Home › Code › unwrap_model

unwrap_model

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

unwrap_model appears in the code Syntology harvested for 41 papers, as 26 distinct code bodies found in 41 places (a place is one code body under one paper). At least one of them ran in 12 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 unwrap_model 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 26 distinct code bodies named unwrap_model; 18 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
3ran · violated contract
2ran · our draft was wrong
0ran · fixture could not drive it
3ran
18unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 12 of the 41 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

41 papers shown of 41, newest first; 41 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 11 papers added by Syntology; 5 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
The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMs added by Syntology 2026-09 (from id) ANDgate99/VT-Contrast/utils/model_utils.py 6b24fbf0b77326ea unverified no licence file found · pointer only
StreamHear: Domain-Adapted Pseudo-Labeling for Semi-Supervised Streaming Speech Recognition added by Syntology 2026-08 (from id) NVIDIA-NeMo/Speech/nemo/utils/model_utils.py d0b9c431aaf4be9f ran Apache-2.0 (permissive)
Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoning added by Syntology 2026-07 (from id) aixiuxiuxiu/Legal-MT-SFT-RL/model/utils.py 0c3ff94987c68b53 unverified MIT (permissive)
Rate-Utility Frontiers for Language Encodings: Comparing Tokens, Bytes, and Pixels Under Controlled Linguistic Content added by Syntology 2026-07 (from id) ziegler-ingo/rate-utility-frontiers/ruf/utils.py d353aa5026e7865e ran Apache-2.0 (permissive)
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI added by Syntology 2026-07 (from id) ntuliuteam/edge-compress/core/dynamic.py 7165fcf78de9cfb2 unverified licence not identified · pointer only
Automatic Labelling of Speech Translation Errors added by Syntology 2026-06 (from id) NVIDIA-NeMo/NeMo/nemo/utils/model_utils.py d0b9c431aaf4be9f ran Apache-2.0 (permissive)
Spectral Collapse in Diffusion Inversion added by Syntology 2026-02 (from id) nicoboou/ovg/utils/helpers.py 4367fc8188e7115f unverified no licence file found · pointer only
Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text added by Syntology 2026-02 (from id) NVIDIA/NeMo/nemo/utils/model_utils.py d0b9c431aaf4be9f ran Apache-2.0 (permissive)
LiFlow: Flow Matching for 3D LiDAR Scene Completion added by Syntology 2026-02 (from id) matteandre/LiFlow/liflow/models/ema_callback.py 9603dea3759c2ec7 unverified MIT (permissive)
Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers added by Syntology 2026-01 (from id) tianyima2000/ICL_LocPol/ICL_locpol.py 35ea6edb8b5b4542 unverified no licence file found · pointer only
Self-Supervised Dynamical System Representations for Physiological Time-Series added by Syntology 2025-12 (from id) yuqinie98/PatchTST/PatchTST_self_supervised/src/utils.py 3cc94cf719642c1f unverified Apache-2.0 (permissive)
Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix 14 Jul 2025 FLEECERmw/PrivacyFedLLM/policy/policy_scaffold.py fd9a34654ce589b0 unverified Apache-2.0 (permissive)
Robustness in Both Domains: CLIP Needs a Robust Text Encoder 3 Jun 2025 LIONS-EPFL/LEAF/src/robust_vlm/train/adversarial_training_clip.py a72cc58ae0995b23 unverified no licence file found · pointer only
LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations 11 Dec 2024 mengcye/LAION-SG/sgEncoderTraining/training/train_and_val_one_iter.py 2bf62c0287050bdd unverified MIT (permissive)
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation 2 Sep 2024 nusnlp/Self-J/kd.py 551e41129f773314 ran no licence file found · pointer only
FLAME: Learning to Navigate with Multimodal LLM in Urban Environments 20 Aug 2024 xyz9911/FLAME/llm_nav/trainer.py 54b2d55aa476a3bc unverified Apache-2.0 (permissive)
xLSTMTime : Long-term Time Series Forecasting With xLSTM 14 Jul 2024 muslehal/xLSTMTime/src/utils.py 3cc94cf719642c1f unverified MIT (permissive)
