SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.06052 · CVPR · 2023

Generating Human Motion from Textual Descriptions with Discrete Representations

Xi Shen, Yong Zhang, Hongtao Lu, Xiaodong Cun, Hongwei Zhao, Jianrong Zhang, Yangsong Zhang, Shan Ying

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 2 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/2301.06052.json · badge: /api/ran/2301.06052.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
Mael-zys/T2M-GPT marked official in Papers with Code
Papers with Code archive
5 ran · 2 no recorded run
FunctionStatusWhere it lives
Block Ran
ran on a synthesized input · constructed an object; no result was computed
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("c850a045304b395b")
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 an instance of its own class, Block: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    'embed_dim': 8,
    'block_size': 4,
    'n_head': 2,
    'drop_out_rate': 0.1,
    'fc_rate': 4,
}
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 Block — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Block 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
CausalCrossConditionalSelfAttention Ran
ran on a synthesized input · constructed an object; no result was computed
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("b2522d3d54eff496")
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 an instance of its own class, CausalCrossConditionalSelfAttention: the run constructed the object and did not call it, so no result was computed. 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 math
import torch
import torch.nn as nn
from torch.nn import functional as F

torch.manual_seed(0)

class CausalCrossConditionalSelfAttention(nn.Module):

    def __init__(self, embed_dim=512, block_size=16, n_head=8, drop_out_rate=0.1):
        super().__init__()
        assert embed_dim % 8 == 0
        self.key = nn.Linear(embed_dim, embed_dim)
        self.query = nn.Linear(embed_dim, embed_dim)
        self.value = nn.Linear(embed_dim, embed_dim)
        self.attn_drop = nn.Dropout(drop_out_rate)
        self.resid_drop = nn.Dropout(drop_out_rate)
        self.proj = nn.Linear(embed_dim, embed_dim)
        self.register_buffer('mask', torch.tril(torch.ones(block_size, block_size)).view(1, 1, block_size, block_size))
        self.n_head = n_head

    def forward(self, x):
        B, T, C = x.size()
        k = self.key(x).view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        q = self.query(x).view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        v = self.value(x).view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        att = q @ k.transpose(-2, -1) * (1.0 / math.sqrt(k.size(-1)))
        att = att.masked_fill(self.mask[:, :, :T, :T] == 0, float('-inf'))
        att = F.softmax(att, dim=-1)
        att = self.attn_drop(att)
        y = att @ v
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        y = self.resid_drop(self.proj(y))
        return y

ARGS = {
    'embed_dim': 8,
    'block_size': 4,
    'n_head': 2,
    'drop_out_rate': 0.1
}
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 CausalCrossConditionalSelfAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CausalCrossConditionalSelfAttention 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
CrossCondTransHead Ran
ran on a synthesized input · constructed an object; no result was computed
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("5bb175d11cfeb528")
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 an instance of its own class, CrossCondTransHead: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'num_vq': 1024,
    'embed_dim': 512,
    'block_size': 16,
    'num_layers': 2,
    'n_head': 8,
    'drop_out_rate': 0.1,
    'fc_rate': 4
}
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 CrossCondTransHead — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CrossCondTransHead 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
PE1d_sincos Ran
ran, honoured the contract we drafted
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("b5884fc2a88a2dca")
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 3, dtype family float, shape (8, 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 math
import torch

torch.manual_seed(0)

ARGS = {
    "seq_length": 8,
    "dim": 4,
}
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 3, dtype family float, shape (8, 1, 4) — shape (8, 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
PositionEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("887cbe398f9b597f")
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 an instance of its own class, PositionEmbedding: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    "seq_length": 8,
    "dim": 4,
    "dropout": 0.1,
    "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 PositionEmbedding — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PositionEmbedding 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
CrossCondTransBase Not yet run
unverified (harvested, no recorded run)
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("78f9934de35620f9")
How it ran

no invocation recorded.

Text2Motion_Transformer Not yet run
unverified (harvested, no recorded run)
Mael-zys/T2M-GPT/models/t2m_trans.py
code served (permissive licence) · get_code("947345f4802a5dd3")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
PE1d_sincos
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later
1607.03827 (2016-07)
The KIT Motion-Language Dataset
2309.00796 (2023-09)
AttT2M: Text-Driven Human Motion Generation with Multi-Perspective Attention Mechanism
2402.01049 (2024-02)
IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognition
and 1 more not named here

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

In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pretrained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNNbased VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive approaches, including recent diffusion-based approaches. For example, on HumanML3D, which is currently the largest dataset, we achieve comparable performance on the consistency between text and generated motion (R-Precision), but with FID 0.116 largely outperforming MotionDiffuse of 0.630. Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach. Our work suggests that VQ-VAE still remains a competitive approach for human motion generation. Our implementation is available on the project

For agents

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

get_harvested_code_for_paper("2301.06052")
get_code_for_paper("2301.06052")
have("2301.06052")

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

curl https://syntology.ai/api/ran/2301.06052.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.06052.svg)](https://syntology.ai/paper/2301.06052)

Connect an agent — have() is free.