SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.09808 · 2024

Famba-V: Fast Vision Mamba with Cross-Layer Token Fusion

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 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/2409.09808.json · badge: /api/ran/2409.09808.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
aiot-mlsys-lab/famba-v canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
bipartite_soft_matching Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aiot-mlsys-lab/famba-v/fambav/token_merge.py
pointer only (licence: NONE); the stored copy get_code serves, from facebookresearch/tome, is pointer only (licence: NOASSERTION) · get_code("424049f15b90678d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

broadcat Ran
ran, honoured the contract we drafted
aiot-mlsys-lab/famba-v/fambav/rope.py
pointer only (licence: NONE) · get_code("f50a8d20efb35c68")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

build_transform Ran
ran; our contract draft was wrong, not the code
aiot-mlsys-lab/famba-v/fambav/datasets.py
pointer only (licence: NONE) · get_code("ebeb7b6e20a434cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

causal_conv1d_ref Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aiot-mlsys-lab/famba-v/causal-conv1d/causal_conv1d/causal_conv1d_interface.py
pointer only (licence: NONE) · get_code("0595d8b8521fd9ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

do_nothing Ran
ran, honoured the contract we drafted
aiot-mlsys-lab/famba-v/fambav/token_merge.py
pointer only (licence: NONE) · get_code("969e8250d805a154")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

kth_bipartite_soft_matching Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
aiot-mlsys-lab/famba-v/fambav/token_merge.py
pointer only (licence: NONE) · get_code("674be50d432e8846")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

new_data_aug_generator Ran
ran; our contract draft was wrong, not the code
aiot-mlsys-lab/famba-v/fambav/augment.py
pointer only (licence: NONE) · get_code("4a0feeebf8ac43a8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

rotate_half Ran
ran; our contract draft was wrong, not the code
aiot-mlsys-lab/famba-v/fambav/rope.py
pointer only (licence: NONE) · get_code("58823d9435a8751b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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.

build_dataset Not yet run
unverified (harvested, no recorded run)
aiot-mlsys-lab/famba-v/fambav/datasets.py
pointer only (licence: NONE) · get_code("80ba95ca0da5ce5f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, aiot-mlsys-lab/famba-v 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 1 the same month, 6 later) and 1 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
rotate_half 21 other papers
8 dated earlier, 12 later, 1 same year, order not determinable · 5 only as an assembly brick
2104.09864 (2021-04)
RoFormer: Enhanced Transformer with Rotary Position Embedding
2205.07514 (2022-05)
Residual Local Feature Network for Efficient Super-Resolution
2211.10658 (2022-11)
EDGE: Editable Dance Generation From Music
and 18 more not named here
broadcat 20 other papers
8 dated earlier, 11 later, 1 same year, order not determinable · 5 only as an assembly brick
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2205.07514 (2022-05)
Residual Local Feature Network for Efficient Super-Resolution
2211.10658 (2022-11)
EDGE: Editable Dance Generation From Music
and 17 more not named here
do_nothing 13 other papers
9 dated earlier, 1 the same month, 3 later · 4 only as an assembly brick
2210.09461 (2022-10)
Token Merging: Your ViT But Faster
2307.10780 (2023-07)
Learned Thresholds Token Merging and Pruning for Vision Transformers
2310.01812 (2023-10)
PPT: Token Pruning and Pooling for Efficient Vision Transformers
and 10 more not named here
bipartite_soft_matching 6 other papers
5 dated earlier, 1 later
2210.09461 (2022-10)
Token Merging: Your ViT But Faster
2307.10780 (2023-07)
Learned Thresholds Token Merging and Pruning for Vision Transformers
2310.01812 (2023-10)
PPT: Token Pruning and Pooling for Efficient Vision Transformers
and 3 more not named here
build_transform 6 other papers
4 dated earlier, 2 later
2310.01812 (2023-10)
PPT: Token Pruning and Pooling for Efficient Vision Transformers
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
2403.01590 (2024-03)
The Hidden Attention of Mamba Models
and 3 more not named here
kth_bipartite_soft_matching 4 other papers
4 dated earlier
2307.10780 (2023-07)
Learned Thresholds Token Merging and Pruning for Vision Transformers
2310.01812 (2023-10)
PPT: Token Pruning and Pooling for Efficient Vision Transformers
2310.19060 (2023-10)
TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding
and 1 more not named here
new_data_aug_generator 4 other papers
2 dated earlier, 2 later
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
2403.01590 (2024-03)
The Hidden Attention of Mamba Models
2411.04168 (2024-11)
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
and 1 more not named here
causal_conv1d_ref 3 other papers
3 dated earlier
2401.14168 (2024-01)
Vivim: a Video Vision Mamba for Medical Video Segmentation
2402.05608 (2024-02)
Scalable Diffusion Models with State Space Backbone
2407.21773 (2024-07)
RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining

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

Mamba and Vision Mamba (Vim) models have shown their potential as an alternative to methods based on Transformer architecture. This work introduces Fast Mamba for Vision (Famba-V), a cross-layer token fusion technique to enhance the training efficiency of Vim models. The key idea of Famba-V is to identify and fuse similar tokens across different Vim layers based on a suit of cross-layer strategies instead of simply applying token fusion uniformly across all the layers that existing works propose. We evaluate the performance of Famba-V on CIFAR-100. Our results show that Famba-V is able to enhance the training efficiency of Vim models by reducing both training time and peak memory usage during training. Moreover, the proposed cross-layer strategies allow Famba-V to deliver superior accuracy-efficiency trade-offs. These results all together demonstrate Famba-V as a promising efficiency enhancement technique for Vim models.

For agents

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

get_harvested_code_for_paper("2409.09808")
get_code_for_paper("2409.09808")
have("2409.09808")

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

curl https://syntology.ai/api/ran/2409.09808.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.09808.svg)](https://syntology.ai/paper/2409.09808)

Connect an agent — have() is free.