---|---|
| Sharp | — | — | open-weights | 12 Dec 2025 | active | |
| FastVLM-1.5B | 1.91B | — | open-weights | 25 Aug 2025 | active | |
| FastVLM-0.5B | 758.8M | — | open-weights | 25 Aug 2025 | active | |
| DepthPro-hf | 952M | — | open-weights | 27 Nov 2024 | active | |
| aimv2-large-patch14-224-lit | 436.7M | — | open-weights | 20 Nov 2024 | active | |
| coreml-mobileclip | — | — | open-weights | 21 Oct 2024 | active | |
| DepthPro | — | — | open-weights | 3 Oct 2024 | active | |
| DFN2B-CLIP-ViT-L-14-39B | 39B | — | open-weights | 8 Jul 2024 | active | |
| MobileCLIP-S1-OpenCLIP | — | — | open-weights | 7 Jun 2024 | active | |
| MobileCLIP-S2-OpenCLIP | — | — | open-weights | 7 Jun 2024 | active | |
| OpenELM-270M | 271.5M | — | open-weights | 12 Apr 2024 | active | |
| OpenELM-1_1B-Instruct | 1.08B | — | open-weights | 12 Apr 2024 | active | |
| DFN2B-CLIP-ViT-B-16 | — | — | open-weights | 31 Oct 2023 | active | |
| DFN2B-CLIP-ViT-L-14 | — | — | open-weights | 30 Oct 2023 | active | |
| DFN5B-CLIP-ViT-H-14 | — | — | open-weights | 30 Oct 2023 | active | |
| DFN5B-CLIP-ViT-H-14-378 | — | — | open-weights | 30 Oct 2023 | active | |
| mobilevitv2-1.0-imagenet1k-256 | — | — | open-weights | 5 Jun 2023 | active | |
| deeplabv3-mobilevit-xx-small | — | — | open-weights | 30 May 2022 | active | |
| mobilevit-xx-small | — | — | open-weights | 30 May 2022 | active | |
| mobilevit-small | — | — | open-weights | 30 May 2022 | active |
This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025
stars 7,417
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Countrycountry1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| US | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Domainsdomains1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| apple.com, machinelearning.apple.com | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Foundedfounded1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 1976 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
GitHub orggithub_org1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| apple | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Headquartersheadquarters1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Cupertino, California | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Hugging Face orghf_org1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| apple | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Kindorg_kind1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| company | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://www.apple.com | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New model: deeplabv3-mobilevit-xx-small (Apple)
huggingfaceNew model: mobilevitv2-1.0-imagenet1k-256 (Apple)
huggingfaceNew model: aimv2-large-patch14-224-lit (Apple)
huggingfaceNew paper: Luce: Relightable Gaussians for 3D Asset Generation (Apple)
apple_ml- New paperPaperIDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model PretrainingApple
New paper: IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining (Apple)
apple_ml New paper: PROOF-Gen: From Optimized Data to Better Distillation (Apple)
apple_ml- New paperPaperFrom Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge AnswersApple
New paper: From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers (Apple)
apple_ml New paper: Agent Seer: Synthesizing Scenarios from Specification Understanding (Apple)
apple_ml- New paperPaperLLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic BeliefsApple
New paper: LLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic Beliefs (Apple)
apple_ml New paper: REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs (Apple)
apple_mlNew paper: SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign (Apple)
apple_ml- New paperPaperPutting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question AnsweringApple
New paper: Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering (Apple)
apple_ml
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Apple Machine Learning Research | machinelearning.apple.com/rss.xml | feed | T1· Official | 1 h ago | 1 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=apple&p=0&sort=downloads | listing | T2· Quality secondary | 1 h ago | 2 |
| GitHub public repositories (HTML, releases.atom, raw files) | github.com/apple-aiml-research/ml-fastvlm | repository | T2· Quality secondary | 1 h ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.