SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.02603 · 2026

EchoJEPA: A Latent Predictive Foundation Model for Echocardiography

Bo Wang, Heather Whitney, Alif Munim, Adibvafa Fallahpour, Teodora Szasz, Ahmadreza Attarpour, River Jiang, Brana Sooriyakanthan, Maala Sooriyakanthan, Jeremy Slivnick, Barry Rubin, Wendy Tsang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-22; 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/2602.02603.json · badge: /api/ran/2602.02603.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
bowang-lab/EchoJEPA community
Papers with Code archive
10 ran · 3 no recorded run
FunctionStatusWhere it lives
Attention Ran
ran on a synthesized input
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("3b523318502aa547")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import torch.nn.functional as F

class Attention(nn.Module):

    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0.0, proj_drop=0.0, use_sdpa=True, is_causal=False):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** (-0.5)
        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop_prob = proj_drop
        self.proj_drop = nn.Dropout(proj_drop)
        self.use_sdpa = use_sdpa
        self.is_causal = is_causal

    def forward(self, x, mask=None, attn_mask=None):
        B, N, C = x.shape
        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        q, k, v = (qkv[0], qkv[1], qkv[2])
        if attn_mask is not None or self.use_sdpa:
            with torch.backends.cuda.sdp_kernel():
                x = F.scaled_dot_product_attention(q, k, v, dropout_p=self.proj_drop_prob, is_causal=self.is_causal, attn_mask=attn_mask)
                attn = None
        else:
            attn = q @ k.transpose(-2, -1) * self.scale
            attn = attn.softmax(dim=-1)
            attn = self.attn_drop(attn)
            x = attn @ v
        x = x.transpose(1, 2).reshape(B, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


INIT_ARGS = {
    'dim': 8,
    'num_heads': 2,
    'qkv_bias': False,
    'qk_scale': None,
    'attn_drop': 0.1,
    'proj_drop': 0.1,
    'use_sdpa': False,
    'is_causal': False,
}

ARGS = {
    'x': torch.randn(2, 3, 8),
    'mask': None,
    'attn_mask': None,
}

if __name__ == '__main__':
    attention = Attention(**INIT_ARGS)
    output = attention(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: {ARGS['x'].shape}")
    assert output.shape == ARGS['x'].shape, f"Shape mismatch: {output.shape} vs {ARGS['x'].shape}"
    print("Success!")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
DropPath Ran
ran on a synthesized input · constructed an object; no result was computed
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("367c364be6605f4c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, DropPath: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from timm.models.layers import drop_path

torch.manual_seed(0)

ARGS = {
    'drop_prob': 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DropPath — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a DropPath output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
RoPEAttention Ran
ran on a synthesized input · constructed an object; no result was computed
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("9336810fe7b340a4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, RoPEAttention: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Build minimal valid arguments for RoPEAttention.__init__
ARGS = {
    'dim': 24,
    'num_heads': 8,
    'qkv_bias': False,
    'qk_scale': None,
    'attn_drop': 0.0,
    'proj_drop': 0.0,
    'use_sdpa': True,
    'grid_size': 14,
    'is_causal': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RoPEAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RoPEAttention output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
SwiGLUFFN Ran
ran on a synthesized input · constructed an object; no result was computed
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("a8eae2afc08cd63e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, SwiGLUFFN: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "in_features": 4,
    "hidden_features": 8,
    "out_features": 3,
    "act_layer": nn.SiLU,
    "drop": 0.0,
    "wide_silu": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SwiGLUFFN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SwiGLUFFN output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
VisionTransformerPredictor Ran
ran on a synthesized input · constructed an object; no result was computed
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("6a8400799234eedd")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, VisionTransformerPredictor: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math

torch.manual_seed(0)

# Build minimal supporting classes/modules
class SimpleMLPHead(nn.Module):
    def __init__(self, in_features, num_classes):
        super().__init__()
        self.fc = nn.Linear(in_features, num_classes)
    
    def forward(self, x):
        return self.fc(x)

class SimplePatchEmbedding(nn.Module):
    def __init__(self, img_size, patch_size, in_channels, embed_dim):
        super().__init__()
        self.proj = nn.Linear(in_channels * patch_size * patch_size, embed_dim)
    
    def forward(self, x):
        # x shape: (B, C, H, W)
        B, C, H, W = x.shape
        # Flatten to (B, num_patches, embed_dim)
        x = x.reshape(B, -1)
        x = self.proj(x)
        return x.unsqueeze(1)

class SimpleTransformerBlock(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.norm = nn.LayerNorm(dim)
        self.mlp = nn.Linear(dim, dim)
    
    def forward(self, x, **kwargs):
        return x + self.mlp(self.norm(x))

class SimpleEncoder(nn.Module):
    def __init__(self, dim, depth):
        super().__init__()
        self.blocks = nn.ModuleList([
            SimpleTransformerBlock(dim) for _ in range(depth)
        ])
    
    def forward(self, x, **kwargs):
        for block in self.blocks:
            x = block(x, **kwargs)
        return x

class SimpleBackbone(nn.Module):
    def __init__(self, embed_dim, depth):
        super().__init__()
        self.encoder = SimpleEncoder(embed_dim, depth)
        self.norm = nn.LayerNorm(embed_dim)
    
    def forward(self, x):
        x = self.encoder(x)
        x = self.norm(x)
        return x

class VisionTransformerPredictor(nn.Module):
    def __init__(self, backbone, head, embed_dim=768, num_patches=196):
        super().__init__()
        self.backbone = backbone
        self.head = head
        self.embed_dim = embed_dim
        self.num_patches = num_patches
    
    def forward(self, x, mask=None):
        # x: (B, C, H, W)
        B = x.shape[0]
        # Get backbone features
        features = self.backbone(x)
        # Average pool over patch dimension if needed
        if features.dim() == 3:
            features = features.mean(dim=1)
        # Pass through head
        output = self.head(features)
        return output

