Home › Code › RMSNorm

RMSNorm

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

RMSNorm appears in the code Syntology harvested for 61 papers, as 63 distinct code bodies found in 63 places (a place is one code body under one paper). At least one of them ran in 59 of the papers; 8 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 RMSNorm 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 61 of the 63 distinct code bodies named RMSNorm; 2 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
0ran · fixture could not drive it
61ran
2unverified
8fingerprinted

Licence is a property of each copy, so it is counted per place: 18 of the 63 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

61 papers shown of 61, newest first; 63 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 29 papers added by Syntology; 1 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
Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks added by Syntology 2026-08 (from id) jingyingma01/CodeBrain/Models/SSSM.py eb1aca90c956ed92 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Stoicheia: Character-Level Masked Diffusion for Ancient Greek Textual Restoration, Parsing, and Metrical Scansion added by Syntology 2026-08 (from id) ericu9500/stoicheia/hf_release/modeling_char_bert_joint.py 2286a7c35ee41c87 ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive)
UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction added by Syntology 2026-08 (from id) JN-Yun/UDT/models/UDT.py 9a95d88a2519390e ran no licence file found · pointer only
From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models added by Syntology 2026-07 (from id) SeunggeunKimkr/genuine-any-order/LatentMDM/model/latent_mdm.py 3960fafde947a0b8 ran · metamorphic tier: invariant Apache-2.0 (permissive)
SechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions added by Syntology 2026-07 (from id) hoangthangta/All-KAN/models/sech_kan.py 1d4a7d068cf45d10 ran · metamorphic tier: deterministic MIT (permissive)
Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs added by Syntology 2026-06 (from id) YVVH/ORE/ORE/ORE_main.py 6347bf161968fa04 ran · metamorphic tier: invariant MIT (permissive)
SamatNext v0.2-B: An Exploratory Study of RMS-Normalized Hybrid Decoders for Curriculum Retention in Small Code Models added by Syntology 2026-06 (from id) samat2003/samatnext-v0.1/models/samat_next/model.py 561893a8e22a4976 ran · metamorphic tier: invariant Apache-2.0 (permissive)
SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning added by Syntology 2026-06 (from id) 5GYYYYY/SPOTR/SPOTR.py 5640196b424b0268 ran · metamorphic tier: deterministic MIT (permissive)
The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders added by Syntology 2026-06 (from id) Tiny-Snow/GenRec/src/genrec/models/model_seqrec/sasrec_sprint.py 82a2d670a351cbcf ran GPL-3.0 (copyleft) · pointer only
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation added by Syntology 2026-06 (from id) thu-ml/RDT2/models/rdt/model.py e1daa20aa3ecf380 ran Apache-2.0 (permissive)
CART: Context-Anchored Recurrent Transformer * A Parameter-Efficient Architecture with Learned Stability added by Syntology 2026-06 (from id) ccapps42/CART/model/cart.py 5e72e01b3a174cc0 ran · metamorphic tier: invariant MIT (permissive)
SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference added by Syntology 2026-05 (from id) rgklab/SurvivalPFN/survivalpfn/models/icl_model.py 6e57086fc97463e2 ran · metamorphic tier: invariant Apache-2.0 (permissive)
Causal Foundation Models with Continuous Treatments added by Syntology 2026-05 (from id) layer6ai-labs/CCPFN-inference/src/ccpfn/models/continuous_icl_model.py 8ebbbd4e10f29278 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use added by Syntology 2026-05 (from id) vectrayx/vectrayx-nano-paper/training/transformer.py 05a42e70386b7c33 ran no licence file found · pointer only
TIDES: Implicit Time-Awareness in Selective State Space Models added by Syntology 2026-05 (from id) TaylanSoydan/TIDES/tides/tides.py ae412fb79bbc7983 ran · metamorphic tier: invariant MIT (permissive)
Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis added by Syntology 2026-04 (from id) simd-ai/shape/shape_foundation/models/gaot_backbone.py 7b2150d02885a569 ran · metamorphic tier: invariant Apache-2.0 (permissive)
