Home › Code › reduce_loss

reduce_loss

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

reduce_loss appears in the code Syntology harvested for 75 papers, as 12 distinct code bodies found in 75 places (a place is one code body under one paper). At least one of them ran in 21 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 reduce_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 12 distinct code bodies named reduce_loss; 7 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
2ran · fixture could not drive it
3ran
7unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 22 of the 75 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

75 papers shown of 75, newest first; 75 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 5 papers added by Syntology; 13 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
P-PatchDiff: Progressive Patch Diffusion Models for Low-light Image Enhancement added by Syntology 2026-09 (from id) RuoyuGuo/P-PatchDiff/BasicSR-light/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Scalar-pathway fidelity improves physical accuracy in short-range equivariant interatomic potentials added by Syntology 2026-06 (from id) JIABI/mace/mace/modules/loss.py 899373c6ab1c87f0 ran licence not identified · pointer only
Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution added by Syntology 2026-02 (from id) Blazedengcy/GTASR/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions added by Syntology 2025-10 (from id) Zhuo-Cao/QV-M2/blocks/loss.py 129fb213ab1543f6 unverified no licence file found · pointer only
Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement added by Syntology 2025-10 (from id) lyd-2022/Latent-Harmony/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery 23 May 2025 hainuo-wang/modem/basicsr/models/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
Progressive Focused Transformer for Single Image Super-Resolution 26 Mar 2025 labshuhanggu/pft-sr/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Visual Autoregressive Modeling for Image Super-Resolution 31 Jan 2025 qyp2000/varsr/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
The dark side of the forces: assessing non-conservative force models for atomistic machine learning 16 Dec 2024 ACEsuit/mace/mace/modules/loss.py 899373c6ab1c87f0 ran no licence file found · pointer only
Auto-Encoded Supervision for Perceptual Image Super-Resolution 28 Nov 2024 2minkyulee/aesop-auto-encoded-supervision-for-perceptual-image-super-resolution/AESOP/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
MAT: Multi-Range Attention Transformer for Efficient Image Super-Resolution 26 Nov 2024 stella-von/MAT/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency 25 Nov 2024 dixin-lab/bfvr-stc/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving 22 Nov 2024 hustvl/diffusiondrive/navsim/agents/diffusiondrive/modules/multimodal_loss.py 3471a2eecf2c0005 unverified MIT (permissive)
M3TR: A Generalist Model for Real-World HD Map Completion 15 Nov 2024 immel-f/m3tr/projects/mmdet3d_plugin/m3tr/losses/map_loss.py b2b9a1966482ef96 ran · fixture could not drive it MIT (permissive)
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation 29 Oct 2024 XiaRho/MADM/modeling/criterion.py b2b9a1966482ef96 ran · fixture could not drive it no licence file found · pointer only
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction 28 Oct 2024 LowlevelAI/ECMamba/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation 24 Oct 2024 shallowdream204/dreamclear/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation 10 Oct 2024 fudan-generative-vision/hallo2/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model 24 Aug 2024 chen-rao/vd-diff/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal 21 Aug 2024 QMoQ/OAPT/oapt/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks 18 Jul 2024 SehwanChoi0307/Mask2Map/projects/mmdet3d_plugin/mask2map/losses/map_loss.py b2b9a1966482ef96 ran · fixture could not drive it Apache-2.0 (permissive)
