SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.18459 · ECCV · 2024

Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild

Seunghoon Hong, Chong Luo, Seongwoong Cho, Donggyun Kim, Semin Kim

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 2 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 2 failures of our instrument; 1 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/2404.18459.json · badge: /api/ran/2404.18459.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
gitgyun/chameleon canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
linear_sample Ran
ran, honoured the contract we drafted
gitgyun/chameleon/dataset/augmentation.py
code served (permissive licence) · get_code("02a0579731cda8c1")
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 float, 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 random

def linear_sample(p_range):
    if isinstance(p_range, float):
        return p_range
    else:
        return p_range[0] + random.random() * (p_range[1] - p_range[0])

# Test with a float value
ARGS = {
    "p_range": 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
log_sample Ran
ran, honoured the contract we drafted
gitgyun/chameleon/dataset/augmentation.py
code served (permissive licence) · get_code("98a7bede28cc1c47")
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 float, 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 random
import math

# The function log_sample takes a parameter p_range which can be either:
# 1. A float (scalar value)
# 2. A tuple/list with two elements representing a range [min, max]

# Test case 1: p_range as a float
ARGS = {
    "p_range": 0.5
}

# Alternative test case with a range tuple (commented out, but showing the other valid input)
# ARGS = {
#     "p_range": (0.001, 0.1)
# }

# The current ARGS uses a float, which is a valid input to log_sample
# Uncommenting the alternative would also work - it would sample from the range [0.001, 0.1]
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
normalize Ran
ran, violated the contract we drafted
gitgyun/chameleon/dataset/augmentation.py
code served (permissive licence) · get_code("f1aba098ff5cbc05")
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 1, dtype family float, shape (6,) 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)

# The function 'normalize' takes a tensor x and normalizes it to [0, 1] range
# It uses: x.max(), x.min(), and arithmetic operations
# We need to provide a tensor with at least one element

x = torch.tensor([1.0, 2.5, 0.5, 3.0, 1.5, 2.0], dtype=torch.float32)

ARGS = {
    "x": x
}
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 1, dtype family float, shape (6,) — shape (6,) 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
spatial_softmax_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gitgyun/chameleon/train/loss.py
code served (permissive licence) · get_code("1a9f1b3ff0f40a80")
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
import torch.nn.functional as F
from einops import rearrange

torch.manual_seed(0)

# Case 1: 6D tensors (B T N C H W)
B, T, N, C, H, W = 2, 3, 4, 5, 6, 7

Y_pred_6d = torch.randn(B, T, N, C, H, W)
Y_6d = torch.randn(B, T, N, C, H, W)
M_6d = torch.rand(B, T, N, C, H, W) > 0.5

ARGS = {
    'Y_pred': Y_pred_6d,
    'Y': Y_6d,
    'M': M_6d,
    'reduction': 'mean',
    'scaled': False
}
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 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
spatio_channel_softmax_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gitgyun/chameleon/train/loss.py
code served (permissive licence) · get_code("056b10a025a6480e")
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
import torch.nn.functional as F
from einops import rearrange

torch.manual_seed(0)

# Construct tensors with distinct dimensions for clarity
# Y_pred: (B=2, T=3, N=4, C=5, H=6, W=7)
B, T, N, C, H, W = 2, 3, 4, 5, 6, 7

Y_pred = torch.randn(B, T, N, C, H, W)
Y = torch.randint(0, C, (B, T, N, C, H, W)).float()
M = torch.randint(0, 2, (B, T, N, C, H, W)).float()

ARGS = {
    'Y_pred': Y_pred,
    'Y': Y,
    'M': M,
    'reduction': 'mean'
}
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 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
str2bool Ran
ran, violated the contract we drafted
gitgyun/chameleon/args.py
pointer only (licence: MIT); the stored copy get_code serves, from SeongwoongCho/meta-controller, is pointer only (licence: NONE) · get_code("0d5ccf3e418960d3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from SeongwoongCho/meta-controller, and GitHub detected no licence in that repository when it was checked. 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.

parse_args Not yet run
unverified (harvested, no recorded run)
gitgyun/chameleon/args.py
code served (permissive licence) · get_code("c0ed6e00d7d1220d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 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
str2bool 2 other papers
1 dated earlier, 1 later
2303.14969 (2023-03)
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
2412.12147 (2024-12)
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
linear_sample 1 other paper
1 dated earlier
2303.14969 (2023-03)
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
log_sample 1 other paper
1 dated earlier
2303.14969 (2023-03)
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
normalize 1 other paper
1 dated earlier
2303.14969 (2023-03)
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching

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

Fig. 1: Chameleon is a data-efficient generalist that can adapt to various unseen dense visual prediction tasks in the wild with arbitrary output structures using a handful of examples (dozens). It can also learn to utilize multi-modal inputs and user-interactions.

For agents

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

get_harvested_code_for_paper("2404.18459")
get_code_for_paper("2404.18459")
have("2404.18459")

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

curl https://syntology.ai/api/ran/2404.18459.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.18459.svg)](https://syntology.ai/paper/2404.18459)

Connect an agent — have() is free.