SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.13232 · 2024

A Touch, Vision, and Language Dataset for Multimodal Alignment

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2402.13232.json · badge: /api/ran/2402.13232.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
Max-Fu/tvl canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
tac_padding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Max-Fu/tvl/tvl_enc/tacvis.py
code served (permissive licence) · get_code("ff9c8cb4ab823fdf")
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 3, dtype family float, shape (3, 4, 5) 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 numpy as np
from PIL import Image
import torchvision.transforms.functional as TF

torch.manual_seed(0)

# Test with a torch.Tensor input
# The function expects shape [C, H, W] based on how it accesses tac.shape[1:]
tac_tensor = torch.randn(3, 4, 5)  # 3 channels, 4 height, 5 width

ARGS = {
    "tac": tac_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch, torchvision — 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, shape (3, 4, 5) — shape (3, 4, 5) 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
to_pil Ran
ran; our contract draft was wrong, not the code
Max-Fu/tvl/tvl_enc/tacvis.py
code served (permissive licence) · get_code("ea1a61a34df40d38")
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 Image. 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 numpy as np
from PIL import Image

torch.manual_seed(0)

# Create a small valid tensor for the function
# The function expects a tensor with shape (C, H, W) where:
# - img.numpy() converts it to numpy
# - multiplication by 255 scales values
# - np.moveaxis(arr, 0, -1) moves channel axis from 0 to -1
# - Image.fromarray expects (H, W, C) format with uint8 values

# Create a tensor with shape (3, 4, 5) representing (channels, height, width)
# Values should be in [0, 1] range for proper scaling to [0, 255]
img_tensor = torch.rand(3, 4, 5)

ARGS = {
    "img": img_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
unnormalize_fn Ran
ran; our contract draft was wrong, not the code
Max-Fu/tvl/tvl_enc/tacvis.py
code served (permissive licence) · get_code("9a73cbb66f31231c")
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 Compose. 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 torchvision.transforms as transforms

torch.manual_seed(0)

ARGS = {
    "mean": (0.485, 0.456, 0.406),
    "std": (0.229, 0.224, 0.225),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Compose — a Compose output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Compose 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
construct_top_k_mask Not yet run
unverified (harvested, no recorded run)
Max-Fu/tvl/tvl_enc/loss.py
code served (permissive licence) · get_code("4b3575a3a594d46a")
How it ran

no invocation recorded.

handle_flash_attn Not yet run
unverified (harvested, no recorded run)
Max-Fu/tvl/tvl_enc/transformer_utils.py
code served (permissive licence) · get_code("22df917b46daf58b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
to_pil 1 other paper
1 later
2408.15980 (2024-08)
In-Context Imitation Learning via Next-Token Prediction
unnormalize_fn 1 other paper
1 later
2408.15980 (2024-08)
In-Context Imitation Learning via Next-Token Prediction

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Touch is an important sensing modality for humans, but it has not yet been incorporated into a multimodal generative language model. This is partially due to the difficulty of obtaining natural language labels for tactile data and the complexity of aligning tactile readings with both visual observations and language descriptions. As a step towards bridging that gap, this work introduces a new dataset of 44K in-the-wild vision-touch pairs, with English language labels annotated by humans (10%) and textual pseudo-labels from GPT-4V (90%). We use this dataset to train a vision-language-aligned tactile encoder for open-vocabulary classification and a touch-vision-language (TVL) model for text generation using the trained encoder. Results suggest that by incorporating touch, the TVL model improves (+29% classification accuracy) touch-vision-language alignment over existing models trained on any pair of those modalities. Although only a small fraction of the dataset is human-labeled, the TVL model demonstrates improved visual-tactile understanding over GPT-4V (+12%) and open-source vision-language models (+32%) on a new touch-vision understanding benchmark. Code and data: https://tactile-vlm.github.io.

For agents

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

get_harvested_code_for_paper("2402.13232")
get_code_for_paper("2402.13232")
have("2402.13232")

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

curl https://syntology.ai/api/ran/2402.13232.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.13232.svg)](https://syntology.ai/paper/2402.13232)

Connect an agent — have() is free.