EvTexture: Event-driven Texture Enhancement for Video Super-Resolution 19 Jun 2024 DachunKai/EvTexture/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Blur-aware Spatio-temporal Sparse Transformer for Video Deblurring 11 Jun 2024 huicongzhang/bsstnet/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Correlation Matching Transformation Transformers for UHD Image Restoration 2 Jun 2024 supersupercong/uhdformer/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model 16 May 2024 yongsongh/irsrmamba/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Learning A Spiking Neural Network for Efficient Image Deraining 10 May 2024 MingTian99/ESDNet/losses.py 2387e49d92c846d7 ran no licence file found · pointer only
Training Transformer Models by Wavelet Losses Improves Quantitative and Visual Performance in Single Image Super-Resolution 17 Apr 2024 mandalinadagi/wavelettention/wavelettention/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction 1 Apr 2024 xiaolul2/MGMap/projects/mmdet3d_plugin/mgmap/losses/map_loss.py b2b9a1966482ef96 ran · fixture could not drive it MIT (permissive)
Ship in Sight: Diffusion Models for Ship-Image Super Resolution 27 Mar 2024 luigisigillo/shipinsight/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
D3T: Distinctive Dual-Domain Teacher Zigzagging Across RGB-Thermal Gap for Domain-Adaptive Object Detection 14 Mar 2024 EdwardDo69/D3T/experiment/flir_rgb2thermal/losses.py b2b9a1966482ef96 ran · fixture could not drive it Apache-2.0 (permissive)
Activating Wider Areas in Image Super-Resolution 13 Mar 2024 arsenalcheng/mma/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Efficient Image Deblurring Networks based on Diffusion Models 11 Jan 2024 bnm6900030/swintormer/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy 7 Jan 2024 xiangtaokong/mioir/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Tokenize Anything via Prompting 14 Dec 2023 baaivision/tokenize-anything/tokenize_anything/layers/loss.py 8288e056db5f29b3 ran Apache-2.0 (permissive)
Iterative Token Evaluation and Refinement for Real-World Super-Resolution 9 Dec 2023 chaofengc/iter/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Online Vectorized HD Map Construction using Geometry 6 Dec 2023 cnzzx/gemap/projects/mmdet3d_plugin/gemap/losses/map_loss.py b2b9a1966482ef96 ran · fixture could not drive it Apache-2.0 (permissive)
Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration 28 Nov 2023 zhihefang/wf-diff/basicsr/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Mind the map! Accounting for existing map information when estimating online HDMaps from sensor 17 Nov 2023 hustvl/maptr/projects/mmdet3d_plugin/maptr/losses/map_loss.py b2b9a1966482ef96 ran · fixture could not drive it MIT (permissive)
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources 6 Nov 2023 tmlr-group/atol/utils/losses.py 9f7b947fbfdaa657 ran · fixture could not drive it no licence file found · pointer only
ScalableMap: Scalable Map Learning for Online Long-Range Vectorized HD Map Construction 20 Oct 2023 jingy1yu/scalablemap/projects/mmdet3d_plugin/ScalableMap/losses/map_loss.py b2b9a1966482ef96 ran · fixture could not drive it no licence file found · pointer only
SurgicalSAM: Efficient Class Promptable Surgical Instrument Segmentation 17 Aug 2023 wenxi-yue/surgicalsam/surgicalSAM/loss.py b2b9a1966482ef96 ran · fixture could not drive it MIT (permissive)
Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model 7 Aug 2023 srameo/led/led/losses/loss_util.py a648a03a952822c0 unverified no licence file found · pointer only
Dual Aggregation Transformer for Image Super-Resolution 7 Aug 2023 zhengchen1999/dat/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Exploiting Diffusion Prior for Real-World Image Super-Resolution 11 May 2023 naagar/art_restoration_dm/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
LMPT: Prompt Tuning with Class-Specific Embedding Loss for Long-tailed Multi-Label Visual Recognition 8 May 2023 richard-peng-xia/LMPT/lmpt/bl.py 93358ba7aa223343 unverified Apache-2.0 (permissive)
Human Guided Ground-truth Generation for Realistic Image Super-resolution 23 Mar 2023 ChrisDud0257/HGGT/ImageEnhancement/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Recursive Generalization Transformer for Image Super-Resolution 11 Mar 2023 zhengchen1999/RGT/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution 9 Mar 2023 wdmwhh/MRefSR/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders 22 Dec 2022 piddnad/ddcolor/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
