Home › Code › feature_loss

feature_loss

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

feature_loss appears in the code Syntology harvested for 27 papers, as 8 distinct code bodies found in 28 places (a place is one code body under one paper). At least one of them ran in 20 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 feature_loss 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 5 of the 8 distinct code bodies named feature_loss; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
4ran
3unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 5 of the 28 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

27 papers shown of 27, newest first; 28 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. 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
SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis 14 Apr 2025 wxzyd123/safespeech/bert_vits2/losses.py 24e8b4731dc3e070 unverified MIT (permissive)
FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching 9 Jan 2025 jjunak-yun/FLowHigh_code/vocoder/BIGVGAN/bigvgan/models.py e453b51f0ed5fb28 ran MIT (permissive)
Mitigating Unauthorized Speech Synthesis for Voice Protection 28 Oct 2024 wxzyd123/pivotal_objective_perturbation/vits/losses.py 24e8b4731dc3e070 unverified no licence file found · pointer only
WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification 2024-09 (from id) zjzser/wmcodec/models.py e453b51f0ed5fb28 ran no licence file found · pointer only
CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approach 15 Jun 2024 hli1221/crossfuse/network/loss.py 849efbd3c9fe8c54 ran no licence file found · pointer only
Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control 4 Jun 2024 yxlu-0102/AP-BWE/models/model.py 4518cce23c4f900e ran MIT (permissive)
Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching 1 Jun 2024 cyanbx/Frieren-V2A/Frieren/vocoder/bigvgan/models.py e453b51f0ed5fb28 ran Apache-2.0 (permissive)
Multi-Scale Sub-Band Constant-Q Transform Discriminator for High-Fidelity Vocoder 2023-11 (from id) nvidia/bigvgan/loss.py 95f8dc8b58c53187 ran MIT (permissive)
Ring Attention with Blockwise Transformers for Near-Infinite Context 3 Oct 2023 seongho608/ringformer/losses.py 24e8b4731dc3e070 unverified MIT (permissive)
Fewer-token Neural Speech Codec with Time-invariant Codes 2023-10 (from id) y-ren16/ticodec/academicodec/models/ticodec/models.py e453b51f0ed5fb28 ran no licence file found · pointer only
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis 1 Jun 2023 IAHispano/Applio/rvc/train/losses.py 0f7c6286a8d000f3 unverified MIT (permissive)
XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech 31 May 2023 vinairesearch/xphonebert/VITS_with_XPhoneBERT/losses.py 24e8b4731dc3e070 unverified MIT (permissive)
Scaling Speech Technology to 1,000+ Languages 22 May 2023 ylacombe/finetune-hf-vits/run_vits_finetuning.py 8feddae84063cbbc ran · honoured contract MIT (permissive)
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model 11 May 2023 zhenye234/CoMoSpeech/hifi-gan/models.py e453b51f0ed5fb28 ran MIT (permissive)
MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition 9 Mar 2023 rongjiehuang/transpeech/research/TranSpeech/hifigan/models.py e453b51f0ed5fb28 ran MIT (permissive)
StyleTTS-VC: One-Shot Voice Conversion by Knowledge Transfer from Style-Based TTS Models 29 Dec 2022 yl4579/StyleTTS-VC/Demo/hifi-gan/vocoder.py e453b51f0ed5fb28 ran MIT (permissive)
Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units 19 Dec 2022 gallilmaimon/DISSC/sr/models.py e453b51f0ed5fb28 ran MIT (permissive)
BigVGAN: A Universal Neural Vocoder with Large-Scale Training 9 Jun 2022 sh-lee-prml/BigVGAN/losses.py 24e8b4731dc3e070 unverified MIT (permissive)
StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis 30 May 2022 yl4579/StyleTTS/Demo/hifi-gan/vocoder.py e453b51f0ed5fb28 ran MIT (permissive)
NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality 9 May 2022 daniilrobnikov/vits2/losses.py f9a2eedb621a3dda unverified MIT (permissive)
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement 24 Mar 2022 rishikksh20/HiFiplusplus-pytorch/models.py e453b51f0ed5fb28 ran MIT (permissive)
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform 4 Mar 2022 hcy71o/autovocoder/models.py e453b51f0ed5fb28 ran Apache-2.0 (permissive)
Learning the Beauty in Songs: Neural Singing Voice Beautifier 27 Feb 2022 MoonInTheRiver/DiffSinger/modules/hifigan/hifigan.py e453b51f0ed5fb28 ran MIT (permissive)
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme 28 Sep 2021 trinhtuanvubk/diff-vc/hifi-gan/models.py e453b51f0ed5fb28 ran MIT recorded; this copy not marked cleared · pointer only
UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation 15 Jun 2021 rishikksh20/UnivNet-pytorch/loss.py e453b51f0ed5fb28 ran MIT (permissive)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech 2021-06 (from id) maum-ai/phaseaug/models.py e453b51f0ed5fb28 ran BSD-3-Clause (permissive)
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech 2021-06 (from id) jaywalnut310/vits/losses.py 24e8b4731dc3e070 unverified MIT (permissive)
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech 8 Jun 2020 shivammehta25/BetterFastSpeech2/fs2/hifigan/models.py e453b51f0ed5fb28 ran 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