# Create minimal instantiations
embed_dim = 64
depth = 2
num_classes = 10
num_patches = 196

backbone = SimpleBackbone(embed_dim=embed_dim, depth=depth)
head = SimpleMLPHead(in_features=embed_dim, num_classes=num_classes)

predictor = VisionTransformerPredictor(
    backbone=backbone,
    head=head,
    embed_dim=embed_dim,
    num_patches=num_patches
)

# Create sample input
x = torch.randn(2, 3, 16, 16)
mask = None

ARGS = {
    "backbone": backbone,
    "head": head,
    "embed_dim": embed_dim,
    "num_patches": num_patches
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type VisionTransformerPredictor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a VisionTransformerPredictor output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
_no_grad_trunc_normal_ Ran
ran; our contract draft was wrong, not the code
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("e7c3b600144accb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import math

torch.manual_seed(0)

# Create a small tensor to be modified
tensor = torch.empty(2, 4)

# Define parameters for truncated normal distribution
mean = 0.0
std = 1.0
a = -2.0  # lower bound
b = 2.0   # upper bound

ARGS = {
    "tensor": tensor,
    "mean": mean,
    "std": std,
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_1d_sincos_pos_embed_from_grid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("f6dd6f9161d38af6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Setup for get_1d_sincos_pos_embed_from_grid
embed_dim = 8  # must be even
pos = np.array([0.0, 1.0, 2.0, 3.0])  # M=4 positions

ARGS = {
    "embed_dim": embed_dim,
    "pos": pos
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 8) — shape (4, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_2d_sincos_pos_embed Ran
ran, honoured the contract we drafted
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("49954bacf90c9e2f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (16, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "embed_dim": 8,
    "grid_size": 4,
    "cls_token": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (16, 8) — shape (16, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_3d_sincos_pos_embed Ran
ran, honoured the contract we drafted
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("e7efdd433b96807d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (12, 8) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    'embed_dim': 8,
    'grid_size': 2,
    'grid_depth': 3,
    'cls_token': False,
    'uniform_power': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (12, 8) — shape (12, 8) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
trunc_normal_ Ran
ran; our contract draft was wrong, not the code
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("4e02bf1d1efcb33d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import math

torch.manual_seed(0)

# Create a small tensor to be initialized
tensor = torch.empty(2, 4)

# Define arguments for trunc_normal_
ARGS = {
    "tensor": tensor,
    "mean": 0.0,
    "std": 1.0,
    "a": -2.0,
    "b": 2.0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
Block Not yet run
unverified (harvested, no recorded run)
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("0785f467b1ee8f5f")
How it ran

no invocation recorded.

apply_masks Not yet run
unverified (harvested, no recorded run)
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("bf083ed6ad81d69e")
How it ran

no invocation recorded.

rotate_queries_or_keys Not yet run
unverified (harvested, no recorded run)
bowang-lab/EchoJEPA/src/models/predictor.py
code served (permissive licence) · get_code("de29ea4d712b0681")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 3 later) and 9 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
trunc_normal_
brick of this paper's assembly: helper
160 other papers
154 dated earlier, 3 the same month, 3 later · 36 only as an assembly brick
1911.10194 (2019-11)
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
2005.10242 (2020-05)
Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
2007.12911 (2020-07)
Tighter risk certificates for neural networks
and 157 more not named here
get_1d_sincos_pos_embed_from_grid
brick of this paper's assembly: helper
26 other papers
23 dated earlier, 3 later · 11 only as an assembly brick
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
2207.06405 (2022-07)
Masked Autoencoders that Listen
2210.10716 (2022-10)
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
and 23 more not named here
DropPath
brick of this paper's assembly: helper
25 other papers
22 dated earlier, 2 the same month, 1 later · 14 only as an assembly brick
2106.08254 (2021-06)
BEIT: BERT Pre-Training of Image Transformers
2111.06377 (2021-11)
Masked Autoencoders Are Scalable Vision Learners
2201.12096 (2022-01)
Mask-based Latent Reconstruction for Reinforcement Learning
and 22 more not named here
apply_masks
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2404.08471 (2024-04)
Revisiting Feature Prediction for Learning Visual Representations from Video

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

Foundation models for echocardiography often struggle to disentangle anatomical signal from the stochastic speckle and acquisition artifacts inherent to ultrasound. We present EchoJEPA, a foundation model trained on 18 million echocardiograms across 300K patients, representing the largest pretraining corpus for this modality to date. By leveraging a latent predictive objective, Echo-JEPA learns robust anatomical representations that ignore speckle noise. We validate this using a novel multi-view probing framework with frozen backbones, where EchoJEPA outperforms leading baselines by approximately 20% in left ventricular ejection fraction (LVEF) estimation and 17% in right ventricular systolic pressure (RVSP) estimation. The model also exhibits remarkable sample efficiency, reaching 79% view classification accuracy with only 1% of labeled data versus 42% for the best baseline trained on 100%. Crucially, EchoJEPA demonstrates superior generalization, degrading by only 2% under physicsinformed acoustic perturbations compared to 17% for competitors. Most remarkably, its zero-shot performance on pediatric patients surpasses fully fine-tuned baselines, establishing latent prediction as a superior paradigm for robust, generalizable medical AI.

For agents

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

get_harvested_code_for_paper("2602.02603")
get_code_for_paper("2602.02603")
have("2602.02603")

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

curl https://syntology.ai/api/ran/2602.02603.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.02603.svg)](https://syntology.ai/paper/2602.02603)

Connect an agent — have() is free.