SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2209.00349 · 2022

FLAME: Free-form Language-based Motion Synthesis & Editing

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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 3 have no contract verdict; 0 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/2209.00349.json · badge: /api/ran/2209.00349.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
kakaobrain/flame canonical (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
FunctionStatusWhere it lives
collate_motion Ran
ran on a synthesized input
kakaobrain/flame/src/utils/collate.py
code served (permissive licence) · get_code("dc0f73f0773cb55e")
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 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 numpy as np
import torch

torch.manual_seed(0)

# Create sample motion data with distinct dimensions
# rotation_6d: (time_steps, num_joints, 6) - 6D rotation representation
# translation: (time_steps, 3) - 3D translation
# annotation: string or list
# motion_length: int - actual length of motion

# Create batch with 2 samples of different lengths
sample1_rotation = np.random.randn(5, 4, 6).astype(np.float32)  # 5 frames, 4 joints, 6D rotation
sample1_translation = np.random.randn(5, 3).astype(np.float32)  # 5 frames, 3D translation
sample1_annotation = "walk"
sample1_length = 5

sample2_rotation = np.random.randn(3, 4, 6).astype(np.float32)  # 3 frames (shorter)
sample2_translation = np.random.randn(3, 3).astype(np.float32)  # 3 frames
sample2_annotation = "run"
sample2_length = 3

# Construct data list for collate function
data = [
    (sample1_rotation, sample1_translation, sample1_annotation, sample1_length),
    (sample2_rotation, sample2_translation, sample2_annotation, sample2_length),
]

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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: none by the harness; any seed is in the setup block
compute_ape_ave Ran
ran on a synthesized input
kakaobrain/flame/src/utils/eval_util.py
code served (permissive licence) · get_code("b076a6b4fc3b1c2e")
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 dict. 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 numpy as np

# Create small sample data matching the function's expectations
num_frames = 5  # Number of frames (time steps)
num_joints = 22  # Number of joints (based on connectivity_map max index + 1)
num_dims = 3  # xyz coordinates

# Generate sample generated motion data
gen_joints_xyz = np.random.randn(num_frames, num_joints, num_dims).astype(np.float32)
gen_translation = np.random.randn(num_frames, 3).astype(np.float32)

# Generate sample ground truth motion data
gt_joints_xyz = np.random.randn(num_frames, num_joints, num_dims).astype(np.float32)
gt_translation = np.random.randn(num_frames, 3).astype(np.float32)

# Create metadata entries
meta_1 = {
    'gen_joints_xyz': gen_joints_xyz,
    'translation': gen_translation,
    'gt_joints_xyz': gt_joints_xyz,
    'gt_translation': gt_translation
}

# Create a second metadata entry with different values
gen_joints_xyz_2 = np.random.randn(num_frames, num_joints, num_dims).astype(np.float32)
gen_translation_2 = np.random.randn(num_frames, 3).astype(np.float32)
gt_joints_xyz_2 = np.random.randn(num_frames, num_joints, num_dims).astype(np.float32)
gt_translation_2 = np.random.randn(num_frames, 3).astype(np.float32)

meta_2 = {
    'gen_joints_xyz': gen_joints_xyz_2,
    'translation': gen_translation_2,
    'gt_joints_xyz': gt_joints_xyz_2,
    'gt_translation': gt_translation_2
}

# Create metadata list
meta_data = [meta_1, meta_2]

ARGS = {
    'meta_data': meta_data
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_local_var_error Ran
ran on a synthesized input
kakaobrain/flame/src/utils/eval_util.py
code served (permissive licence) · get_code("afede4d8f258b3ef")
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 float32, 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 numpy as np

# Construct valid arguments for get_local_var_error
# The function expects:
# - gen: array of shape (num_frames, num_joints, num_coordinates)
# - gt: array of shape (num_frames, num_joints, num_coordinates)

# Create small test data
num_frames = 4
num_joints = 22  # Max joint index in connectivity_map is 21, so need at least 22 joints
num_coordinates = 3

# Generate random pose data for generated output
np.random.seed(0)
gen = np.random.randn(num_frames, num_joints, num_coordinates).astype(np.float32)

# Generate random pose data for ground truth
gt = np.random.randn(num_frames, num_joints, num_coordinates).astype(np.float32)

ARGS = {
    "gen": gen,
    "gt": gt,
}
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 float32, 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
compute_metrics Not yet run
unverified (harvested, no recorded run)
kakaobrain/flame/src/utils/eval_util.py
code served (permissive licence) · get_code("538ba2f56aa645b7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Text-based motion generation models are drawing a surge of interest for their potential for automating the motion-making process in the game, animation, or robot industries. In this paper, we propose a diffusion-based motion synthesis and editing model named FLAME. Inspired by the recent successes in diffusion models, we integrate diffusion-based generative models into the motion domain. FLAME can generate high-fidelity motions well aligned with the given text. Also, it can edit the parts of the motion, both frame-wise and joint-wise, without any fine-tuning. FLAME involves a new transformer-based architecture we devise to better handle motion data, which is found to be crucial to manage variable-length motions and well attend to free-form text. In experiments, we show that FLAME achieves state-of-the-art generation performances on three text-motion datasets: HumanML3D, BABEL, and KIT. We also demonstrate that editing capability of FLAME can be extended to other tasks such as motion prediction or motion in-betweening, which have been previously covered by dedicated models.

For agents

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

get_harvested_code_for_paper("2209.00349")
get_code_for_paper("2209.00349")
have("2209.00349")

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

curl https://syntology.ai/api/ran/2209.00349.json

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

[![Syntology run record](https://syntology.ai/api/ran/2209.00349.svg)](https://syntology.ai/paper/2209.00349)

Connect an agent — have() is free.