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion added by Syntology 2026-04 (from id) mikumifa/GS-Quant/codebook/rqvae.py e90fe98be09c54bd ran · metamorphic tier: invariant Apache-2.0 (permissive)
Representation Alignment for Just Image Transformers is not Easier than You Think added by Syntology 2026-03 (from id) kaist-cvml/PixelREPA/model_pixelREPA.py 77d34b3ccaee6e17 ran MIT (permissive)
RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States added by Syntology 2026-03 (from id) XiangjieXiao/ReSched/PPO/SchedulingModel.py 9465fd5c593cbef5 ran · metamorphic tier: deterministic MIT (permissive)
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data added by Syntology 2026-02 (from id) adminasmi/OmniZip-CVPR2026/models/rwkv7_hira_moa_moe.py c1ff30fd8e32c15e ran fingerprinted no licence file found · pointer only
VariViT: A Vision Transformer for Variable Image Sizes added by Syntology 2026-02 (from id) Aswathi-Varma/varivit/model/navit.py 02d91e9f7f403be0 ran · metamorphic tier: deterministic no licence file found · pointer only
PixelGen: Improving Pixel Diffusion with Perceptual Supervision added by Syntology 2026-02 (from id) Zehong-Ma/PixelGen/src/models/transformer/JiT.py 84963760feac9e7d ran · metamorphic tier: invariant no licence file found · pointer only
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices added by Syntology 2026-01 (from id) wz1119/KromHC/hyper_conn/Kromhc.py 9570166c272034c8 ran · metamorphic tier: deterministic no licence file found · pointer only
Spectral-Window Hybrid (SWH) added by Syntology 2026-01 (from id) VladimerKhasia/SWH/swh.py 132d910895b3fe88 ran no licence file found · pointer only
Degradation-Aware Metric Prompting for Hyperspectral Image Restoration added by Syntology 2025-12 (from id) MiliLab/DAMP/DAMP.py 6aba4598e0003aae ran · metamorphic tier: deterministic no licence file found · pointer only
Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials added by Syntology 2025-11 (from id) LeapLabTHU/LinearDiff/image_classification/models/vca_deit.py af5816548ff50622 ran · metamorphic tier: invariant no licence file found · pointer only
SEMPO: Lightweight Foundation Models for Time Series Forecasting added by Syntology 2025-10 (from id) mala-lab/SEMPO/models/SEMPO.py 0a5b83bc7ce0cd66 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers added by Syntology 2025-10 (from id) wjc2830/Siren/src/siren/model.py 9669b074ff77501a ran · metamorphic tier: deterministic no licence file found · pointer only
Toward Embodiment Equivariant Vision-Language-Action Policy added by Syntology 2025-09 (from id) hhcaz/e2vla/models/action_expert.py ea08af0febc2e0f0 ran · metamorphic tier: invariant MIT (permissive)
arXiv:2507.06363 2025-07 (from id) gmum/MambaHoME/src/models/soft_moe_2d_3d.py 5e5be82456aab234 ran · metamorphic tier: deterministic MIT (permissive)
Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture 24 Jun 2025 scxue/AO-GPT-MDM/model_AOGPT_AdaLN6_NoRep_cond_128_trunc_qknorm.py 7d84ead0fe5b239f ran fingerprinted no licence file found · pointer only
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play 5 May 2025 maitrix-org/Voila/model.py 25e14d2b6e56efe1 ran MIT (permissive)
PixelFlow: Pixel-Space Generative Models with Flow 10 Apr 2025 shoufachen/pixelflow/pixelflow/model.py a5e686c656d9d355 ran MIT (permissive)
KV-Edit: Training-Free Image Editing for Precise Background Preservation 24 Feb 2025 Xilluill/KV-Edit/models/kv_edit.py b4affeaaac4bcdd4 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting 11 Feb 2025 ljc-fvnr/structural-aligned-mixture-of-var/models/AutoregressiveAlignment.py 45502bf8690c09af ran · metamorphic tier: invariant MIT (permissive)
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features 6 Feb 2025 helblazer811/ConceptAttention/concept_attention/flux/dit_block.py 5c52ab157dc1c15c ran · metamorphic tier: deterministic no licence file found · pointer only
LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer 3 Feb 2025 showlab/LayerTracer/library/flux_models.py 4de3b3072dadcd2f ran · metamorphic tier: deterministic MIT (permissive)
Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space 26 Jan 2025 hexin5515/MbaGCN/NodeClassification/models.py f79868a941682af4 ran · metamorphic tier: deterministic no licence file found · pointer only