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs 14 Jun 2024 yangrui2015/generalizable-reward-model/rlhf/ppo/model_utils.py 54b2d55aa476a3bc unverified MIT (permissive)
Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutes 9 May 2024 ModelTC/FCPTS/utils.py 8ba24560996e7d76 ran · violated contract no licence file found · pointer only
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction 25 Mar 2024 citymind-lab/urbanvlp/models/utils.py 2bf62c0287050bdd unverified no licence file found · pointer only
LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error 7 Mar 2024 microsoft/simulated-trial-and-error/llama-recipes/model_checkpointing/checkpoint_handler.py b530360e413bc3fd unverified MIT (permissive)
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models 19 Feb 2024 chs20/robustvlm/train/adversarial_training_clip.py 04cf221e803c96d7 unverified MIT (permissive)
SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models 11 Dec 2023 TencentARC/SmartEdit/train/DS_SmartEdit_train.py 53f81df53706a39a ran · violated contract no licence file found · pointer only
PG-Video-LLaVA: Pixel Grounding Large Video-Language Models 22 Nov 2023 mbzuai-oryx/video-llava/video_chatgpt/train/llava_trainer.py 54b2d55aa476a3bc unverified no licence file found · pointer only
HexGen: Generative Inference of Large Language Model over Heterogeneous Environment 2023-11 (from id) relaxed-system-lab/hexgen/hexgen/hexgen_core/heterogeneous_pipeline.py 85b5684d7d73dde9 ran · our draft was wrong Apache-2.0 (permissive)
A path-norm toolkit for modern networks: consequences, promises and challenges 2 Oct 2023 agonon/pathnorm_toolkit/repro/icml25/utils/pathnorm_transform.py 25a99cb17f71ec59 unverified BSD-3-Clause (permissive)
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks 29 Sep 2023 Hhhhhhao/Noisy-Model-Learning/timm/utils/model.py 7a86fad403e4e95e unverified no licence file found · pointer only
AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining 10 Aug 2023 haoheliu/audioldm-training-finetuning/audioldm_train/modules/clap/training/lp_train.py 2bf62c0287050bdd unverified MIT (permissive)
PreNAS: Preferred One-Shot Learning Towards Efficient Neural Architecture Search 2023-04 (from id) tinyvision/PreNAS/lib/score_maker.py 2bf62c0287050bdd unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Deep Incubation: Training Large Models by Divide-and-Conquering 8 Dec 2022 leaplabthu/model-assembling/timm/utils/model.py 7a86fad403e4e95e unverified MIT (permissive)
OntoProtein: Protein Pretraining With Gene Ontology Embedding 23 Jan 2022 zjunlp/OntoProtein/src/models.py d0f318a102295076 ran · violated contract MIT (permissive)
State-Aware Tracker for Real-Time Video Object Segmentation 1 Mar 2020 MegviiDetection/video_analyst/videoanalyst/utils/torch_module.py 99a642ee770823da unverified MIT (permissive)
Towards Robust and Reproducible Active Learning Using Neural Networks 21 Feb 2020 acl21/deep-active-learning-pytorch/pycls/core/net.py 8ba24560996e7d76 ran · violated contract MIT (permissive)
On Network Design Spaces for Visual Recognition 30 May 2019 tuggeluk/pycls/pycls/core/net.py 8ba24560996e7d76 ran · violated contract MIT (permissive)
ParticleNet: Jet Tagging via Particle Clouds 22 Feb 2019 hqucms/weaver-core/weaver/utils/nn/tools.py 464cf959f947b7c4 unverified MIT (permissive)
Pruning Filters for Efficient ConvNets 31 Aug 2016 siyuan0/pytorch_model_prune/prune.py f21b8549dee8b153 ran · our draft was wrong MIT (permissive)
arXiv:Zhang_Spiking_Transformers_for_Event-Based_Single_Object_Tracking_CVPR_2022_paper Jee-King/CVPR2022_STNet/videoanalyst/utils/torch_module.py 99a642ee770823da unverified MIT (permissive)
arXiv:Yang_Attentive_Mask_CLIP_ICCV_2023_paper microsoft/A-CLIP/utils.py 2bf62c0287050bdd unverified MIT (permissive)
arXiv:Tang_Progressive_Attention_on_Multi-Level_Dense_Difference_Maps_for_Generic_Event_CVPR_2022_paper MCG-NJU/DDM/DDM-Net/utils/checkpoint_saver.py 7a86fad403e4e95e unverified MIT (permissive)
arXiv:2025.naacl-long.298 pyf98/NeMo_VoiceTextBlender/nemo/utils/model_utils.py aaa3faafc96337d0 unverified Apache-2.0 (permissive)
arXiv:2025.emnlp-main.19 zechenli03/SensorLLM/sensorllm/train/sensorllm_trainer.py 54b2d55aa476a3bc 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