SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.09160 · ICLR · 2025

EFFICIENT RESOURCE-CONSTRAINED TRAINING OF TRANSFORMERS VIA SUBSPACE OPTIMIZATION

Enzo Tartaglione, Van-Tam Nguyen, Le-Trung Nguyen

arXiv · PDF · Open in the Atlas

Code that ran

None of the 5 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (5 no recorded run), measured 2026-11-22; 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/2510.09160.json · badge: /api/ran/2510.09160.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
Le-TrungNguyen/ICLR2026-WASI community
Papers with Code archive
0 ran · 5 no recorded run
FunctionStatusWhere it lives
Linear_WASI_op Not yet run
unverified (harvested, no recorded run)
Le-TrungNguyen/ICLR2026-WASI/main/custom_op/linear/linear_WASI.py
pointer only (licence: NONE) · get_code("85673bd2f016892f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Le-TrungNguyen/ICLR2026-WASI 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.

_get_wasi_streams Not yet run
unverified (harvested, no recorded run)
Le-TrungNguyen/ICLR2026-WASI/main/custom_op/linear/linear_WASI.py
pointer only (licence: NONE) · get_code("242e22557809363f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Le-TrungNguyen/ICLR2026-WASI 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.

_low_rank_linear Not yet run
unverified (harvested, no recorded run)
Le-TrungNguyen/ICLR2026-WASI/main/custom_op/linear/linear_WASI.py
pointer only (licence: NONE) · get_code("b6f2df73350c1d74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Le-TrungNguyen/ICLR2026-WASI 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.

_wasi_grad_weight_3d Not yet run
unverified (harvested, no recorded run)
Le-TrungNguyen/ICLR2026-WASI/main/custom_op/linear/linear_WASI.py
pointer only (licence: NONE) · get_code("21fde2690444842c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Le-TrungNguyen/ICLR2026-WASI 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.

_wasi_grad_weight_4d Not yet run
unverified (harvested, no recorded run)
Le-TrungNguyen/ICLR2026-WASI/main/custom_op/linear/linear_WASI.py
pointer only (licence: NONE) · get_code("fc79ed64e6c1d90e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Le-TrungNguyen/ICLR2026-WASI 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

As AI increasingly shapes daily life, energy consumption and data privacy have become pressing concerns. On-device learning trains models directly on edge devices, cutting energy consumption and safeguarding data privacy. However, the expanding scale of modern neural networks creates a major obstacle for ondevice training. Although prior work has concentrated on compact convolutional architectures, we instead apply subspace-based training to transformer models. Motivated by the idea that a model's essential information lies in a fixed subspace, we introduce Weight-Activation Subspace Iteration (WASI), a method that mitigates the memory bottleneck of backpropagation and boosts inference efficiency in transformer models by restricting training to this subspace. Our results demonstrate that WASI maintains accuracy comparable to vanilla training while reducing memory usage by up to 62× and computational cost (FLOPs) by up to 2×. On a Raspberry Pi 5, WASI achieves roughly 1.4× faster training and inference than vanilla training. The code is available at https://github.com/Le-TrungNguyen/ICLR2026-WASI.git.

For agents

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

get_harvested_code_for_paper("2510.09160")
get_code_for_paper("2510.09160")
have("2510.09160")

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

curl https://syntology.ai/api/ran/2510.09160.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.09160.svg)](https://syntology.ai/paper/2510.09160)

Connect an agent — have() is free.