SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.23264 · 2026

MotionHiFlow: Text-to-Motion via Hierarchical Flow Matching

Shuai Li, Heng Li, Jian-Fang Hu, Xiaotong Lin, Ling-An Zeng, Yulei Kang

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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, 3 violated it and 0 have no contract verdict; 10 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/2604.23264.json · badge: /api/ran/2604.23264.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
ai-lh/MotionHiFlow canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
FunctionStatusWhere it lives
edge2mat Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/src/utils/graph_tools.py
pointer only (licence: NONE); the stored copy get_code serves, from hyer/HDFormer, is pointer only (licence: NONE) · get_code("5f5ae82020ac7ec2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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_k_scale_graph Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ai-lh/MotionHiFlow/src/utils/graph_tools.py
pointer only (licence: NONE) · get_code("d3e8dd52d4a2755a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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_padding_mask Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/src/evaluators/t2m_eval_modules.py
pointer only (licence: NONE) · get_code("5fdf5df48906cb4f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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_sgp_mat Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/src/utils/graph_tools.py
pointer only (licence: NONE) · get_code("5940d00ced3d0637")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

interpolate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ai-lh/MotionHiFlow/src/utils/interp.py
pointer only (licence: NONE) · get_code("aa80cf540821b93b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

is_float Ran
ran, violated the contract we drafted
ai-lh/MotionHiFlow/src/utils/get_opt.py
pointer only (licence: NONE) · get_code("b1f8a286e3a73b80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

is_list Ran
ran, violated the contract we drafted
ai-lh/MotionHiFlow/src/utils/get_opt.py
pointer only (licence: NONE) · get_code("d3167ba038ed089c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

is_number Ran
ran, violated the contract we drafted
ai-lh/MotionHiFlow/src/utils/get_opt.py
pointer only (licence: NONE) · get_code("e9840a10d733a764")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

length_to_mask Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/src/utils/eval_t2m.py
pointer only (licence: NONE) · get_code("e959dab51139ef27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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_prompts Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/gen_t2m.py
pointer only (licence: NONE) · get_code("baa3a35c6527cbfc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

pool_motion Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/src/pipelines/vae_trainer.py
pointer only (licence: NONE) · get_code("6d888496b78f2615")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

positional_encoding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ai-lh/MotionHiFlow/src/evaluators/t2m_eval_modules.py
pointer only (licence: NONE) · get_code("cdd18b1ca5a038e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

top_k_logits Ran
ran; our contract draft was wrong, not the code
ai-lh/MotionHiFlow/src/evaluators/t2m_eval_modules.py
pointer only (licence: NONE) · get_code("0f0021cdea13e4da")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

build_evaluators Not yet run
unverified (harvested, no recorded run)
ai-lh/MotionHiFlow/src/evaluators/t2m_eval_wrapper.py
pointer only (licence: NONE) · get_code("939b4a7d3178c666")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

build_models Not yet run
unverified (harvested, no recorded run)
ai-lh/MotionHiFlow/src/evaluators/t2m_eval_wrapper.py
pointer only (licence: NONE) · get_code("0e89c3d7e91130b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

capture_init_kwargs Not yet run
unverified (harvested, no recorded run)
ai-lh/MotionHiFlow/src/utils/decorator.py
pointer only (licence: NONE) · get_code("5095b9f0062251b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

create_text_encoder Not yet run
unverified (harvested, no recorded run)
ai-lh/MotionHiFlow/src/arch/text_encoder.py
pointer only (licence: NONE) · get_code("65a0365600654f6e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ai-lh/MotionHiFlow 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.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 0 the same month, 0 later) and 9 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
top_k_logits 16 other papers
16 dated earlier
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.02039 (2021-06)
Offline Reinforcement Learning as One Big Sequence Modeling Problem
2106.14131 (2021-06)
SymbolicGPT: A Generative Transformer Model for Symbolic Regression
and 13 more not named here
edge2mat 7 other papers
7 dated earlier
2208.10741 (2022-08)
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
2302.01825 (2023-02)
HDFormer: High-order Directed Transformer for 3D Human Pose Estimation
and 4 more not named here
get_k_scale_graph 2 other papers
2 dated earlier
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
2305.11468 (2023-05)
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
get_sgp_mat 2 other papers
2 dated earlier
2211.09590 (2022-11)
Hypergraph Transformer for Skeleton-based Action Recognition
2305.11468 (2023-05)
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
build_evaluators 1 other paper
1 dated earlier
2312.00063 (2023-12)
MoMask: Generative Masked Modeling of 3D Human Motions
build_models 1 other paper
1 dated earlier
2312.00063 (2023-12)
MoMask: Generative Masked Modeling of 3D Human Motions
get_padding_mask 1 other paper
1 dated earlier
2312.00063 (2023-12)
MoMask: Generative Masked Modeling of 3D Human Motions
positional_encoding 1 other paper
1 dated earlier
2312.00063 (2023-12)
MoMask: Generative Masked Modeling of 3D Human Motions

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-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natural movements, they usually operate at only one temporal scale, which limits both semantic alignment and temporal coherence. Inspired by the fact that complex motions are conceptualized hierarchically rather than at a single temporal scale in the human cognitive system, we propose MotionHiFlow, a hierarchical flow matching framework to generate motion progressively by constructing flow path from low to high temporal scales. The flows at lower scales capture high-level semantics and coarse motion structures, while flows at higher scales refine temporal details. To link the flows across scales, we introduce a novel cross-scale transition process, ensuring continuity and preserving noise consistency. Furthermore, by integrating a Text-Motion Diffusion Transformer and a topology-aware Motion VAE, MotionHiFlow explicitly models structural dependencies among joints via jointaware positional encoding and skeletal topology, enabling precise semantic alignment alongside fine-grained motion details. Extensive experiments on HumanML3D and KIT-ML benchmarks demonstrate state-of-the-art performance, with ablation studies confirming the effectiveness of the hierarchical design and key components. Code is available at https://github.com/ai-lh/MotionHiFlow.

For agents

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

get_harvested_code_for_paper("2604.23264")
get_code_for_paper("2604.23264")
have("2604.23264")

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

curl https://syntology.ai/api/ran/2604.23264.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.23264.svg)](https://syntology.ai/paper/2604.23264)

Connect an agent — have() is free.