Papers › Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
Haoran He, Chenjia Bai, Ling Pan, Weinan Zhang, Bin Zhao, Xuelong Li
Learning a generalist embodied agent capable of completing multiple tasks poses challenges, primarily stemming from the scarcity of action-labeled robotic datasets. In contrast, a vast amount of human videos exist, capturing intricate tasks and interactions with the physical world. Promising prospects arise for utilizing actionless human videos for pre-training and transferring the knowledge to facilitate robot policy learning through limited robot demonstrations. However, it remains a challenge due to the domain gap between humans and robots. Moreover, it is difficult to extract useful information representing the dynamic world from human videos, because of its noisy and multimodal data structure. In this paper, we introduce a novel framework to tackle these challenges, which leverages a unified discrete diffusion to combine generative pre-training on human videos and policy fine-tuning on a small number of action-labeled robot videos. We start by compressing both human and robot videos into unified video tokens. In the pre-training stage, we employ a discrete diffusion model with a mask-and-replace diffusion strategy to predict future video tokens in the latent space. In the fine-tuning stage, we harness the imagined future videos to guide low-level action learning with a limited set of robot data. Experiments demonstrate that our method generates high-fidelity future videos for planning and enhances the fine-tuned policies compared to previous state-of-the-art approaches with superior performance. Our project website is available at https://video-diff.github.io/.
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.
Syntology holds a reference implementation of unified discrete diffusion, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='unified discrete diffusion') (how to connect); the free check have('2402.14407') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2402.14407")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2402.14407", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2402.14407")
Code
Syntology 18 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 9 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: 6 samples from 1 repository, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 12 samples from 2 repositories, 12 ran (3 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. 3 of the 17 samples that ran have no recorded date.
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
18 samples harvested: 17 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 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.
Licence: 3 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. 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.
e163906c3cdc2aa6 · report
fixture: returned Huber · level recorded 2026-09-22 acf269bb622e8d6a · report
fixture: returned StateHuber · level recorded 2026-09-22 43177911c1fd1d18 · report
fixture: returned WeightedStateLoss · level recorded 2026-09-22 8d04d499d75080d0 · report
fixture: signature model:callable/0/?, x:Tensor/2/float, cond:Tensor/2/float, task:Tensor/2/float, value:Tensor/2/float, context_mask:Tensor/2/float, t:Tensor/1/int, sample_kwargs:dict/0/? · returned tuple · level recorded 2026-09-22 ee809dc4a6634822 · report
fixture: returned videoloss · level recorded 2026-09-22 81f1f429fb4a7f3e · report
c99fb7b9654ea364 · report
fixture: signature act:str/0/str · returned ReLU · level recorded 2026-09-24 8458f9ba0361ff43 · report
fixture: signature f:callable/0/? · returned function · level recorded, date not recorded 60fff7c3c400d7ff · report
fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64 agents/peract_bc/perceiver_lang_io.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only ·
aa5486a3650902d8 · report
fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded 0a61ee3eb30e145f · report
fixture: signature lst:list/1/int · returned int · level recorded 2026-09-24 9ed9933be23b28a5 · report
fixture: signature norm:str/0/str, num_channels:int/0/int · returned BatchNorm1d · level recorded 2026-09-24 d0264b5831943fb9 · report
fixture: signature norm:str/0/str, channels:int/0/int · returned BatchNorm2d · level recorded 2026-09-24 051af9d2e2264347 · report
fixture: signature d:dict/0/? · returned list · level recorded 2026-09-24 5b55e1bed13f5a58 · report
fixture: returned str · level recorded 2026-09-24 cda51c68aff53692 · report
fixture: returned str · level recorded 2026-09-24 755db90b1e706d42 · report
fixture: returned str · level recorded 2026-09-24 295aa3b49a6888ac · report
fixture: signature factor_space:Discrete/0/int, n:int/0/int · returned ndarray · level recorded 2026-09-24 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
2 assemblies on this paper: 1 harvested, 1 generated.
generated Assembly for unified discrete diffusion (graph method: unified discrete diffusion), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).
label matches by construction: the code was generated for this method (not judged by a model)
- discrete_diffusion_forward_sample entry · level 3 · ran · honoured contract ·
6409fc676adb12ca856b2bec4442eaaf11e86d89e890f92a3a26afbbc7ea067b
harvested Assembly for unified discrete diffusion (graph method: unified discrete diffusion). 17 bricks; individually on a fixture: 12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.
- DTDiffusion entry · level 0 · unverified ·
81f1f429fb4a7f3e - cosine_beta_schedule helper · level 1 · ran · honoured contract ·
b6113e0f43155a33 - default_sample_fn helper · level 1 · ran · our draft was wrong ·
8d04d499d75080d0 - extract helper · level 0 · unverified ·
09c8479d9a5b3e06 - make_timesteps helper · level 1 · ran · honoured contract ·
51db163798eb0f5e - sort_by_values helper · level 1 · ran · honoured contract ·
c409be426eec3eec - vp_beta_schedule helper · level 1 · ran · honoured contract ·
47c7ce0ace6e7c47 - ValueLoss helper · level 0 · unverified ·
2033d022f4c21dd8 - WeightedLoss helper · level 1 · ran ·
31a6a65466c90f16 - WeightedStateLoss helper · level 1 · ran ·
43177911c1fd1d18 - videoloss helper · level 1 · ran ·
ee809dc4a6634822 - Huber helper · level 1 · ran ·
e163906c3cdc2aa6 - StateHuber helper · level 1 · ran ·
acf269bb622e8d6a - ValueL1 helper · level 0 · unverified ·
15f5f25cbe9d72e0 - ValueL2 helper · level 0 · unverified ·
4b9ad2741a65b9b0 - WeightedL1 helper · level 1 · ran ·
bb0b654d7e2f043a - WeightedL2 helper · level 1 · ran ·
63bb8b129db38dfb
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="2402.14407") returns these assemblies with each brick's role and wiring (how to connect).
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
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