SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.02625 · ICML · 2024

Enhancing Transformer RNNs with Multiple Temporal Perspectives

Mihai Surdeanu, Razvan-Gabriel Dumitru, Darius Peteleaza

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.02625.json · badge: /api/ran/2402.02625.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
RazvanDu/TemporalRNNs canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
razvandu/temporalrnns canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
code Ran
ran, honoured the contract we drafted
RazvanDu/TemporalRNNs/MultiplePerspectives/src/binidx.py
pointer only (licence: NONE) · get_code("78743ba0d202ec36")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RazvanDu/TemporalRNNs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

cosine_similarity Ran
ran; our contract draft was wrong, not the code
RazvanDu/TemporalRNNs/MultiplePerspectives/src/model_run_ours.py
pointer only (licence: NONE) · get_code("c698017abb36d19c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RazvanDu/TemporalRNNs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

data_file_path Ran
ran; our contract draft was wrong, not the code
RazvanDu/TemporalRNNs/MultiplePerspectives/src/binidx.py
pointer only (licence: NONE) · get_code("bdf28f9492a770dc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RazvanDu/TemporalRNNs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

index_file_path Ran
ran; our contract draft was wrong, not the code
RazvanDu/TemporalRNNs/MultiplePerspectives/src/binidx.py
pointer only (licence: NONE) · get_code("8b1a74a6db32c163")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RazvanDu/TemporalRNNs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_float Ran
ran; our contract draft was wrong, not the code
RazvanDu/TemporalRNNs/MultiplePerspectives/src/utils.py
pointer only (licence: NONE) · get_code("c1934c6bad591733")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, RazvanDu/TemporalRNNs when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

RWKV_RNN Not yet run
unverified (harvested, no recorded run)
razvandu/temporalrnns/MultiplePerspectives/src/model_run_ours.py
pointer only (licence: NONE) · get_code("e7f22ce43cbbcab9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, razvandu/temporalrnns when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
data_file_path 8 other papers
5 dated earlier, 3 later
2022.emnlp-demos.40 (2022 (year only))
BMCook: A Task-agnostic Compression Toolkit for Big Models
2302.13939 (2023-02)
SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks
2305.09137 (2023-05)
Pre-Training to Learn in Context
and 5 more not named here
index_file_path 8 other papers
5 dated earlier, 3 later
2022.emnlp-demos.40 (2022 (year only))
BMCook: A Task-agnostic Compression Toolkit for Big Models
2302.13939 (2023-02)
SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks
2305.09137 (2023-05)
Pre-Training to Learn in Context
and 5 more not named here
code 7 other papers
4 dated earlier, 2 later, 1 same year, order not determinable
2022.emnlp-demos.40 (2022 (year only))
BMCook: A Task-agnostic Compression Toolkit for Big Models
2305.09137 (2023-05)
Pre-Training to Learn in Context
2307.15504 (2023-07)
Exploring Format Consistency for Instruction Tuning
and 4 more not named here
to_float 1 other paper
1 dated earlier
2302.13939 (2023-02)
SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce the concept of multiple temporal perspectives, a novel approach applicable to Recurrent Neural Network (RNN) architectures for enhancing their understanding of sequential data. This method involves maintaining diverse temporal views of previously encountered text, significantly enriching the language models' capacity to interpret context. To show the efficacy of this approach, we incorporate it into the Receptance Weighted Key Value (RWKV) architecture, addressing its inherent challenge of retaining all historical information within a single hidden state. Notably, this improvement is achieved with a minimal increase in the number of parameters -even as little as 0.04% of the original number of parameters. Further, the additional parameters necessary for the multiple temporal perspectives are fine-tuned with minimal computational overhead, avoiding the need for a full pre-training. The resulting model maintains linear computational complexity during prompt inference, ensuring consistent efficiency across various sequence lengths. The empirical results and ablation studies included in our research validate the effectiveness of our approach, showcasing improved performance across multiple benchmarks. The code, model weights and datasets are open-sourced at https://github.com/RazvanDu/TemporalRNNs.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.02625")
get_code_for_paper("2402.02625")
have("2402.02625")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.02625.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.02625.svg)](https://syntology.ai/paper/2402.02625)

Connect an agent — have() is free.