SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.01015 · NeurIPS · 2023

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

Yuan Li, Li Yuan, Yanbo Fan, Jin Peng, Zhongqian Sun, Yang Wei, Yang Wu

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2311.01015.json · badge: /api/ran/2311.01015.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
jpthu17/GraphMotion canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
get_last_checkpoint Ran
ran; our contract draft was wrong, not the code
jpthu17/GraphMotion/GraphMotion/launch/prepare.py
code served (permissive licence) · get_code("937fa0d85f36fce1")
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 str. 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 tempfile
from pathlib import Path
import hydra
from hydra import initialize, compose
from hydra.core.global_hydra import GlobalHydra

# Clean up any existing Hydra instance
GlobalHydra.instance().clear()

# Create a temporary directory to serve as the output_dir
temp_dir = tempfile.mkdtemp()

# Initialize Hydra with a temporary config directory
with initialize(version_base=None, config_path=None):
    # Create the checkpoints subdirectory structure
    checkpoints_dir = Path(temp_dir) / "checkpoints"
    checkpoints_dir.mkdir(parents=True, exist_ok=True)
    
    # Create a dummy checkpoint file
    dummy_ckpt = checkpoints_dir / "last.ckpt"
    dummy_ckpt.touch()
    
    ARGS = {
        'path': temp_dir,
        'ckpt_name': 'last.ckpt'
    }
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
hydra — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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_module_config Ran
ran; our contract draft was wrong, not the code
jpthu17/GraphMotion/GraphMotion/config.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from li-ronghui/LODGE, is pointer only (licence: NONE) · get_code("77a953404a04592f")
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 li-ronghui/LODGE, 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.

get_obj_from_str Ran
ran; our contract draft was wrong, not the code
jpthu17/GraphMotion/GraphMotion/config.py
code served (permissive licence) · get_code("221b2d116fdf1032")
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 type. 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 importlib
import torch
import torch.nn as nn

torch.manual_seed(0)

# The function get_obj_from_str takes a string like "module.path.ClassName"
# and returns the class/object by:
# 1. Splitting on the last dot to get module path and class name
# 2. Optionally reloading the module if reload=True
# 3. Importing the module and getting the attribute (class/object)

# We need to provide:
# - string: a valid module.class path that exists
# - reload: boolean flag

# Using a built-in class that's guaranteed to exist
string_value = "torch.nn.Linear"
reload_value = False

ARGS = {
    "string": string_value,
    "reload": reload_value,
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
parse_args Ran
ran; our contract draft was wrong, not the code
jpthu17/GraphMotion/GraphMotion/launch/blender.py
code served (permissive licence) · get_code("e80c033b31c865ac")
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 Namespace. 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 sys
from argparse import ArgumentParser, Namespace

class MockParser:
    """Stand-in ArgumentParser with parse_args_bak method"""
    def __init__(self):
        self.parser = ArgumentParser()
        self.parser.add_argument('--test', default='value')
    
    def parse_args_bak(self, args=None, namespace=None):
        """Mock implementation of parse_args_bak"""
        return self.parser.parse_args(args=args, namespace=namespace)

# Create instance
parser_instance = MockParser()

# Define arguments for parse_args
ARGS = {
    'self': parser_instance,
    'args': None,
    'namespace': None
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
sample_from_distribution Ran
ran, honoured the contract we drafted
jpthu17/GraphMotion/GraphMotion/models/architectures/actor_vae.py
code served (permissive licence) · get_code("d28112bcad3cc54b")
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 2, dtype family float, shape (1, 4) 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.distributions as dist

torch.manual_seed(0)

# Create a simple distribution object that has the required attributes and methods
# The function uses: dist.loc, dist.rsample()
class MockDistribution:
    def __init__(self):
        self.loc = torch.randn(4)  # batch dimension will be added by unsqueeze(0)
    
    def rsample(self):
        return torch.randn(4)

# Create the distribution instance
mock_dist = MockDistribution()

ARGS = {
    "dist": mock_dist,
    "fact": 1.0,
    "sample_mean": False,
}
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 2, dtype family float, shape (1, 4) — shape (1, 4) 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
working_path Ran
ran; our contract draft was wrong, not the code
jpthu17/GraphMotion/GraphMotion/launch/prepare.py
code served (permissive licence) · get_code("e14c06506149a878")
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 str. 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 os
from pathlib import Path

# The function working_path takes a single parameter 'path' which should be
# a string or Path-like object representing a relative or absolute path.
# The function constructs a full path by joining the current working directory
# with the provided path and returns it as a string.

ARGS = {
    "path": "relative/path/to/file.txt"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
code_path Not yet run
unverified (harvested, no recorded run)
jpthu17/GraphMotion/GraphMotion/launch/prepare.py
code served (permissive licence) · get_code("0613065c8c248c4d")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
jpthu17/GraphMotion/GraphMotion/models/get_model.py
code served (permissive licence) · get_code("d36c7fc6ca58c56c")
How it ran

no invocation recorded.

get_module Not yet run
unverified (harvested, no recorded run)
jpthu17/GraphMotion/GraphMotion/models/get_model.py
code served (permissive licence) · get_code("526e7520c87e4281")
How it ran

no invocation recorded.

instantiate_from_config Not yet run
unverified (harvested, no recorded run)
jpthu17/GraphMotion/GraphMotion/config.py
code served (permissive licence) · get_code("ef52d142b2c30ac2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 6 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
get_obj_from_str 54 other papers
15 dated earlier, 1 the same month, 37 later, 1 same year, order not determinable · 12 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2112.00384 (2021-12)
Exploration into Translation-Equivariant Image Quantization
and 51 more not named here
instantiate_from_config 24 other papers
6 dated earlier, 18 later · 7 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
and 21 more not named here
get_module_config 2 other papers
1 dated earlier, 1 later
2310.12978 (2023-10)
HumanTOMATO: Text-aligned Whole-body Motion Generation
2403.10518 (2024-03)
Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives
parse_args 2 other papers
1 dated earlier, 1 later
2306.14795 (2023-06)
MotionGPT: Human Motion as a Foreign Language
2404.09445 (2024-04)
Exploring Text-to-Motion Generation with Human Preference

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

Most text-driven human motion generation methods employ sequential modeling approaches, e.g., transformer, to extract sentence-level text representations automatically and implicitly for human motion synthesis. However, these compact text representations may overemphasize the action names at the expense of other important properties and lack fine-grained details to guide the synthesis of subtly distinct motion. In this paper, we propose hierarchical semantic graphs for fine-grained control over motion generation. Specifically, we disentangle motion descriptions into hierarchical semantic graphs including three levels of motions, actions, and specifics. Such global-to-local structures facilitate a comprehensive understanding of motion description and fine-grained control of motion generation. Correspondingly, to leverage the coarse-to-fine topology of hierarchical semantic graphs, we decompose the text-to-motion diffusion process into three semantic levels, which correspond to capturing the overall motion, local actions, and action specifics. Extensive experiments on two benchmark human motion datasets, including HumanML3D and KIT, with superior performances, justify the efficacy of our method. More encouragingly, by modifying the edge weights of hierarchical semantic graphs, our method can continuously refine the generated motion, which may have a far-reaching impact on the community. Code and pre-training weights are available at https://github.com/jpthu17/GraphMotion.

For agents

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

get_harvested_code_for_paper("2311.01015")
get_code_for_paper("2311.01015")
have("2311.01015")

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

curl https://syntology.ai/api/ran/2311.01015.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.01015.svg)](https://syntology.ai/paper/2311.01015)

Connect an agent — have() is free.