Papers › Intention-Conditioned Flow Occupancy Models

Intention-Conditioned Flow Occupancy Models

10 Jun 2025arXiv:2506.08902archive 2025-07-28

Chongyi Zheng, Seohong Park, Sergey Levine, Benjamin Eysenbach

Large-scale pre-training has fundamentally changed how machine learning research is done today: large foundation models are trained once, and then can be used by anyone in the community (including those without data or compute resources to train a model from scratch) to adapt and fine-tune to specific tasks. Applying this same framework to reinforcement learning (RL) is appealing because it offers compelling avenues for addressing core challenges in RL, including sample efficiency and robustness. However, there remains a fundamental challenge to pre-train large models in the context of RL: actions have long-term dependencies, so training a foundation model that reasons across time is important. Recent advances in generative AI have provided new tools for modeling highly complex distributions. In this paper, we build a probabilistic model to predict which states an agent will visit in the temporally distant future (i.e., an occupancy measure) using flow matching. As large datasets are often constructed by many distinct users performing distinct tasks, we include in our model a latent variable capturing the user intention. This intention increases the expressivity of our model, and enables adaptation with generalized policy improvement. We call our proposed method intention-conditioned flow occupancy models (InFOM). Comparing with alternative methods for pre-training, our experiments on 36 state-based and 4 image-based benchmark tasks demonstrate that the proposed method achieves 1.8 × median improvement in returns and increases success rates by 36%. Website: https://chongyi-zheng.github.io/infom Code: https://github.com/chongyi-zheng/infom

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 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (10 with no instrument failure; 1 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chongyi-zheng/infom officialmentioned in papermentioned on GitHubjaxSyntology: 14 samples, 11 ran (1 instrument-failed) · 3 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

14 samples harvested: 11 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
10ran
3unverified

Licence: 0 of the 14 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 chongyi-zheng/infom. “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.

chongyi-zheng/infom official repository 14 samples, 11 ran (1 instrument-failed) · 3 unverified
AddSpatialCoordinates agents/infom.py ran MIT (permissive) · b76fee603c23832b · report fixture: returned AddSpatialCoordinates · level recorded 2026-09-22
GroupNorm in 10 papers agents/infom.py ran MIT (permissive) · df206f07444e8679 · report fixture: returned GroupNorm · level recorded 2026-09-22
ImpalaEncoder in 6 papers agents/infom.py ran MIT (permissive) · 82a37d485fffbe7c · report fixture: returned ImpalaEncoder · level recorded 2026-09-22
IntentionEncoder agents/infom.py ran MIT (permissive) · 5fd7c55ff6bc1c8c · report fixture: returned IntentionEncoder · level recorded 2026-09-22
MLP in 375 papers agents/infom.py ran MIT (permissive) · 3a92290722d6d764 · report fixture: returned MLP · level recorded 2026-09-22
ModuleDict in 6 papers agents/infom.py ran MIT (permissive) · afcc6a74fc1afd44 · report fixture: returned ModuleDict · level recorded 2026-09-22
ResNetBlock in 8 papers agents/infom.py ran MIT (permissive) · e8d3d57d274492b3 · report fixture: returned ResNetBlock · level recorded 2026-09-22
ResNetEncoder in 6 papers agents/infom.py ran MIT (permissive) · 753cfc3e30a2a633 · report fixture: returned ResNetEncoder · level recorded 2026-09-22
Value in 10 papers agents/infom.py ran MIT (permissive) · 028beb23076e7758 · report fixture: returned Value · level recorded 2026-09-22
VectorField agents/infom.py ran MIT (permissive) · 346889c56384a53c · report fixture: returned VectorField · level recorded 2026-09-22
ensemblize in 12 papers agents/infom.py ran · our draft was wrong MIT (permissive) · e2b6e84f73d1d030 · report fixture: signature cls:callable/0/?, num_qs:int/0/int, out_axes:int/0/int · returned type · level recorded 2026-09-22
Actor in 68 papers agents/infom.py unverified MIT (permissive) · 17f5041025f7c2b2 · report
InFOMAgent agents/infom.py unverified MIT (permissive) · a821b42336bda776 · report
TransformedWithMode agents/infom.py unverified MIT (permissive) · cea8929c82a646bd · 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 intention-conditioned flow occupancy models (InFOM) (graph method: intention-conditioned flow occupancy models (InFOM)). 17 bricks; individually on a fixture: 14 ran (of which 12 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. InFOMAgent entry · level 0 · unverified · a821b42336bda776
  2. Actor helper · level 0 · unverified · 17f5041025f7c2b2
  3. IntentionEncoder model · level 1 · ran · 5fd7c55ff6bc1c8c
  4. ModuleDict helper · level 1 · ran · afcc6a74fc1afd44
  5. TrainState helper · level 1 · ran · 320b57aeb460d8c6
  6. Value helper · level 1 · ran · 028beb23076e7758
  7. VectorField model · level 1 · ran · 346889c56384a53c
  8. MLP model · level 1 · ran · 3a92290722d6d764
  9. TransformedWithMode helper · level 0 · unverified · cea8929c82a646bd
  10. default_init helper · level 1 · ran · our draft was wrong · 2aaa6f4e0d62bf22
  11. ensemblize helper · level 1 · ran · our draft was wrong · e2b6e84f73d1d030
  12. AddSpatialCoordinates helper · level 1 · ran · b76fee603c23832b
  13. GroupNorm helper · level 1 · ran · df206f07444e8679
  14. ImpalaEncoder helper · level 1 · ran · 82a37d485fffbe7c
  15. ResNetBlock helper · level 1 · ran · e8d3d57d274492b3
  16. ResNetEncoder helper · level 1 · ran · 753cfc3e30a2a633
  17. ResnetStack helper · level 1 · ran · 6a774c1075ea7123

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="2506.08902") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Reinforcement Learning (RL)

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