Papers › Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks

Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks

6 Feb 2024arXiv:2402.04248archive 2025-07-28

Jongho Park, Jaeseung Park, Zheyang Xiong, Nayoung Lee, Jaewoong Cho, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos

State-space models (SSMs), such as Mamba (Gu & Dao, 2023), have been proposed as alternatives to Transformer networks in language modeling, by incorporating gating, convolutions, and input-dependent token selection to mitigate the quadratic cost of multi-head attention. Although SSMs exhibit competitive performance, their in-context learning (ICL) capabilities, a remarkable emergent property of modern language models that enables task execution without parameter optimization, remain underexplored compared to Transformers. In this study, we evaluate the ICL performance of SSMs, focusing on Mamba, against Transformer models across various tasks. Our results show that SSMs perform comparably to Transformers in standard regression ICL tasks, while outperforming them in tasks like sparse parity learning. However, SSMs fall short in tasks involving non-standard retrieval functionality. To address these limitations, we introduce a hybrid model, MambaFormer, that combines Mamba with attention blocks, surpassing individual models in tasks where they struggle independently. Our findings suggest that hybrid architectures offer promising avenues for enhancing ICL in language models.

PaperPDFCodeCode Syntology ran

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 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 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 (6 with no instrument failure; 5 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

krafton-ai/mambaformer-icl officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 11 ran (5 instrument-failed) · 3 unverified report
hazyresearch/based mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Zoology: Measuring and Improving Recall in Efficient Language Models (arXiv:2312.04927; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

14 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 5 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · violated contract
5ran · our draft was wrong
5ran
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 krafton-ai/mambaformer-icl. “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.

krafton-ai/mambaformer-icl official repository 14 samples, 11 ran (5 instrument-failed) · 3 unverified
basic_plot in 5 papers src/plot_utils.py ran Apache-2.0 (permissive) · 5b74687909baf467 · report fixture: signature metrics:dict/0/?, models:list/1/str, trivial:float/0/float, colors:list/1/str · returned tuple · level recorded 2026-09-24
generate_dummy_vector src/filtering_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b1c1ac424117b8de · report fixture: signature w:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_final_var in 9 papers src/curriculum.py ran Apache-2.0 (permissive) · 3c24ac252fef0868 · report fixture: signature init_var:float/0/float, total_steps:int/0/int, inc:float/0/float, n_steps:int/0/int, lim:float/0/float · returned float · level recorded 2026-09-25
mean_squared_error in 26 papers src/tasks.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · fc94f27a0973e093 · report fixture: signature ys_pred:Tensor/2/float, ys:Tensor/2/float · returned Tensor · level recorded 2026-09-22
orthogonalize in 5 papers src/filtering_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · a46d1c2a317b35c5 · report fixture: signature vector:Tensor/2/float, basis:Tensor/2/float · returned Tensor · level recorded 2026-09-24
sample_transformation in 5 papers src/samplers.py ran · our draft was wrong Apache-2.0 (permissive) · 7f92ad21604fa243 · report fixture: signature eigenvalues:Tensor/1/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-25
squared_error in 9 papers src/tasks.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 348d63a78eb4cb94 · report fixture: signature ys_pred:Tensor/2/float, ys:Tensor/2/float · returned Tensor · level recorded 2026-09-22
squared_norm_error src/tasks.py ran fingerprinted Apache-2.0 (permissive) · b4326d9d300aa5c0 · report fixture: signature ys_pred:Tensor/2/float, ys:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-24
str2bool in 533 papers src/util.py ran · violated contract Apache-2.0 (permissive) · 8605dc8a088f3db8 · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
train_step in 47 papers src/train_parallel.py ran Apache-2.0 (permissive) · 47f61861b53edf4d · report fixture: signature rank:int/0/int, iter:int/0/int, model:callable/0/?, xs:Tensor/2/float, ys:Tensor/3/float, optimizer:SGD/0/?, loss_func:callable/0/?, max_grad_norm:float/0/float, filtering_inds:Tensor/1/bool · returned tuple · level recorded 2026-09-24
zero_pad_ys src/filtering_utils.py ran Apache-2.0 (permissive) · 75e826964a91f44b · report fixture: signature tokenized:bool/0/bool, xs:Tensor/2/float, ys:Tensor/2/float · returned Tensor · level recorded 2026-09-24
get_data_sampler in 6 papers src/samplers.py unverified Apache-2.0 (permissive) · 54f3966e15e1afe1 · report
randperm_2d_with_query src/samplers.py unverified Apache-2.0 (permissive) · ddd35c92ba9c2871 · report
sample_seeds src/train_parallel.py unverified Apache-2.0 (permissive) · 4d49c710f74c99c4 · report

Tasks

In-Context LearningLanguage ModelingLanguage ModellingMambaRetrievalState Space Models

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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