SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.02048 · NeurIPS · 2022

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

Chenlin Meng, Stefano Ermon, Ji Lin, Song Han, Jun-Yan Zhu, Muyang Li

arXiv · PDF · Open in the Atlas

Code that ran

6 of 17 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; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 11 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/2211.02048.json · badge: /api/ran/2211.02048.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
lmxyy/sige canonical (classifier label)
classifier basis: classifier_2025
6 ran · 11 no recorded run
FunctionStatusWhere it lives
Downsample Ran
ran on a synthesized input
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("7a0f92aace8379bd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEConv2d Ran
ran on a synthesized input
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("335c75661060896d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEModule Ran
ran on a synthesized input
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("d507545007f66e19")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("b8dedf14898e5502")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

my_group_norm Ran
ran on a synthesized input
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("1dc30e6b525d42ae")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

reduce_mask Ran
ran on a synthesized input
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("153647897a024a30")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

Gather Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("e6819730eb3cbd0f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEDownsample Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("5fd30a8dc69ba054")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEFusedAttnBlock Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("ab08502e82055fad")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEFusedResnetBlock Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("4f54fe4195f44e4a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEFusedUNet Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("045129cab1cb8c3a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEModel Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("024f482cc587c98d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEModuleWrapper Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("8a575c88399bbcf7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

SIGEUpsample Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("f153297ee40e8b8d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

Scatter Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("aae8fcf6a37d95da")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

ScatterGather Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("c3a4f27f51286763")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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.

ScatterWithBlockResidual Not yet run
unverified (harvested, no recorded run)
lmxyy/sige/diffusion/models/ddpm_arch/sige_fused_unet.py
pointer only (licence: NOASSERTION) · get_code("198eb290f706c5a3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lmxyy/sige (NOASSERTION). 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 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 17 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

During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing operations. In this work, we present Spatially Sparse Inference (SSI), a general-purpose technique that selectively performs computation for edited regions and accelerates various generative models, including both conditional GANs and diffusion models. Our key observation is that users prone to gradually edit the input image. This motivates us to cache and reuse the feature maps of the original image. Given an edited image, we sparsely apply the convolutional filters to the edited regions while reusing the cached features for the unedited areas. Based on our algorithm, we further propose Sparse Incremental Generative Engine (SIGE) to convert the computation reduction to latency reduction on off-the-shelf hardware. With about 1%-area edits, SIGE accelerates DDPM by 3.0× on NVIDIA RTX 3090 and 4.6× on Apple M1 Pro GPU, Stable Diffusion by 7.2× on 3090, and GauGAN by 5.6× on 3090 and 5.2× on M1 Pro GPU. Compared to our conference version, we extend SIGE to accommodate attention layers and apply it to Stable Diffusion. Additionally, we offer support for Apple M1 Pro GPU and include more results with large and sequential edits.

For agents

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

get_harvested_code_for_paper("2211.02048")
get_code_for_paper("2211.02048")
have("2211.02048")

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

curl https://syntology.ai/api/ran/2211.02048.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.02048.svg)](https://syntology.ai/paper/2211.02048)

Connect an agent — have() is free.