MovieCLIP: Visual Scene Recognition in Movies 20 Oct 2022 usc-sail/mica-MovieCLIP/losses/loss_functions.py 9f7b947fbfdaa657 ran · fixture could not drive it MIT (permissive)
Grounded Affordance from Exocentric View 28 Aug 2022 lhc1224/cross-view-affordance-grounding/code/extension/utils/loss.py 9f7b947fbfdaa657 ran · fixture could not drive it MIT (permissive)
Exploring evolution-aware & -free protein language models as protein function predictors 14 Jun 2022 elttaes/revisiting-plms/ESM-1b_Pretrain/DDP_train_1b.py 7bbb1a6e077ff43b unverified MIT (permissive)
Recurrent Video Restoration Transformer with Guided Deformable Attention 5 Jun 2022 labshuhanggu/mia-vsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
Blueprint Separable Residual Network for Efficient Image Super-Resolution 12 May 2022 xiaom233/bsrn/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution 27 Mar 2022 csjliang/DASR/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection 21 Dec 2021 happinesslz/epnetv2/lib/net/seg_utils.py b2b9a1966482ef96 ran · fixture could not drive it MIT (permissive)
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection 9 Dec 2021 2gunsu/monocon-pytorch/losses/utils.py 19a94ffb350de071 unverified Apache-2.0 (permissive)
SOTR: Segmenting Objects with Transformers 15 Aug 2021 easton-cau/SOTR/adet/modeling/sotr/loss.py 93358ba7aa223343 unverified MIT (permissive)
YOLOX: Exceeding YOLO Series in 2021 18 Jul 2021 StephenStorm/YOLOX/yolox/models/VariFocalLoss.py 93358ba7aa223343 unverified Apache-2.0 (permissive)
CvT: Introducing Convolutions to Vision Transformers 29 Mar 2021 leoxiaobin/CvT/lib/core/loss.py 9f7b947fbfdaa657 ran · fixture could not drive it MIT recorded; this copy not marked cleared · pointer only
PanNuke Dataset Extension, Insights and Baselines 24 Mar 2020 kaiseem/pointnu-net/losses/generalise_focal_loss.py 93358ba7aa223343 unverified MIT (permissive)
SOLOv2: Dynamic and Fast Instance Segmentation 23 Mar 2020 OpenFirework/pytorch_solov2/modules/solov2.py b2b9a1966482ef96 ran · fixture could not drive it no licence file found · pointer only
arXiv:ijcai2024_0081 JPWang-CS/FreqFormer/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
arXiv:aaai_32582 Hankitle/PEIE/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
arXiv:aaai_28514 wenxi-yue/SurgicalSAM/surgicalSAM/loss.py b2b9a1966482ef96 ran · fixture could not drive it MIT (permissive)
arXiv:aaai_28354 W-JG/BPOSR/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
arXiv:aaai_28342 VUT-HFUT/EulerMormer/utils/utils.py a648a03a952822c0 unverified MIT (permissive)
arXiv:Zheng_Efficient_Video_Super-Resolution_for_Real-time_Rendering_with_Decoupled_G-buffer_Guidance_CVPR_2025_paper sunny2109/RDG/basicsr/losses/loss_util.py a648a03a952822c0 unverified Apache-2.0 (permissive)
arXiv:Pan_Deep_Discriminative_Spatial_and_Temporal_Network_for_Efficient_Video_Deblurring_CVPR_2023_paper xuboming8/DSTNet/basicsr/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
arXiv:Liao_Multiple_View_Geometry_Transformers_for_3D_Human_Pose_Estimation_CVPR_2024_paper XunshanMan/MVGFormer/lib/core/loss.py 93358ba7aa223343 unverified Apache-2.0 (permissive)
arXiv:Kong_Efficient_Frequency_Domain-Based_Transformers_for_High-Quality_Image_Deblurring_CVPR_2023_paper kkkls/FFTformer/basicsr/models/losses/loss_util.py a648a03a952822c0 unverified MIT (permissive)
arXiv:Deng_Harmonious_Teacher_for_Cross-Domain_Object_Detection_CVPR_2023_paper kinredon/Harmonious-Teacher/ht_c2b/losses.py b2b9a1966482ef96 ran · fixture could not drive it Apache-2.0 (permissive)
arXiv:Chao_Equivalent_Transformation_and_Dual_Stream_Network_Construction_for_Mobile_Image_CVPR_2023_paper ECNUSR/ETDS/core/losses/loss_util.py 438e27f593f0b3c1 unverified Apache-2.0 (permissive)
arXiv:2023.findings-emnlp.517 jyansir/Text2Tree/balanced_loss_utils.py 93358ba7aa223343 unverified MIT (permissive)
arXiv:136790177 yuhuUSTC/FSDGN/basicsr/losses/loss_util.py a648a03a952822c0 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