SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.08243 · CVPR · 2023

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

Ishan Misra, Piotr Bojanowski, Pascal Vincent, Yann Lecun, Michael Rabbat, Nicolas Ballas, Mahmoud Assran, Quentin Duval

arXiv · PDF · Open in the Atlas

Code that ran

5 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 9 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2301.08243.json · badge: /api/ran/2301.08243.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
waterdisappear/sar-jepa community
Papers with Code archive
3 ran · 7 no recorded run
facebookresearch/ijepa marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
lightly-ai/lightly community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input
facebookresearch/ijepa/src/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("5a10f46fdda5375c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/ijepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GF Ran
ran on a synthesized input · constructed an object; no result was computed
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("abc90f0c6dffd99f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
facebookresearch/ijepa/src/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("fc939725b0bb127b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/ijepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_rpe_config Ran
ran; our contract draft was wrong, not the code
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("ab8156d726620d7e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_single_rpe_config Ran
ran; our contract draft was wrong, not the code
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("b67bfbf8a86f8ae3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Attention Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("d5d4d27df91c3a11")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Block Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("6710d315e3285047")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

IJEPAPredictor Not yet run
unverified (harvested, no recorded run)
lightly-ai/lightly/lightly/models/modules/ijepa.py
code served (permissive licence) · get_code("534c33c21ec7b299")
How it ran

no invocation recorded.

MaskedAutoencoderViT Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("91e43c1af69c43ab")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

VisionTransformerPredictor Not yet run
unverified (harvested, no recorded run)
facebookresearch/ijepa/src/models/vision_transformer.py
pointer only (licence: NOASSERTION) · get_code("9d96610a96ece7b7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/ijepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

build_rpe Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("7f5fc306914d0a48")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_bucket_ids_2d Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("d5148a7973cd80a8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

iRPE Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("0a8854a10b0caba2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

iRPE_Cross Not yet run
unverified (harvested, no recorded run)
waterdisappear/sar-jepa/Pretraining/models_lomar.py
pointer only (licence: NOASSERTION) · get_code("6ea577bc7d8c4a62")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, waterdisappear/sar-jepa (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 6 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 6 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
Block
brick of this paper's assembly: model
12 other papers
5 dated earlier, 7 later · 4 only as an assembly brick
2010.11929 (2020-10)
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
2101.11986 (2021-01)
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
2103.10455 (2021-03)
3D Human Pose Estimation with Spatial and Temporal Transformers
and 9 more not named here
iRPE
brick of this paper's assembly: helper
2 other papers
1 dated earlier, 1 later
2107.14222 (2021-07)
Rethinking and Improving Relative Position Encoding for Vision Transformer
2404.08351 (2024-04)
OmniSat: Self-Supervised Modality Fusion for Earth Observation
build_rpe
brick of this paper's assembly: helper
1 other paper
1 later
2404.08351 (2024-04)
OmniSat: Self-Supervised Modality Fusion for Earth Observation
get_2d_sincos_pos_embed
brick of this paper's assembly: helper
1 other paper
1 later
2308.00566 (2023-08)
Stochastic positional embeddings improve masked image modeling
get_rpe_config
brick of this paper's assembly: helper
1 other paper
1 later
2404.08351 (2024-04)
OmniSat: Self-Supervised Modality Fusion for Earth Observation
iRPE_Cross
brick of this paper's assembly: helper
1 other paper
1 later
2404.08351 (2024-04)
OmniSat: Self-Supervised Modality Fusion for Earth Observation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Imagebased Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) sample target blocks with sufficiently large scale (semantic), and to (b) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/14 on ImageNet using 16 A100 GPUs in under 72 hours to achieve strong downstream performance across a wide range of tasks, from linear classification to object counting and depth prediction.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.08243")
get_code_for_paper("2301.08243")
have("2301.08243")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.08243.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.08243.svg)](https://syntology.ai/paper/2301.08243)

Connect an agent — have() is free.