Papers › Can Transformers Learn Full Bayesian Inference in Context?
Can Transformers Learn Full Bayesian Inference in Context?
Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, David Rügamer
Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. While not yet fully understood, ICL has already proved to be an intriguing phenomenon, allowing transformers to learn in context -- without requiring further training. In this paper, we further advance the understanding of ICL by demonstrating that transformers can perform full Bayesian inference for commonly used statistical models in context. More specifically, we introduce a general framework that builds on ideas from prior fitted networks and continuous normalizing flows which enables us to infer complex posterior distributions for methods such as generalized linear models and latent factor models. Extensive experiments on real-world datasets demonstrate that our ICL approach yields posterior samples that are similar in quality to state-of-the-art MCMC or variational inference methods not operating in context.
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 general framework, 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='general framework') (how to connect); the free check have('2501.16825') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2501.16825")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2501.16825", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2501.16825")
Code
Syntology 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.
By repository: official repository: 16 samples from 1 repository, 12 ran (12 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. 1 of the 12 samples that ran has 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
16 samples harvested: 12 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 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.
Licence: 16 of the 16 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 arikreuter/icl_for_full_bayesian_inference. “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 4 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.
3672477c19ee824f · report
fixture: returned ConditionalBatchNorm · level recorded 2026-09-22 7334dfff7c15eb8c · report
fixture: returned ConditionalLayerNorm · level recorded 2026-09-22 8746a274af2a0929 · report
fixture: returned DecoderBlockConditional · level recorded 2026-09-22 cf23a8049b4ef088 · report
fixture: returned EncoderBlockConditional · level recorded 2026-09-22 8f40ac592744ccad · report
fixture: returned Linear_block · level recorded 2026-09-22 02ac666b2ac3c6a1 · report
fixture: returned Linear_skip_block · level recorded 2026-09-22 67f27ed04e3e9672 · report
fixture: returned MLP · level recorded 2026-09-22 19ec286a9acca6f1 · report
fixture: returned MLPConditional · level recorded 2026-09-22 census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket LinearRegression/Models/Transformer_CNF.py ran no licence file found · pointer only ·
870643f6c036b79d · report
fixture: returned PositionalEncoding · level recorded 2026-09-22 c8a3be75f1c48e47 · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24 a5253f7ea1d3f236 · report
fixture: signature x:Tensor/3/float, condition:Tensor/2/float · returned Tensor · level recorded 2026-09-24 c838b52183d58395 · report
fixture: signature s:str/0/str · returned bool · level recorded, date not recorded 76c46a50e69c7c97 · report
420e50cb6931a973 · report
6a80680a5be99f66 · report
ad9007e5c53a09ac · 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. 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 general framework (graph method: general framework), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 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)
- sample_gmm_observation entry · level 3 · ran · violated contract ·
c8550f83f55b0a0136a97899e2ef4037e5113414837abe7bf85077145af191bb
harvested Assembly for general framework (graph method: general framework). 15 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
- TransformerCNF entry · level 0 · unverified ·
76c46a50e69c7c97 - MLPConditional model · level 1 · ran ·
19ec286a9acca6f1 - TransformerConditional helper · level 0 · unverified ·
420e50cb6931a973 - ConditionalBatchNorm helper · level 1 · ran ·
3672477c19ee824f - Linear_block helper · level 1 · ran ·
8f40ac592744ccad - Linear_skip_block helper · level 1 · ran ·
02ac666b2ac3c6a1 - MLP helper · level 1 · ran ·
67f27ed04e3e9672 - TransformerDecoderConditional model · level 0 · unverified ·
6a80680a5be99f66 - TransformerEncoderConditional model · level 0 · unverified ·
ad9007e5c53a09ac - DecoderBlockConditional model · level 1 · ran ·
8746a274af2a0929 - PositionalEncoding helper · level 1 · ran ·
870643f6c036b79d - EncoderBlockConditional helper · level 1 · ran ·
cf23a8049b4ef088 - ConditionalLayerNorm model · level 1 · ran ·
7334dfff7c15eb8c - PositionwiseFeedForward model · level 1 · ran ·
c8a3be75f1c48e47 - Rescale model · level 1 · ran ·
a5253f7ea1d3f236
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="2501.16825") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
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