Home › Code › compress

compress

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

compress appears in the code Syntology harvested for 35 papers, as 11 distinct code bodies found in 35 places (a place is one code body under one paper). At least one of them ran in 9 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 compress 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 4 of the 11 distinct code bodies named compress; 7 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
1ran · fixture could not drive it
2ran
7unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 13 of the 35 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

35 papers shown of 35, newest first; 35 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 4 papers added by Syntology; 2 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
Thinned Mean Field Langevin Dynamics added by Syntology 2026-05 (from id) hudsonchen/thinned_mfld/utils/kt.py b8179bb351b7af3d ran no licence file found · pointer only
LoReC: Rethinking Large Language Models for Graph Data Analysis added by Syntology 2026-04 (from id) Git-King-Zhan/LoReC/lorec-gpt/graphgpt/model/compression.py 80dde39da1ba3708 unverified no licence file found · pointer only
DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment added by Syntology 2026-03 (from id) lm-sys/FastChat/fastchat/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
Garbage Attention in Large Language Models: <BOS> Sink Heads and Sink-aware Pruning added by Syntology 2026-01 (from id) CASIA-LMC-Lab/FLAP/lib/prune.py 1e3629d8fc0ca6c7 unverified Apache-2.0 (permissive)
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models 26 Sep 2024 hui-po-wang/LM-GC/compressors/png.py a97701702e1a2e67 ran MIT (permissive)
Exploring Design Choices for Building Language-Specific LLMs 20 Jun 2024 atutej/token-language-adaptation/FastChat/fastchat/model/compression.py 80dde39da1ba3708 unverified no licence file found · pointer only
FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models 7 Jun 2024 rui-ye/fedllm-bench/compression.py 80dde39da1ba3708 unverified no licence file found · pointer only
Debiased Distribution Compression 18 Apr 2024 identical code first harvested elsewhere 9a913678c56785e8 ran · fixture could not drive it licence of this copy not recorded
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models 12 Mar 2024 openbmb/toolbench/toolbench/model/compression.py 386536152177a379 unverified Apache-2.0 (permissive)
Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference 7 Mar 2024 BirgerMoell/SwedishLLMBenchmark/fastchat/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents 4 Mar 2024 yifan-song793/eto/fastchat/model/compression.py 80dde39da1ba3708 unverified no licence file found · pointer only
UrbanGPT: Spatio-Temporal Large Language Models 25 Feb 2024 hkuds/urbangpt/urbangpt/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
Graph Diffusion Policy Optimization 26 Feb 2024 sail-sg/gdpo/model/diffusion_discrete.py 4d13d6ce3ccd0cc1 unverified no licence file found · pointer only
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic 19 Feb 2024 declare-lab/red-instruct/starling_training/fastchat/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning 3 Feb 2024 WEIYanbin1999/GITA/fastchat/model/compression.py 80dde39da1ba3708 unverified no licence file found · pointer only
RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning 16 Jan 2024 Junjie-Ye/RoTBench/Code/model/compression.py 386536152177a379 unverified Apache-2.0 (permissive)
VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things 1 Dec 2023 zhongyy/viotgpt/train/compression.py 386536152177a379 unverified no licence file found · pointer only
Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks 30 Oct 2023 qtli/coeval/webapp/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
JudgeLM: Fine-tuned Large Language Models are Scalable Judges 26 Oct 2023 hitz-zentroa/eval-MCG-COLING-2025/evaluation/JudgeLM-main/judgelm/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
GraphGPT: Graph Instruction Tuning for Large Language Models 19 Oct 2023 HKUDS/GraphGPT/graphgpt/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
Language Modeling Is Compression 19 Sep 2023 google-deepmind/language_modeling_is_compression/compressors/png.py a97701702e1a2e67 ran Apache-2.0 (permissive)
3D-LLM: Injecting the 3D World into Large Language Models 24 Jul 2023 umass-foundation-model/3d-llm/3DLanguage_data/ChatCaptioner_based/quetion_model.py 80dde39da1ba3708 unverified MIT recorded; this copy not marked cleared · pointer only
Phoenix: Democratizing ChatGPT across Languages 20 Apr 2023 freedomintelligence/llmzoo/llmzoo/deploy/webapp/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU 13 Mar 2023 fminference/flexgen/flexllmgen/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
Compress Then Test: Powerful Kernel Testing in Near-linear Time 14 Jan 2023 identical code first harvested elsewhere 9a913678c56785e8 ran · fixture could not drive it licence of this copy not recorded
Self-attention Does Not Need $O(n^2)$ Memory 10 Dec 2021 stability-ai/fastchat/fastchat/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (permissive)
Distribution Compression in Near-linear Time 15 Nov 2021 microsoft/goodpoints/goodpoints/compress.py 9a913678c56785e8 ran · fixture could not drive it MIT (permissive)
Generalized Kernel Thinning 4 Oct 2021 identical code first harvested elsewhere 9a913678c56785e8 ran · fixture could not drive it licence of this copy not recorded
Unsupervised Hashing with Contrastive Information Bottleneck 13 May 2021 qiuzx2/CIBHash/model/CIBHash.py 9d8f8e1077379f49 ran · our draft was wrong MIT (permissive)
Kernel Thinning 12 May 2021 identical code first harvested elsewhere 9a913678c56785e8 ran · fixture could not drive it licence of this copy not recorded
Event Outlier Detection in Continuous Time 19 Dec 2019 siqil/CPPOD/summarize_results_std.py 2889e16a4eb04885 unverified MIT (permissive)
Deep Signature Transforms 21 May 2019 anh-tong/signax/src/signax/utils.py 240a22a9a6f347bd unverified MIT (permissive)
Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression 20 Mar 2019 mauriceqch/pcc_geo_cnn/src/compress.py 68ecd4d88b382314 unverified MIT (permissive)
arXiv:2025.emnlp-main.1337 RazvanDu/CopySpec/FastChat/fastchat/model/compression.py 80dde39da1ba3708 unverified MIT (permissive)
arXiv:2024.findings-emnlp.559 hitz-zentroa/cn-eval/evaluation/JudgeLM-main/judgelm/model/compression.py 80dde39da1ba3708 unverified Apache-2.0 (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