SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.08303 · CVPR · 2025

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

Valeo Ai, Spyros Gidaris, Efstathios Karypidis, Ioannis Kakogeorgiou, Nikos Komodakis, Athena Archimedes, Greece Research Center

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 2 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/2501.08303.json · badge: /api/ran/2501.08303.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
sta8is/futurist marked official in Papers with Code
Papers with Code archive
6 ran · 2 no recorded run
FunctionStatusWhere it lives
AddBroadcastPosEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("8a974cbe1001d2e3")
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, AddBroadcastPosEmbed: 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)

# The AddBroadcastPosEmbed module expects:
# - shape: tuple of integers representing the spatial dimensions
# - embd_dim: embedding dimension (must be divisible by len(shape))
# - dim: either -1 or 1 (the dimension to concatenate embeddings on)

# Let's create a simple 2D case
shape = (4, 3)  # 2D spatial dimensions with distinct sizes
n_dim = len(shape)  # 2
embd_dim = 8  # divisible by 2

ARGS = {
    'shape': shape,
    'embd_dim': embd_dim,
    'dim': -1
}
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 AddBroadcastPosEmbed — 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 AddBroadcastPosEmbed 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
Attention Ran
ran on a synthesized input
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("f7968fce35e007d8")
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 tuple. 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

INIT_ARGS = {
    'embed_dim': 4,
    'num_heads': 2,
    'dropout': 0.1,
}

ARGS = {
    'x': torch.randn(2, 3, 4),
    'mask': None,
}

if __name__ == '__main__':
    attention = nn.Module.__new__(type('Attention', (nn.Module,), {
        '__init__': lambda self, embed_dim, num_heads, dropout=0.0: (
            super(type(self), self).__init__(),
            setattr(self, 'dim', embed_dim),
            setattr(self, 'mha', nn.MultiheadAttention(embed_dim, num_heads=num_heads, dropout=dropout, batch_first=True, bias=True))
        ),
        'forward': lambda self, x, mask=None: (
            self.mha(x, x, x, attn_mask=mask) if mask is not None else self.mha(x, x, x)
        )
    }))
    
    attention.__init__(**INIT_ARGS)
    attention_value, attention_weight = attention(**ARGS)
    print(f"Attention value shape: {attention_value.shape}")
    print(f"Attention weight shape: {attention_weight.shape}")
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 tuple — a tuple output has no array shape of its own; none is 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
FeedForward Ran
ran on a synthesized input · constructed an object; no result was computed
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("73f0b6932d0b0069")
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, FeedForward: 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 = {
    "dim": 4,
    "hidden_dim": 8,
    "dropout": 0.1,
}
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 FeedForward — 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 FeedForward 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
PreNorm Ran
ran on a synthesized input · constructed an object; no result was computed
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("2cd986aaeac6b22b")
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, PreNorm: 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)

# Create a simple function module that will be used in PreNorm
class SimpleFunction(nn.Module):
    def __init__(self, dim):
        super().__init__()
        self.linear = nn.Linear(dim, dim)
    
    def forward(self, x, **kwargs):
        return self.linear(x)

# Define the arguments for PreNorm
dim = 4
fn = SimpleFunction(dim)

ARGS = {
    "dim": dim,
    "fn": fn
}
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 PreNorm — 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 PreNorm 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
TransformerEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("974919609ba7f2ff")
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, TransformerEncoder: 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 = {
    "dim": 4,
    "depth": 2,
    "heads": 2,
    "mlp_dim": 8,
    "dropout": 0.1
}
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 TransformerEncoder — 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 TransformerEncoder 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
TransformerEncoderSeperableAttention Ran
ran on a synthesized input · constructed an object; no result was computed
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("36d663d1929fba10")
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, TransformerEncoderSeperableAttention: 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)

# Define ARGS dict with all parameters for TransformerEncoderSeperableAttention
ARGS = {
    "dim": 4,
    "depth": 2,
    "heads": 2,
    "mlp_dim": 8,
    "dropout": 0.1,
    "window_size": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TransformerEncoderSeperableAttention — 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 TransformerEncoderSeperableAttention 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
Futurist Not yet run
unverified (harvested, no recorded run)
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("da9bf75a3bed9d36")
How it ran

no invocation recorded.

MaskTransformer Not yet run
unverified (harvested, no recorded run)
sta8is/futurist/src/futurist.py
code served (permissive licence) · get_code("ad84686f18317ddd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
PreNorm
brick of this paper's assembly: helper
43 other papers
38 dated earlier, 5 later · 38 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
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
and 40 more not named here
Attention
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
2412.11673 (2024-12)
DINO-Foresight: Looking into the Future with DINO
FeedForward
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2412.11673 (2024-12)
DINO-Foresight: Looking into the Future with DINO
TransformerEncoder
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
2412.11673 (2024-12)
DINO-Foresight: Looking into the Future with DINO
TransformerEncoderSeperableAttention
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
2412.11673 (2024-12)
DINO-Foresight: Looking into the Future with DINO

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

5 IACM-Forth Inputs Predictions Oracle Figure 1. Our framework predicts future semantic segmentation and depth maps using a multimodal transformer architecture. Leveraging masked visual modeling and cross-modal fusion, it excels in future semantic prediction, achieving state-of-the-art results in both tasks.

For agents

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

get_harvested_code_for_paper("2501.08303")
get_code_for_paper("2501.08303")
have("2501.08303")

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

curl https://syntology.ai/api/ran/2501.08303.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.08303.svg)](https://syntology.ai/paper/2501.08303)

Connect an agent — have() is free.