SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.02693 · 2024

Diffusion-based Visual Anagram as Multi-task Learning

arXiv · PDF · Open in the Atlas

Code that ran

5 of 12 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 7 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/2412.02693.json · badge: /api/ran/2412.02693.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
pixtella/anagram-mtl canonical (classifier label)
classifier basis: census
5 ran · 7 no recorded run
FunctionStatusWhere it lives
betas_for_alpha_bar Ran
ran, honoured the contract we drafted
pixtella/anagram-mtl/glide_text2im/gaussian_diffusion.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from NVlabs/DiffPure, is pointer only (licence: NOASSERTION) · get_code("2ab2316ac6fdd869")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from NVlabs/DiffPure, and GitHub could not classify the licence of that repository (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_beta_schedule Ran
ran, honoured the contract we drafted
pixtella/anagram-mtl/glide_text2im/gaussian_diffusion.py
code served (permissive licence) · get_code("0996aa0f716afd2d")
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 1, dtype family float, shape (1000,) 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 = {
    'beta_schedule': 'linear',
    'beta_start': 0.0001,
    'beta_end': 0.02,
    'num_diffusion_timesteps': 1000,
}
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 1, dtype family float, shape (1000,) — shape (1000,) 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_named_beta_schedule Ran
ran, honoured the contract we drafted
pixtella/anagram-mtl/glide_text2im/gaussian_diffusion.py
code served (permissive licence) · get_code("14e2c5e6c9d5ba6c")
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 1, dtype family float, shape (100,) 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 math
import numpy as np

ARGS = {
    'schedule_name': 'linear',
    'num_diffusion_timesteps': 100,
}
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 1, dtype family float, shape (100,) — shape (100,) 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
noise_vector_rectification Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pixtella/anagram-mtl/visual_anagrams/mtl.py
code served (permissive licence) · get_code("f4c92d5b3b58db03")
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 0, dtype family float, shape () 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

torch.manual_seed(0)

# Analyze function usage:
# - noise_pred: torch.Tensor with shape (b, t, c, h, w), indexed as [0, i], [0, j]
# - predicted_variance: torch.Tensor with shape (b, t, c, h, w), viewed to (b, t, -1)
# - alpha: indexed as alpha[0, i, 0] and alpha[0, j, 0], so shape at least (1, t, 1)

b = 2
t = 3
c = 4
h = 5
w = 6

noise_pred = torch.randn(b, t, c, h, w)
predicted_variance = torch.randn(b, t, c, h, w)
alpha = torch.randn(1, t, 1)

ARGS = {
    "noise_pred": noise_pred,
    "predicted_variance": predicted_variance,
    "alpha": alpha,
}
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 0, dtype family float, shape () — shape () 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
zero_module Ran
ran; our contract draft was wrong, not the code
pixtella/anagram-mtl/glide_text2im/nn.py
code served (permissive licence) · get_code("129b804760b3115f")
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 SimpleModule. 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 module with some parameters
class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.conv = nn.Conv1d(2, 2, 3)
    
    def forward(self, x):
        return x

module = SimpleModule()

# Verify the module has non-zero parameters before zeroing
for p in module.parameters():
    assert p.abs().sum() > 0, "Parameters should be non-zero initially"

ARGS = {
    "module": module
}
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 SimpleModule — a SimpleModule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModule 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
avg_pool_nd Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/glide_text2im/nn.py
code served (permissive licence) · get_code("ecd0fc28815b65ae")
How it ran

no invocation recorded.

conv_nd Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/glide_text2im/nn.py
code served (permissive licence) · get_code("fe4eb545bbb728e0")
How it ran

no invocation recorded.

fetch_file_cached Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/glide_text2im/download.py
code served (permissive licence) · get_code("0ded220539a3a3ea")
How it ran

no invocation recorded.

load_checkpoint Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/glide_text2im/download.py
code served (permissive licence) · get_code("0537243f2ce113e1")
How it ran

no invocation recorded.

register_attention_control Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/attn_utils.py
code served (permissive licence) · get_code("0deefdc623c31f3d")
How it ran

no invocation recorded.

sample_stage_1 Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/visual_anagrams/samplers_mtl.py
code served (permissive licence) · get_code("9956e18fb3ff0e4a")
How it ran

no invocation recorded.

sample_stage_2 Not yet run
unverified (harvested, no recorded run)
pixtella/anagram-mtl/visual_anagrams/samplers_mtl.py
code served (permissive licence) · get_code("5d1a6c4919453f7c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 5 the same month, 6 later) and 4 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
zero_module 196 other papers
162 dated earlier, 3 the same month, 30 later, 1 same year, order not determinable · 49 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
and 193 more not named here
conv_nd 121 other papers
101 dated earlier, 1 the same month, 16 later, 3 same year, order not determinable · 32 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 118 more not named here
avg_pool_nd 113 other papers
97 dated earlier, 1 the same month, 12 later, 3 same year, order not determinable · 31 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2110.11291 (2021-10)
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory
and 110 more not named here
betas_for_alpha_bar 92 other papers
83 dated earlier, 7 later, 2 same year, order not determinable · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
and 89 more not named here
get_beta_schedule 31 other papers
23 dated earlier, 1 the same month, 7 later
2202.09671 (2022-02)
TRUNCATED DIFFUSION PROBABILISTIC MODELS AND DIFFUSION-BASED ADVERSARIAL AUTO-ENCODERS
2210.07574 (2022-10)
Is synthetic data from generative models ready for image recognition?
2306.02562 (2023-06)
Video Diffusion Models with Local-Global Context Guidance
and 28 more not named here
get_named_beta_schedule 25 other papers
19 dated earlier, 1 the same month, 5 later
2210.07574 (2022-10)
Is synthetic data from generative models ready for image recognition?
2306.02562 (2023-06)
Video Diffusion Models with Local-Global Context Guidance
2306.12511 (2023-06)
Semi-Implicit Denoising Diffusion Models (SIDDMs)
and 22 more not named here
fetch_file_cached 2 other papers
2 dated earlier
2210.07574 (2022-10)
Is synthetic data from generative models ready for image recognition?
2212.08751 (2022-12)
Point-E: A System for Generating 3D Point Clouds from Complex Prompts
load_checkpoint 1 other paper
1 dated earlier
2210.07574 (2022-10)
Is synthetic data from generative models ready for image recognition?

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

Visual anagrams are images that change appearance upon transformation, like flipping or rotation. With the advent of diffusion models, generating such optical illusions can be achieved by averaging noise across multiple views during the reverse denoising process. However, we observe two critical failure modes in this approach: (i) concept segregation, where concepts in different views are independently generated, which can not be considered a true anagram, and (ii) concept domination, where certain concepts overpower others. In this work, we cast the visual anagram generation problem in a multi-task learning setting, where different viewpoint prompts are analogous to different tasks,and derive denoising trajectories that align well across tasks simultaneously. At the core of our designed framework are two newly introduced techniques, where (i) an anti-segregation optimization strategy that promotes overlap in cross-attention maps between different concepts, and (ii) a noise vector balancing method that adaptively adjusts the influence of different tasks. Additionally, we observe that directly averaging noise predictions yields suboptimal performance because statistical properties may not be preserved, prompting us to derive a noise variance rectification method. Extensive qualitative and quantitative experiments demonstrate our method's superior ability to generate visual anagrams spanning diverse concepts.

For agents

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

get_harvested_code_for_paper("2412.02693")
get_code_for_paper("2412.02693")
have("2412.02693")

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

curl https://syntology.ai/api/ran/2412.02693.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.02693.svg)](https://syntology.ai/paper/2412.02693)

Connect an agent — have() is free.