{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/moe","entry":"MoE","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":10,"n_papers_ran":2,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":10,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":10,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":8},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2604.18256","paper":"/paper/arxiv-2604-18256","title":"Domain-Specialized Object Detection via Model-Level Mixtures of Experts","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"KASTEL-MobilityLab/mixtures-of-experts","path":"models/deeplab_moe.py","file_url":"https://github.com/KASTEL-MobilityLab/mixtures-of-experts/blob/HEAD/models/deeplab_moe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT-0","inline_ok":true,"code_sha256_prefix":"673afb68f4ec8289","mcp_get_code":{"code_sha256":"673afb68f4ec8289"}},{"arxiv_id":"2603.29765","paper":"/paper/arxiv-2603-29765","title":"Training-Free Dynamic Upcycling of Expert Language Models","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"gensyn-ai/dume","path":"models/mixture_of_experts.py","file_url":"https://github.com/gensyn-ai/dume/blob/HEAD/models/mixture_of_experts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4de3c66084ad46a","mcp_get_code":{"code_sha256":"f4de3c66084ad46a"}},{"arxiv_id":"2602.22286","paper":"/paper/arxiv-2602-22286","title":"OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"adminasmi/OmniZip-CVPR2026","path":"models/rwkv7_hira_moa_moe.py","file_url":"https://github.com/adminasmi/OmniZip-CVPR2026/blob/HEAD/models/rwkv7_hira_moa_moe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5e190de60aac899d","mcp_get_code":{"code_sha256":"5e190de60aac899d"}},{"arxiv_id":"2412.20413","paper":"/paper/eraseanything-enabling-concept-erasure-in","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","date":"2024-12-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tomguluson92/eraseanything","path":"ir_concept.py","file_url":"https://github.com/tomguluson92/eraseanything/blob/HEAD/ir_concept.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"2f410d45aa8c1315","mcp_get_code":{"code_sha256":"2f410d45aa8c1315"}},{"arxiv_id":"2405.01029","paper":"/paper/mvmoe-multi-task-vehicle-routing-solver-with","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","date":"2024-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"royalskye/routing-mvmoe","path":"models/MOELayer.py","file_url":"https://github.com/royalskye/routing-mvmoe/blob/HEAD/models/MOELayer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e3b2870d5860fe6","mcp_get_code":{"code_sha256":"6e3b2870d5860fe6"}},{"arxiv_id":"2402.12656","paper":"/paper/hypermoe-towards-better-mixture-of-experts","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Bumble666/Hyper_MoE","path":"gpt-2-moe/transformers/models/layers.py","file_url":"https://github.com/Bumble666/Hyper_MoE/blob/HEAD/gpt-2-moe/transformers/models/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"89f7e4ccbdd62673","mcp_get_code":{"code_sha256":"89f7e4ccbdd62673"}},{"arxiv_id":"2401.04088","paper":"/paper/mixtral-of-experts","title":"Mixtral of Experts","date":"2024-01-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamanphoebe/look-into-moes","path":"mixtral_instruct/modeling_mixtral_instruct.py","file_url":"https://github.com/kamanphoebe/look-into-moes/blob/HEAD/mixtral_instruct/modeling_mixtral_instruct.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"253c6ed84c1f2c72","mcp_get_code":{"code_sha256":"253c6ed84c1f2c72"}},{"arxiv_id":"2203.06569","paper":"/paper/summareranker-a-multi-task-mixture-of-experts-1","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","date":"2022-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ntunlp/summareranker","path":"src/summareranker/model_moe.py","file_url":"https://github.com/ntunlp/summareranker/blob/HEAD/src/summareranker/model_moe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"82537626815bab7d","mcp_get_code":{"code_sha256":"82537626815bab7d"}},{"arxiv_id":"2006.16668","paper":"/paper/gshard-scaling-giant-models-with-conditional","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","date":"2020-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lucidrains/mixture-of-experts","path":"mixture_of_experts/mixture_of_experts.py","file_url":"https://github.com/lucidrains/mixture-of-experts/blob/HEAD/mixture_of_experts/mixture_of_experts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"928216f4fee84bf9","mcp_get_code":{"code_sha256":"928216f4fee84bf9"}},{"arxiv_id":"1701.06538","paper":"/paper/outrageously-large-neural-networks-the","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","date":"2017-01-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"davidmrau/mixture-of-experts","path":"moe.py","file_url":"https://github.com/davidmrau/mixture-of-experts/blob/HEAD/moe.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"c31aa0d1c4d7c7dc","mcp_get_code":{"code_sha256":"c31aa0d1c4d7c7dc"}}]}