HunyuanVideo: A Systematic Framework For Large Video Generative Models 3 Dec 2024 tencent/hunyuanvideo/hyvideo/modules/models.py 9fa452fc273f7d2a ran licence not identified · pointer only
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification 14 Oct 2024 hustvl/LightningDiT/models/lightningdit.py 3777a235d6ea1491 ran MIT (permissive)
Differential Transformer 7 Oct 2024 hammoudhasan/diffclip/diff_attention.py 84b5e228ae8799e1 ran · metamorphic tier: invariant no licence file found · pointer only
ControlAR: Controllable Image Generation with Autoregressive Models 3 Oct 2024 hustvl/controlar/autoregressive/models/gpt.py edd6b8543cc0d1ab ran Apache-2.0 (permissive)
Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation 2024-09 (from id) OpenDriveLab/CLOVER/FeedbackPolicy/models/policy.py 008a90cb086e88c6 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection 23 Jul 2024 VisualAIKHU/MonoWAD/visualDet3D/networks/detectors/MonoWAD.py 234fd6dd12768c7d ran · metamorphic tier: invariant MIT (permissive)
Learning Trimodal Relation for AVQA with Missing Modality 23 Jul 2024 VisualAIKHU/Missing-AVQA/net_grd_avst/net_avst.py 30e7fae83920ab01 ran · metamorphic tier: deterministic fingerprinted MIT (permissive)
Simplified and Generalized Masked Diffusion for Discrete Data 6 Jun 2024 google-deepmind/md4/md4/models/diffusion/md4.py a75e172eea6d85f1 unverified Apache-2.0 (permissive)
Disentangling and Integrating Relational and Sensory Information in Transformer Architectures 26 May 2024 awni00/abstract_transformer/dual_attention_transformer.py 01777e072296c0bb ran · metamorphic tier: deterministic MIT (permissive)
TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment 22 May 2024 dhg-wei/topa/llama/model.py df852b6b3526e46e ran · metamorphic tier: deterministic MIT (permissive)
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases 22 Feb 2024 jingyaogong/minimind/model/model_minimind.py a8a84e7ddb0551b0 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Learning Structure-Aware Representations of Dependent Types 3 Feb 2024 konstantinoskokos/quill/src/quill/nn/model.py 8183f36aee184817 ran no licence file found · pointer only
Mamba: Linear-Time Sequence Modeling with Selective State Spaces 1 Dec 2023 human9000/nd-mamba2-torch/torchnssd/nd_mamba2.py ba026d72b685bee1 ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only
From Sparse to Soft Mixtures of Experts 2 Aug 2023 lucidrains/soft-moe-pytorch/soft_moe_pytorch/soft_moe.py 024a5f1d96cb0afb ran MIT (permissive)
Llama 2: Open Foundation and Fine-Tuned Chat Models 18 Jul 2023 Lightning-AI/lit-gpt/litgpt/model.py 1e7100681c300ca2 ran fingerprinted Apache-2.0 (permissive)
LLaMA: Open and Efficient Foundation Language Models 27 Feb 2023 akanyaani/miniLLAMA/model.py 0ea811a4ad9027b8 ran · metamorphic tier: invariant MIT (permissive)
LLaMA: Open and Efficient Foundation Language Models 27 Feb 2023 young-geng/easylm/EasyLM/models/llama/llama_model.py aaa8a447973c0f68 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
LLaMA: Open and Efficient Foundation Language Models 27 Feb 2023 Lightning-AI/lit-llama/lit_llama/model.py 133fab2290f71687 ran fingerprinted Apache-2.0 (permissive)
Training Compute-Optimal Large Language Models 29 Mar 2022 karpathy/llama2.c/model.py e27b34a3f741d4de ran · metamorphic tier: deterministic MIT (permissive)
MaskGIT: Masked Generative Image Transformer 8 Feb 2022 valeoai/maskgit-pytorch/Network/transformer.py 86a159a05ae09375 ran MIT (permissive)
Improving language models by retrieving from trillions of tokens 8 Dec 2021 lucidrains/RETRO-pytorch/retro_pytorch/retro_pytorch.py a4ae5f96225b96f3 ran · metamorphic tier: deterministic Apache-2.0 (permissive)
Sparse Attention with Linear Units 14 Apr 2021 rishikksh20/rectified-linear-attention/attention.py cc210ef49adb120a ran · metamorphic tier: deterministic MIT (permissive)
Denoising Diffusion Probabilistic Models 19 Jun 2020 lucidrains/make-a-video-pytorch/make_a_video_pytorch/make_a_video.py 7b794fd52131431f ran · metamorphic tier: deterministic MIT (permissive)
Root Mean Square Layer Normalization 16 Oct 2019 hazdzz/RMSNorm/norm.py 9c235f0c904962f7 ran fingerprinted MIT (permissive)
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism 17 Sep 2019 kingoflolz/mesh-transformer-jax/mesh_transformer/transformer_shard.py ae952da8d1f3ecfc 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