Papers › Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals

Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals

8 Jul 2024arXiv:2407.05996links table onlyarchive 2025-07-28

Moritz Reuss, Ömer Erdinç Yağmurlu, Fabian Wenzel, Rudolf Lioutikov

The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.

This work introduces the Multimodal Diffusion Transformer (MDT), a novel diffusion policy framework, that excels at learning versatile behavior from multimodal goal specifications with few language annotations. MDT leverages a diffusion-based multimodal transformer backbone and two self-supervised auxiliary objectives to master long-horizon manipulation tasks based on multimodal goals. The vast majority of imitation learning methods only learn from individual goal modalities, e.g. either language or goal images. However, existing large-scale imitation learning datasets are only partially labeled with language annotations, which prohibits current methods from learning language conditioned behavior from these datasets. MDT addresses this challenge by introducing a latent goal-conditioned state representation that is simultaneously trained on multimodal goal instructions. This state representation aligns image and language based goal embeddings and encodes sufficient information to predict future states. The representation is trained via two self-supervised auxiliary objectives, enhancing the performance of the presented transformer backbone. MDT shows exceptional performance on 164 tasks provided by the challenging CALVIN and LIBERO benchmarks, including a LIBERO version that contains less than 2% language annotations. Furthermore, MDT establishes a new record on the CALVIN manipulation challenge, demonstrating an absolute performance improvement of 15% over prior state-of-the-art methods that require large-scale pretraining and contain 10× more learnable parameters. MDT shows its ability to solve long-horizon manipulation from sparsely annotated data in both simulated and real-world environments. Demonstrations and Code are available at https://intuitive-robots.github.io/mdt_policy/.

PaperPDFCodeCode Syntology ran

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 17 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 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: 17 samples from 1 repository, 15 ran (6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

intuitive-robots/mdt_policy officialmentioned on GitHubMITSyntology: 17 samples, 15 ran (9 instrument-failed) · 2 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

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 9 where Syntology's instrument failed) · 2 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.

2ran · honoured contract
2ran · violated contract
8ran · our draft was wrong
1ran; the contract check could not run
2ran
2unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from intuitive-robots/mdt_policy. “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”. “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.

intuitive-robots/mdt_policy official repository 17 samples, 15 ran (9 instrument-failed) · 2 unverified
append_zero in 5 papers mdt/models/edm_diffusion/gc_sampling.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 43f2167b019a5fb7 · report fixture: signature action:Tensor/1/float · returned Tensor · level recorded 2026-09-22
check_condition mdt/evaluation/multistep_sequences.py ran · violated contract MIT (permissive) · 907517ed3b614cc8 · report fixture: signature state:dict/0/?, condition:dict/0/? · returned bool · level recorded 2026-09-24
count_success mdt/evaluation/mdt_evaluate.py ran · our draft was wrong fingerprinted MIT (permissive) · 924cae6f210421b2 · report fixture: signature results:list/1/int · returned list · level recorded 2026-09-24
get_checkpoint_i_from_dir mdt/evaluation/utils.py ran MIT (permissive) · 84f14e237dee0362 · report fixture: signature dir:PosixPath/0/?, i:int/0/int · returned PosixPath · level recorded 2026-09-24
get_log_dir in 9 papers mdt/evaluation/mdt_evaluate.py ran · our draft was wrong MIT (permissive) · e2bd842daf595f33 · report fixture: signature log_dir:str/0/str · returned PosixPath · level recorded 2026-09-24
get_sigmas_exponential mdt/models/edm_diffusion/gc_sampling.py ran · honoured contract MIT (permissive) · 205e97641ece09f8 · report fixture: signature n:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_sigmas_karras in 8 papers mdt/models/edm_diffusion/gc_sampling.py ran · honoured contract MIT (permissive) · a3ae2e8a897b4d99 · report fixture: signature n:int/0/int, sigma_min:float/0/float, sigma_max:float/0/float, rho:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_video_tag mdt/evaluation/mdt_evaluate.py ran · our draft was wrong fingerprinted MIT (permissive) · bc8ceb8ab2fa1d19 · report fixture: signature i:int/0/int · returned str · level recorded 2026-09-24
is_multi_gpu_training mdt/training.py ran · violated contract fingerprinted MIT (permissive) · 6cd960334bdf5b85 · report fixture: signature gpus:int/0/int · returned bool · level recorded 2026-09-24
load_class in 10 papers mdt/evaluation/utils.py ran · our draft was wrong MIT (permissive) · 30fcb27ec8c091af · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-24
load_npz in 17 papers mdt/datasets/disk_dataset.py ran · our draft was wrong MIT (permissive) · c0de2c3f2828b5a3 · report fixture: signature filename:PosixPath/0/? · returned NpzFile · level recorded 2026-09-24
load_pkl in 46 papers mdt/datasets/disk_dataset.py ran · our draft was wrong MIT (permissive) · 3ffdb6fe27bf366d · report fixture: signature filename:PosixPath/0/? · returned dict · level recorded 2026-09-24
setup_logger in 122 papers mdt/training.py ran MIT (permissive) · 08c8831b3905ef52 · report fixture: signature cfg:DictConfig/0/?, model:callable/0/? · returned TensorBoardLogger · level recorded 2026-09-24
update_state in 11 papers mdt/evaluation/multistep_sequences.py ran · our draft was wrong MIT (permissive) · 916d58d0838c488b · report fixture: signature state:dict/0/?, effect:dict/0/? · returned dict · level recorded 2026-09-24
valid_task mdt/evaluation/multistep_sequences.py ran · our draft was wrong MIT (permissive) · 5879a63c0a8f823e · report fixture: signature curr_state:dict/0/?, task:list/1/dict · returned list · level recorded 2026-09-24
load_evaluation_checkpoint mdt/evaluation/utils.py unverified MIT (permissive) · 3e9e61cbcea37bd0 · report
setup_callbacks in 6 papers mdt/training.py unverified MIT (permissive) · 8ab9acda1d0ae3ee · report

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