Home › Code › average_checkpoints

average_checkpoints

Syntologyentry name in harvested coderead from the graph 2026-09-24

average_checkpoints appears in the code Syntology harvested for 21 papers, as 13 distinct code bodies found in 22 places (a place is one code body under one paper). At least one of them ran in 2 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named average_checkpoints do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 2 of the 13 distinct code bodies named average_checkpoints; 11 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
0ran · fixture could not drive it
1ran
11unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 6 of the 22 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

21 papers shown of 21, newest first; 22 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 1 papers added by Syntology; 1 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio Generation added by Syntology 2025-12 (from id) k2-fsa/Flow2GAN/flow2gan/checkpoint.py 74b622eae4c5ab2f unverified Apache-2.0 (permissive)
Unifying Streaming and Non-streaming Zipformer-based ASR 17 Jun 2025 k2-fsa/icefall/icefall/checkpoint.py c90ec0af48b591a2 unverified Apache-2.0 (permissive)
ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate 5 Nov 2024 iShohei220/adopt/imagenet/utils.py 4eca7815147e1708 unverified Apache-2.0 (permissive)
Textual Training for the Hassle-Free Removal of Unwanted Visual Data: Case Studies on OOD and Hateful Image Detection 30 Sep 2024 Saehyung-Lee/HFTT/utils.py 30862aa4330bfa12 unverified no licence file found · pointer only
Large Language Models are Strong Audio-Visual Speech Recognition Learners 18 Sep 2024 umbertocappellazzo/llama-avsr/utils/avg_checkpoints_original.py 3ae2eab75af094e1 unverified no licence file found · pointer only
Isomorphic Pruning for Vision Models 5 Jul 2024 VainF/Isomorphic-Pruning/pbench/utils.py 4eca7815147e1708 unverified no licence file found · pointer only
Self-Modifying State Modeling for Simultaneous Machine Translation 4 Jun 2024 EurekaForNLP/SM2/average_checkpoints.py 7cc2e301e30389d1 unverified MIT (permissive)
ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining 23 May 2024 syr-cn/reactxt/average_ckpt.py d73f14bf46e46bc6 unverified MIT (permissive)
BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition 2 Apr 2024 ahaliassos/raven/utils.py 96ab9eba7ed25bc3 ran MIT (permissive)
Hardware Resilience Properties of Text-Guided Image Classifiers 23 Nov 2023 talalwasim/textguidedresilience/utils.py 30862aa4330bfa12 unverified no licence file found · pointer only
LLM Performance Predictors are good initializers for Architecture Search 25 Oct 2023 ubc-nlp/llmas/average_checkpoints.py 7cc2e301e30389d1 unverified no licence file found · pointer only
Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels 25 Mar 2023 mpc001/auto_avsr/average_checkpoints.py 3ae2eab75af094e1 unverified Apache-2.0 (permissive)
Robust Speech Recognition via Large-Scale Weak Supervision 6 Dec 2022 open-creator/icefall/icefall/checkpoint.py 69124b03f4b749bd unverified Apache-2.0 (permissive)
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation 14 Oct 2022 microsoft/automoe/average_checkpoints.py 7cc2e301e30389d1 unverified MIT (permissive)
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs 26 Nov 2021 shantanuj/tdam_top_down_attention_module/training_and_usage_scripts/custom_utils.py 8166275d7eed870a unverified MIT (permissive)
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers 24 Mar 2021 zeyuanyin/tiny-imagenet/classification/utils.py 30862aa4330bfa12 unverified MIT (permissive)
Very Deep Transformers for Neural Machine Translation 18 Aug 2020 microsoft/deepnmt/nmt_eval/average_checkpoints.py 7cc2e301e30389d1 unverified MIT (permissive)
Enhancing Monotonic Multihead Attention for Streaming ASR 19 May 2020 hirofumi0810/neural_sp/neural_sp/bin/eval_utils.py 6ff5a3b80d5b430d unverified Apache-2.0 (permissive)
Time-aware Large Kernel Convolutions 8 Feb 2020 lioutasb/talkconvolutions/utils/average_checkpoints.py 93ba0aaaba0bfada ran · our draft was wrong MIT (permissive)
Time-aware Large Kernel Convolutions 8 Feb 2020 lioutasb/TaLKConvolutions/utils/average_checkpoints.py 7cc2e301e30389d1 unverified MIT (permissive)
Data Diversification: A Simple Strategy For Neural Machine Translation 5 Nov 2019 nxphi47/data_diversification/average_checkpoints.py fcf378b4ce4a5217 unverified no licence file found · pointer only
arXiv:2024.findings-acl.318 syr-cn/ReactXT/average_ckpt.py d73f14bf46e46bc6 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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