Home › Code › get_loss_func

get_loss_func

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

get_loss_func appears in the code Syntology harvested for 26 papers, as 19 distinct code bodies found in 27 places (a place is one code body under one paper). At least one of them ran in 13 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 get_loss_func 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 8 of the 19 distinct code bodies named get_loss_func; 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
7ran
11unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 7 of the 27 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

26 papers shown of 26, newest first; 27 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; 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
UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning added by Syntology 2026-06 (from id) Wenhao-Chi/UNIEGO/timesformer/models/losses.py c90b5f606f54d4f7 ran licence not identified · pointer only
Guided Diffusion Sampling on Function Spaces with Applications to PDEs 22 May 2025 neuraloperator/fundps/generation/dps.py 507e51ab566b1005 ran · our draft was wrong MIT (permissive)
Mean Flows for One-step Generative Modeling 19 May 2025 andypinxinliu/GestureLSM/optimizers/loss_factory.py 4f043bf1bec12652 ran MIT (permissive)
Motion meets Attention: Video Motion Prompts 3 Jul 2024 q1xiangchen/vmps/timesformer/models/losses.py c90b5f606f54d4f7 ran MIT (permissive)
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening 13 Jun 2024 BarSGuy/Efficient-Subgraph-GNNs/utils/training.py 87c78454cb407527 ran MIT (permissive)
MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models 14 Mar 2024 kkakkkka/MambaTalk/optimizers/loss_factory.py 4f043bf1bec12652 ran Apache-2.0 (permissive)
ReViT: Enhancing Vision Transformers Feature Diversity with Attention Residual Connections 17 Feb 2024 adiko1997/revit/model/loss.py 345d213a14918073 ran MIT (permissive)
Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products 13 Feb 2024 barsguy/subgraphormer/utils/training.py d0664f0de7749db7 ran MIT (permissive)
Pixel-Wise Recognition for Holistic Surgical Scene Understanding 20 Jan 2024 bcv-uniandes/grasp/TAPIS/tapis/models/losses.py c90b5f606f54d4f7 ran MIT (permissive)
Pixel-Wise Recognition for Holistic Surgical Scene Understanding 20 Jan 2024 bcv-uniandes/tapir/slowfast/models/losses.py aaac7c46cd146e47 ran MIT (permissive)
How Much Temporal Long-Term Context is Needed for Action Segmentation? 22 Aug 2023 ltcontext/ltcontext/ltc/model/loss.py 2399cfec24000d94 ran licence not identified · pointer only
AltFreezing for More General Video Face Forgery Detection 17 Jul 2023 zhendongwang6/altfreezing/slowfast/models/losses.py c90b5f606f54d4f7 ran MIT (permissive)
Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023 28 Jun 2023 dandoge/palm/ego4d_forecasting/models/losses.py dd72775d1ea00db7 unverified MIT (permissive)
Reversible Vision Transformers 9 Feb 2023 facebookresearch/mvit/mvit/models/losses.py 836ddfc4a5544d55 unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models 29 Jan 2023 haoheliu/audioldm_eval/audioldm_eval/feature_extractors/panns/losses.py e424ea90cdf3fd97 unverified MIT (permissive)
Video + CLIP Baseline for Ego4D Long-term Action Anticipation 1 Jul 2022 srijandas07/clip_baseline_lta_ego4d/ego4d/models/losses.py dd72775d1ea00db7 unverified MIT (permissive)
Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data 15 Dec 2021 RetroCirce/Zero_Shot_Audio_Source_Separation/losses.py 7205233542780552 unverified MIT (permissive)
Adaptive Token Sampling For Efficient Vision Transformers 30 Nov 2021 adaptivetokensampling/ATS/libs/models/losses.py ffe68781a7c4ab89 unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Ego4D: Around the World in 3,000 Hours of Egocentric Video 13 Oct 2021 ego4d/forecasting/ego4d_forecasting/models/losses.py dd72775d1ea00db7 unverified MIT (permissive)
Object-Region Video Transformers 13 Oct 2021 eladb3/orvit/slowfast/models/losses.py bd99fa4d54003b3b unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
MaCLR: Motion-aware Contrastive Learning of Representations for Videos 17 Jun 2021 amazon-science/self-supervised-maclr/slowfast/models/losses.py c90b5f606f54d4f7 ran Apache-2.0 (permissive)
ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos 25 May 2021 coldmanck/VidHOI/slowfast/models/losses.py c90b5f606f54d4f7 ran Apache-2.0 recorded; this copy not marked cleared · pointer only
PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition 2019-12 (from id) qiuqiangkong/audioset_tagging_cnn/pytorch/losses.py a79c3eb46da2b363 unverified MIT (permissive)
Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization 2019-12 (from id) qiuqiangkong/sound_event_detection_dcase2017_task4/pytorch/losses.py 8c5cf2ee2f049223 unverified MIT recorded; this copy not marked cleared · pointer only
SlowFast Networks for Video Recognition 10 Dec 2018 tonysy/PyAction/pyaction/models/losses.py ce9eeb4d3e39ef8b unverified Apache-2.0 (permissive)
arXiv:136950157 kami93/kcenter_video/kcenter_transformer/utils/losses.py 76d03c11b9f557f3 unverified Apache-2.0 (permissive)
arXiv:136950068 wangjk666/STTS/MViT/slowfast/models/losses.py 5d31891875a52ac6 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