Papers › FiLM: Visual Reasoning with a General Conditioning Layer

FiLM: Visual Reasoning with a General Conditioning Layer

22 Sep 2017arXiv:1709.07871archive 2025-07-28

Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, Aaron Courville

We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - answering image-related questions which require a multi-step, high-level process - a task which has proven difficult for standard deep learning methods that do not explicitly model reasoning. Specifically, we show on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error for the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are robust to ablations and architectural modifications, and 4) generalize well to challenging, new data from few examples or even zero-shot.

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 10 code samples harvested from 5 repositories linked to this paper: 9 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 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: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 9 samples from 4 repositories, 8 ran (7 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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.

ethanjperez/film officialmentioned in paperpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
CPJKU/audio_conditioned_unet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
GuessWhatGame/clevr mentioned on GitHubtfSyntology: not harvested report
caffeinism/film-pytorch mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (1 instrument-failed) · 1 unverified report
jjgo/hyperlight mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Magnitude Invariant Parametrizations Improve Hypernetwork Learning (arXiv:2304.07645; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
kdaip/stabletts mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
keonlee9420/Daft-Exprt mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

10 samples harvested: 9 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 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 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
8ran
1unverified

Licence: 7 of the 10 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 5 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”. For 2 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.

ethanjperez/film official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FiLM in 11 papers vr/models/filmed_net.py ran licence not identified · pointer only · b8723266db5e5556 · report fixture: signature x:Tensor/4/float, gammas:Tensor/2/float, betas:Tensor/2/float · returned Tensor · level recorded 2026-09-24
CPJKU/audio_conditioned_unet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FiLM in 11 papers audio_conditioned_unet/network.py ran MIT (permissive) · bd2e6b10e2f47993 · report fixture: signature x:Tensor/4/float, z:Tensor/2/float · returned Tensor · level recorded 2026-09-24
caffeinism/film-pytorch community (archive-listed) 6 samples, 5 ran (1 instrument-failed) · 1 unverified
Classifier in 72 papers networks.py ran fingerprinted no licence file found · pointer only · 37dda49b6caaba23 · report fixture: returned Classifier · level recorded 2026-09-22
FeatureExtractor in 24 papers networks.py ran fingerprinted no licence file found · pointer only · edbfcccbabd461c6 · report fixture: returned FeatureExtractor · level recorded 2026-09-22
FiLMBlock networks.py ran no licence file found · pointer only · 32874c063a45b37a · report fixture: signature x:Tensor/4/float, gamma:Tensor/2/float, beta:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
networks.py ran no licence file found · pointer only · 779ef9590306ac85 · report fixture: returned ResBlock · level recorded 2026-09-22
conv in 178 papers networks.py ran · our draft was wrong no licence file found · pointer only · b4a8caf47616fa06 · report fixture: signature ic:int/0/int, oc:int/0/int, k:int/0/int, s:int/0/int, p:int/0/int · returned Sequential · level recorded 2026-09-22
FiLM in 11 papers networks.py unverified no licence file found · pointer only · 6d21918b730bc046 · report
kdaip/stabletts community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FiLMLayer models/estimator.py ran MIT (permissive) · 04d3db3a0eb24a12 · report fixture: returned FiLMLayer · level recorded 2026-09-22
keonlee9420/Daft-Exprt community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FiLM in 11 papers model/blocks.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · bc5a2b1350c91ae2 · report fixture: signature x:Tensor/3/float, gammas:Tensor/3/float, betas:Tensor/3/float · returned Tensor · level recorded 2026-09-22

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for FiLM (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for FiLM (graph method: FiLM). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. FiLM entry · level 1 · ran · bc5a2b1350c91ae2

harvested Assembly for FiLM (graph method: FiLM). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. FiLM entry · level 1 · ran · bd2e6b10e2f47993

harvested Assembly for FiLM (graph method: FiLM). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. FiLM entry · level 1 · ran · b8723266db5e5556

harvested Assembly for FiLM (graph method: FiLM). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 5 siblings

  1. FiLMLayer entry · level 1 · ran · 04d3db3a0eb24a12

harvested Assembly for FiLM (graph method: FiLM). 6 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. FiLM entry · level 0 · unverified · 6d21918b730bc046
  2. Classifier model · level 1 · ran · 37dda49b6caaba23
  3. FeatureExtractor model · level 1 · ran · edbfcccbabd461c6
  4. ResBlock model · level 1 · ran · 779ef9590306ac85
  5. conv helper · level 1 · ran · our draft was wrong · b4a8caf47616fa06
  6. FiLMBlock model · level 1 · ran · 32874c063a45b37a

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="1709.07871") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Retrieval with Multi-Modal QueryVisual Question Answering (VQA)Visual Question Answering (VQA) Split AVisual Question Answering (VQA) Split BVisual Reasoning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Retrieval with Multi-Modal Query MIT-States FiLM Recall@1 10.1 #4 of 5 Archive leaderboard report
Image Retrieval with Multi-Modal Query MIT-States FiLM Recall@10 38.3 #4 of 5 Archive leaderboard report
Image Retrieval with Multi-Modal Query MIT-States FiLM Recall@5 27.7 #4 of 5 Archive leaderboard report
Visual Question Answering (VQA) CLEVR CNN+GRU+FiLM Accuracy 97.7 #11 of 15 Archive leaderboard report
Visual Question Answering (VQA) CLEVR-Humans CNN+GRU+FiLM Accuracy 75.9 #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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