Methods › General › Optimization › Lion

Evolved Sign Momentum

Lion

32 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

The Lion optimizer is discovered by symbolic program search. It is more memory-efficient than most adaptive optimizers as it only needs to momentum. The update of Lion is produced by the sign function.

See Code · google/automl

In Syntology repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2305.12870) is about this method is not checked.

From the lookup's note on this name: The same name also belongs to “LION”, a method in the paper “LION: Latent Point Diffusion Models for 3D Shape Generation” (arXiv:2210.06978, 733 citations), which the lookup finds cited far more than the paper this answer is about (49 citations), so this answer may be about a different sense of the name. For arXiv:2210.06978: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2305.12870 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified (of 11 harvested samples) · 1 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 32 · with a code link: 11 · where Syntology ran a sample: 9 (8 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (9 of 32 tagged: 8 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 32 of 32, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 38 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Language Modeling4
Language Modelling4
Quantization3
Contrastive Learning2
GPU2
Position2
Stochastic Optimization2
parameter-efficient fine-tuning2
3D Object Detection1
Attribute1
Audio-Visual Speech Recognition1
Diversity1
Federated Learning1
Handwritten Text Recognition1
Image Classification1
L2 Regularization1
LAMBADA1
Large Language Model1
Lip Reading1
Lipreading1

Usage over time archive 2025-07-28

Papers per year tagged with Lion: 2023 to 2025, peak 14 14 0 2023: 12 papers 2023 2024: 14 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (32 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Optimization

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