Papers › Compositional Generalization in Grounded Language Learning via Induced Model Sparsity

Compositional Generalization in Grounded Language Learning via Induced Model Sparsity

6 Jul 2022NAACL (ACL) 2022 7arXiv:2207.02518archive 2025-07-28

Sam Spilsbury, Alexander Ilin

We provide a study of how induced model sparsity can help achieve compositional generalization and better sample efficiency in grounded language learning problems. We consider simple language-conditioned navigation problems in a grid world environment with disentangled observations. We show that standard neural architectures do not always yield compositional generalization. To address this, we design an agent that contains a goal identification module that encourages sparse correlations between words in the instruction and attributes of objects, composing them together to find the goal. The output of the goal identification module is the input to a value iteration network planner. Our agent maintains a high level of performance on goals containing novel combinations of properties even when learning from a handful of demonstrations. We examine the internal representations of our agent and find the correct correspondences between words in its dictionary and attributes in the environment.

PaperPDFConference PDFCodeCode 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 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 7 ran (7 with no instrument failure; 0 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.

aalto-ai/sparse-compgen officialmentioned in paperpytorchSyntology: 10 samples, 7 ran (0 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

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 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.

7ran
3unverified

Licence: 0 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 aalto-ai/sparse-compgen. “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.

aalto-ai/sparse-compgen official repository 10 samples, 7 ran (0 instrument-failed) · 3 unverified
ImageBOWEmbedding grounded_compgen_research/models/imitation/conv_transformer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · ce9a198bf543d15d · report fixture: signature inputs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ImageBlock grounded_compgen_research/models/imitation/conv_transformer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · f363048cbd07e14e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
InstructionEncodingBlock grounded_compgen_research/models/imitation/conv_transformer.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 0f60d4b3cc7f7bdb · report fixture: signature sentence:Tensor/2/int · returned tuple · level recorded 2026-09-22
ObservationBlock grounded_compgen_research/models/imitation/conv_transformer.py ran fingerprinted MIT (permissive) · 6ff15de325f9d856 · report fixture: signature img:Tensor/4/int · returned Tensor · level recorded 2026-09-24
PositionalAddEncoding grounded_compgen_research/models/imitation/conv_transformer.py ran · metamorphic tier: invariant MIT (permissive) · 7a2b9fca729945a9 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 1 of 5, arg 1: rank 3, kind float, dtype float32
grounded_compgen_research/models/imitation/conv_transformer.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 6d88134a57f82380 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
RelationalBlock grounded_compgen_research/models/imitation/conv_transformer.py ran MIT (permissive) · 11e6375c51d915d7 · report fixture: signature x:tuple/1/Tensor · returned tuple · level recorded 2026-09-24
ConvTransformerModel grounded_compgen_research/models/imitation/conv_transformer.py unverified MIT (permissive) · 86f07e914b4a1a28 · report
ProcessingTransformer grounded_compgen_research/models/imitation/conv_transformer.py unverified MIT (permissive) · e6c51e69ff1b0120 · report
initialize_parameters grounded_compgen_research/models/imitation/conv_transformer.py unverified MIT (permissive) · 6125d291452ba72a · 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 Induced Model Sparsity (graph method: Induced Model Sparsity). 10 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. ConvTransformerModel entry · level 0 · unverified · 86f07e914b4a1a28
  2. ProcessingTransformer model · level 0 · unverified · e6c51e69ff1b0120
  3. InstructionEncodingBlock model · level 1 · ran · 0f60d4b3cc7f7bdb
  4. ObservationBlock model · level 1 · ran · 6ff15de325f9d856
  5. RelationalBlock model · level 1 · ran · 11e6375c51d915d7
  6. PositionalAddEncoding helper · level 1 · ran · 7a2b9fca729945a9
  7. ImageBOWEmbedding helper · level 1 · ran · ce9a198bf543d15d
  8. ImageBlock model · level 1 · ran · f363048cbd07e14e
  9. initialize_parameters helper · level 0 · unverified · 6125d291452ba72a
  10. PositionalEncoding helper · level 1 · ran · 6d88134a57f82380

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="2207.02518") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Grounded language learning

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