SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_25754 · AAAI · 2023

Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

Jianfeng Lu, Bin Li, Dong Wei, Huaijiang Sun, Weiqing Li, Xiaoning Sun, Shengxiang Hu

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 3 have no contract verdict; 0 failures of our instrument; 2 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/aaai_25754.json · badge: /api/ran/aaai_25754.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
csdwei/MotionDiff canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
FunctionStatusWhere it lives
create_logger Ran
ran on a synthesized input
csdwei/MotionDiff/utils/logger.py
code served (permissive licence) · get_code("e80e9b137849e33a")
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 Logger. 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 logging
import os
import tempfile

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_filename = os.path.join(temp_dir, "test_logger.log")

ARGS = {
    "filename": log_filename,
    "file_handle": True,
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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_flat_grad_from Ran
ran on a synthesized input
csdwei/MotionDiff/utils/torch.py
code served (permissive licence) · get_code("35c32bab695e0f6c")
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 (31,) 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 as nn

torch.manual_seed(0)

# Create a list of tensors to act as inputs (parameters)
# Each tensor needs to have a .grad attribute that we can access
param1 = torch.randn(4, 3, requires_grad=True)
param2 = torch.randn(5, 2, requires_grad=True)
param3 = torch.randn(6, requires_grad=True)

# Simulate gradients by doing a simple backward pass
loss1 = param1.sum()
loss1.backward()

loss2 = param2.sum()
loss2.backward()

loss3 = param3.sum()
loss3.backward()

# Create another set of parameters where one has no gradient
param4 = torch.randn(3, requires_grad=True)
# Don't compute gradient for param4

inputs = [param1, param2, param3, param4]

ARGS = {
    "inputs": inputs,
    "grad_grad": 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 1, dtype family float, shape (31,) — shape (31,) 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_flat_params_from Ran
ran on a synthesized input
csdwei/MotionDiff/utils/torch.py
code served (permissive licence) · get_code("748ebf6d58779d56")
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 (59,) 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 as nn

torch.manual_seed(0)

# Create a simple model with some parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Create another model with different dimensions
class AnotherModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(5, 6)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate models
model1 = SimpleModel()
model2 = AnotherModel()

ARGS = {
    'models': (model1, model2)
}
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 (59,) — shape (59,) 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
batch_to Not yet run
unverified (harvested, no recorded run)
csdwei/MotionDiff/utils/torch.py
pointer only (licence: MIT); the stored copy get_code serves, from xccyue/MutualDistance, is pointer only (licence: NONE) · get_code("f6e42d1a52522ffb")
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 xccyue/MutualDistance, 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. No invocation recorded.

denomarlize Not yet run
unverified (harvested, no recorded run)
csdwei/MotionDiff/models/common.py
code served (permissive licence) · get_code("d3e4d27d0720e510")
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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
create_logger 4 other papers
2 dated earlier, 1 later, 1 same year, order not determinable
2108.08422 (2021-08)
Generating Smooth Pose Sequences for Diverse Human Motion Prediction
2110.03659 (2021-10)
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
2306.00036 (2023-06)
Symmetry-Aware Robot Design with Structured Subgroups
and 1 more not named here
batch_to 2 other papers
1 dated earlier, 1 same year, order not determinable
2103.14023 (2021-03)
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting
2310.00615 (2023-10)
Scene-aware Human Motion Forecasting via Mutual Distance Prediction
get_flat_params_from 1 other paper
1 dated earlier
2103.14023 (2021-03)
AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting

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

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process not only offers a natural way to obtain the "whitened" latents without any trainable parameters, but also introduces a new noise in each diffusion step, both of which facilitate more diverse motions. Human motion prediction is then regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a flexible refinement network to further enable geometric losses and align with the ground truth. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both diversity and accuracy.

For agents

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

get_harvested_code_for_paper("aaai_25754")
get_code_for_paper("aaai_25754")
have("aaai_25754")

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

curl https://syntology.ai/api/ran/aaai_25754.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_25754.svg)](https://syntology.ai/paper/aaai_25754)

Connect an agent — have() is free.