Home › Code › load_balancing_loss_func

load_balancing_loss_func

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

load_balancing_loss_func appears in the code Syntology harvested for 24 papers, as 17 distinct code bodies found in 27 places (a place is one code body under one paper). At least one of them ran in 10 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 load_balancing_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 9 of the 17 distinct code bodies named load_balancing_loss_func; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

1ran · honoured contract
2ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
6ran
8unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 14 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

24 papers shown of 24, 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 6 papers added by Syntology; 3 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
TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval added by Syntology 2026-09 (from id) sejong-rcv/TAME/modules/MoE_utils.py 3e863ec151094058 unverified no licence file found · pointer only
TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval added by Syntology 2026-09 (from id) sejong-rcv/TAME/modules/until_module.py 9b9174b87f63cc4c unverified no licence file found · pointer only
Eigenvectors of Experts are Training-free Non-collapsing Routers added by Syntology 2026-05 (from id) giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_olmoe.py d0725ff0666ee959 ran · violated contract no licence file found · pointer only
Eigenvectors of Experts are Training-free Non-collapsing Routers added by Syntology 2026-05 (from id) giangdip2410/SSMoE/SSMoE/Language/SSMoE-Embedding/models/modeling_gritlm8x7b.py e566aca3f6f9392e ran no licence file found · pointer only
Eigenvectors of Experts are Training-free Non-collapsing Routers added by Syntology 2026-05 (from id) giangdip2410/SSMoE/SSMoE/Vision/CLIP-SSMoE/clipmoe/model_clipmoe.py 25b8549e7bd56c7d ran no licence file found · pointer only
MoE-Spec: Expert Budgeting for Efficient Speculative Decoding added by Syntology 2026-02 (from id) SafeAILab/EAGLE/eagle/model/modeling_mixtral_kv.py d9308d9bf18cd072 unverified no licence file found · pointer only
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference added by Syntology 2026-01 (from id) fvliang/DART/dart/model/modeling_mixtral_kv.py d9308d9bf18cd072 unverified Apache-2.0 (permissive)
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification added by Syntology 2026-01 (from id) 5SSjw/MARS/mars/model/modeling_mixtral_kv.py d9308d9bf18cd072 unverified MIT (permissive)
ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding added by Syntology 2025-09 (from id) KangJialiang/ViSpec/vispec/model/modeling_mixtral_kv.py d9308d9bf18cd072 unverified Apache-2.0 (permissive)
arXiv:2507.22424 2025-07 (from id) PineTreeWss/SpecVLA/openvla/specdecoding/model/modeling_mixtral_kv.py d9308d9bf18cd072 unverified MIT (permissive)
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention 16 Jun 2025 minimax-ai/minimax-m1/modeling_minimax_m1.py 2d7fb5c16b69ee87 unverified Apache-2.0 (permissive)
JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model 22 May 2025 Qihao-Duan/JanusDNA/janusdna/modeling_janusdna.py afa4dd8b92112788 unverified Apache-2.0 (permissive)
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration 10 Mar 2025 idea-isail-lab-uiuc/resmoe/mixtral/resmoe_mixtral/modeling_mixtral.py e566aca3f6f9392e ran MIT (permissive)
Demystifying Domain-adaptive Post-training for Financial LLMs 9 Jan 2025 salesforceairesearch/findap/FinDAP/utils/packing/monkey_patch_packing.py ecadd5acaff4db07 unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free 14 Oct 2024 tianyi-lab/moe-embedding/models/modeling_olmoe.py d0725ff0666ee959 ran · violated contract no licence file found · pointer only
Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts 24 Sep 2024 Time-MoE/Time-MoE/time_moe/models/modeling_time_moe.py e0d3c24aaf39d620 ran · honoured contract Apache-2.0 (permissive)
Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding 1 Aug 2024 XiaoBin1992/clover/clover/model/modeling_mixtral_kv.py d9308d9bf18cd072 unverified Apache-2.0 (permissive)
Mixture of In-Context Experts Enhance LLMs' Long Context Awareness 28 Jun 2024 p1nksnow/moice/modeling/modeling_llama.py 114e672ea51890e7 ran · violated contract no licence file found · pointer only
AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models 19 Jun 2024 cengzihao/adamoe/exp_1/src/mola_modeling_llama_hacked.py e9ff56fcac52d4ac ran no licence file found · pointer only
Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space 22 May 2024 cognizant-ai-labs/semantic-density-paper/huggingface_replacement/modeling_mixtral.py d9308d9bf18cd072 unverified no licence file found · pointer only
Retrieval Head Mechanistically Explains Long-Context Factuality 24 Apr 2024 nightdessert/retrieval_head/faiss_attn/source/modeling_mixtral.py 71b1358cf9d3dbda ran no licence file found · pointer only
Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs 19 Feb 2024 arcee-ai/distillkit/distillkit/monkey_patch_packing.py e4ac3e44dca69ef9 unverified Apache-2.0 (permissive)
Higher Layers Need More LoRA Experts 13 Feb 2024 gcyzsl/mola/src/mola_modeling_llama_hacked.py 94e2e2c1c3336f07 ran no licence file found · pointer only
CLEX: Continuous Length Extrapolation for Large Language Models 25 Oct 2023 DAMO-NLP-SG/CLEX/CLEX/mixtral/modeling_mixtral_clex.py 74f2d25c8432bf82 ran MIT (permissive)
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection 17 Oct 2023 ShayekhBinIslam/openrag/openrag/modeling_openrag.py d9308d9bf18cd072 unverified CC-BY-4.0 · pointer only
arXiv:openreview_4iupzej9nT hikvision-research/STEP/step/model/olmoe/modeling_olmoe.py 84f6b3be4b370b1a unverified Apache-2.0 (permissive)
arXiv:2025.emnlp-main.231 chenziwenhaoshuai/TS-CLIP/time_moe/models/modeling_time_moe.py e0d3c24aaf39d620 ran · honoured contract 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