Papers › M³GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation

M³GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation

25 May 2024arXiv:2405.16273archive 2025-07-28

Mingshuang Luo, Ruibing Hou, Zhuo Li, Hong Chang, Zimo Liu, YaoWei Wang, Shiguang Shan

This paper presents M³GPT, an advanced Multimodal, Multitask framework for Motion comprehension and generation. M³GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary. The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M³GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M³GPT is the first model capable of comprehending and generating motions based on multiple signals. Extensive experiments highlight M³GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: https://github.com/luomingshuang/M3GPT.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 25 code samples harvested from 1 repository linked to this paper: 17 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 25 samples from 1 repository, 17 ran (8 with no instrument failure; 9 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

luomingshuang/m3gpt officialmentioned in papermentioned on GitHubpytorchSyntology: 25 samples, 17 ran (9 instrument-failed) · 8 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

25 samples harvested: 17 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
1ran; the contract check could not run
7ran
8unverified

Licence: 25 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from luomingshuang/m3gpt. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

luomingshuang/m3gpt official repository 25 samples, 17 ran (9 instrument-failed) · 8 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran no licence file found · pointer only · af4cc52db9e5aa3b · report fixture: returned Conv2d · level recorded 2026-09-22
CrossAttentionLayer in 10 papers m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran no licence file found · pointer only · 393e561d1764ea4e · report fixture: returned CrossAttentionLayer · level recorded 2026-09-22
FFNLayer m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran no licence file found · pointer only · dddec67cab845dc9 · report fixture: returned FFNLayer · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 4, kind float, dtype float32
m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · cb65f982177791b7 · report fixture: signature x:Tensor/4/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
SelfAttentionLayer in 6 papers m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran no licence file found · pointer only · cdc9f7050bfb9dbf · report fixture: returned SelfAttentionLayer · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
m3gpt/core/utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 78d1f9f766be74b7 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
accuracy_multi m3gpt/core/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8a63c5da44344ba6 · report fixture: signature output:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-24
flat in 11 papers m3gpt/core/config.py ran · honoured contract fingerprinted no licence file found · pointer only · 4570d6d70bccdfb6 · report fixture: signature nums:list/1/int · returned list · level recorded 2026-09-24
get_logger in 383 papers m3gpt/utils.py ran no licence file found · pointer only · bd1cba25bacbf54d · report fixture: signature fpath:str/0/str, local_rank:int/0/int, name:str/0/str · returned Logger · level recorded 2026-09-24
init in 55 papers m3gpt/core/fp16/amp.py ran no licence file found · pointer only · eb8a2600afc1de95 · report fixture: signature enable_caching:bool/0/bool, verbose:bool/0/bool · returned AmpHandle · level recorded 2026-09-24
mask2pos m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran · our draft was wrong no licence file found · pointer only · 4418374c5f2c445c · report fixture: signature mask:Tensor/3/bool · returned tuple · level recorded 2026-09-22
param_group_fc m3gpt/core/make_param_group.py ran · our draft was wrong no licence file found · pointer only · 70165e0988ce9571 · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-24
param_group_multitask m3gpt/core/make_param_group.py ran · our draft was wrong no licence file found · pointer only · e4a7663d686ce91a · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-24
param_group_no_wd m3gpt/core/make_param_group.py ran · our draft was wrong no licence file found · pointer only · 0540cf098dbc3d42 · report fixture: signature model:callable/0/? · returned tuple · level recorded 2026-09-24
pos2posemb2d in 5 papers m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5d5d46e55c97947a · report fixture: signature pos:Tensor/2/float, num_pos_feats:int/0/int, temperature:int/0/int · returned Tensor · level recorded 2026-09-22
read_json in 250 papers m3gpt/utils.py ran · our draft was wrong no licence file found · pointer only · 7d6e263caea8e963 · report fixture: signature fpath:str/0/str · returned dict · level recorded 2026-09-24
retry_if_cuda_oom m3gpt/core/memory.py ran · our draft was wrong no licence file found · pointer only · ff1253be17efe1ae · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
TransformerDecoder in 49 papers m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py unverified no licence file found · pointer only · e2a72e23375812ed · report
c2_xavier_fill m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py unverified no licence file found · pointer only · fe1c1ba4ad057e5f · report
dist_init in 7 papers m3gpt/core/distributed_utils.py unverified no licence file found · pointer only · c7d1fdb02e6cad00 · report
float_function m3gpt/core/fp16/amp.py unverified no licence file found · pointer only · f27c7ab614e20039 · report
get_2d_sincos_pos_embed in 170 papers m3gpt/core/models/decoders/network/transformer_decoder/transformer_decoder.py unverified no licence file found · pointer only · 09d724b291a01fbe · report
half_function m3gpt/core/fp16/amp.py unverified no licence file found · pointer only · 6b4eee4b4bb1f238 · report
simple_group_split in 6 papers m3gpt/core/distributed_utils.py unverified no licence file found · pointer only · b1471eccec180d87 · report
specific_group_split m3gpt/core/distributed_utils.py unverified no licence file found · pointer only · 4e36f197c125d4d3 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for M3GPT (graph method: M3GPT). 15 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. TransformerDecoder entry · level 0 · unverified · e2a72e23375812ed
  2. Conv2d helper · level 1 · ran · af4cc52db9e5aa3b
  3. CrossAttentionLayer model · level 1 · ran · 393e561d1764ea4e
  4. FFNLayer model · level 1 · ran · dddec67cab845dc9
  5. MLP helper · level 1 · ran · 88342bac1e676835
  6. PositionEmbeddingSine helper · level 1 · ran · cb65f982177791b7
  7. SelfAttentionLayer model · level 1 · ran · cdc9f7050bfb9dbf
  8. c2_xavier_fill helper · level 0 · unverified · fe1c1ba4ad057e5f
  9. get_2d_sincos_pos_embed helper · level 0 · unverified · 09d724b291a01fbe
  10. inverse_sigmoid helper · level 1 · ran · our draft was wrong · 83c03ceb1307c6c4
  11. mask2pos helper · level 1 · ran · our draft was wrong · 4418374c5f2c445c
  12. pos2posemb2d helper · level 1 · ran · our draft was wrong · 5d5d46e55c97947a
  13. _get_activation_fn helper · level 1 · ran · our draft was wrong · ad74da3f2efb5b95
  14. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · f10004e059714d42
  15. get_1d_sincos_pos_embed_from_grid helper · level 0 · unverified · 12035a2f77d8016c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2405.16273") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingLarge Language ModelMotion GenerationQuantizationZero-shot Generalization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections