{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/moe/papers/ran/1","list_of":"/method/moe","method":"MoE","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not isolate this method inside it.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,64],"of":64,"counts":{"archive_papers_tagged":366,"with_a_code_link":142,"where_syntology_ran_a_sample":64,"not_listed_spam_title":0,"listed":366,"listed_where_code_ran":64,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":49,"every_run_a_failure_of_syntologys_instrument":15,"listed_with_a_run_with_no_instrument_failure":49,"listed_every_run_a_failure_of_syntologys_instrument":15,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/moe/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/ming-omni-a-unified-multimodal-model-for","slug":"ming-omni-a-unified-multimodal-model-for","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","date":"2025-06-11","arxiv_id":"2506.09344","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":11,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["inclusionai/ming"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/flashdmoe-fast-distributed-moe-in-a-single","slug":"flashdmoe-fast-distributed-moe-in-a-single","title":"FlashDMoE: Fast Distributed MoE in a Single Kernel","date":"2025-06-05","arxiv_id":"2506.04667","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["osayamenja/aristos","osayamenja/kleos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/hidream-i1-a-high-efficient-image-generative","slug":"hidream-i1-a-high-efficient-image-generative","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","date":"2025-05-28","arxiv_id":"2505.22705","n_code_links":2,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hidream-ai/hidream-e1","hidream-ai/hidream-i1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/i2moe-interpretable-multimodal-interaction","slug":"i2moe-interpretable-multimodal-interaction","title":"I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts","date":"2025-05-25","arxiv_id":"2505.19190","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["raina-xin/i2moe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/janusdna-a-powerful-bi-directional-hybrid-dna","slug":"janusdna-a-powerful-bi-directional-hybrid-dna","title":"JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model","date":"2025-05-22","arxiv_id":"2505.17257","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["qihao-duan/janusdna"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/dense-backpropagation-improves-training-for","slug":"dense-backpropagation-improves-training-for","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","date":"2025-04-16","arxiv_id":"2504.12463","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vatsal0/default-moe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixture-of-lookup-experts","slug":"mixture-of-lookup-experts","title":"Mixture of Lookup Experts","date":"2025-03-20","arxiv_id":"2503.15798","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jieshibo/mole"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/resmoe-space-efficient-compression-of-mixture","slug":"resmoe-space-efficient-compression-of-mixture","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","date":"2025-03-10","arxiv_id":"2503.06881","n_code_links":1,"syntology":{"ran":10,"of":15,"n_ran_checked":7,"n_instrument":3,"unverified":5,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["idea-isail-lab-uiuc/resmoe"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-comprehensive-survey-of-mixture-of-experts","slug":"a-comprehensive-survey-of-mixture-of-experts","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","date":"2025-03-10","arxiv_id":"2503.07137","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["deepseek-ai/DeepEP"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/comet-fine-grained-computation-communication","slug":"comet-fine-grained-computation-communication","title":"Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts","date":"2025-02-27","arxiv_id":"2502.19811","n_code_links":4,"syntology":{"ran":9,"of":20,"n_ran_checked":9,"n_instrument":0,"unverified":11,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","official":{"repos":["bytedance/flux"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":11,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/drop-upcycling-training-sparse-mixture-of","slug":"drop-upcycling-training-sparse-mixture-of","title":"Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization","date":"2025-02-26","arxiv_id":"2502.19261","n_code_links":0,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/make-lora-great-again-boosting-lora-with","slug":"make-lora-great-again-boosting-lora-with","title":"Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment","date":"2025-02-24","arxiv_id":"2502.16894","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":3,"n_instrument":3,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["facico/goat-peft"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/delta-decompression-for-moe-based-llms","slug":"delta-decompression-for-moe-based-llms","title":"Delta Decompression for MoE-based LLMs Compression","date":"2025-02-24","arxiv_id":"2502.17298","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["lliai/d2moe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/the-empirical-impact-of-reducing-symmetries","slug":"the-empirical-impact-of-reducing-symmetries","title":"The Empirical Impact of Reducing Symmetries on the Performance of Deep Ensembles and MoE","date":"2025-02-24","arxiv_id":"2502.17391","n_code_links":0,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":7,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/training-sparse-mixture-of-experts-text","slug":"training-sparse-mixture-of-experts-text","title":"Training Sparse Mixture Of Experts Text Embedding Models","date":"2025-02-11","arxiv_id":"2502.07972","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":9,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nomic-ai/contrastors"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/hierarchical-time-aware-mixture-of-experts","slug":"hierarchical-time-aware-mixture-of-experts","title":"Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation","date":"2025-01-24","arxiv_id":"2501.14269","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["SStarCCat/HM4SR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/minimax-01-scaling-foundation-models-with","slug":"minimax-01-scaling-foundation-models-with","title":"MiniMax-01: Scaling Foundation Models with Lightning Attention","date":"2025-01-14","arxiv_id":"2501.08313","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/transforming-vision-transformer-towards","slug":"transforming-vision-transformer-towards","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","date":"2025-01-12","arxiv_id":"2501.06884","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"pointer_only":7,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yewen1486/emtal"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/remoe-fully-differentiable-mixture-of-experts","slug":"remoe-fully-differentiable-mixture-of-experts","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","date":"2024-12-19","arxiv_id":"2412.14711","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thu-ml/remoe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/towards-a-multimodal-large-language-model","slug":"towards-a-multimodal-large-language-model","title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine","date":"2024-12-12","arxiv_id":"2412.09278","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shawnhuang497/medplib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/post-training-statistical-calibration-for","slug":"post-training-statistical-calibration-for","title":"Post-Training Statistical Calibration for Higher Activation Sparsity","date":"2024-12-10","arxiv_id":"2412.07174","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["intellabs/scap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/llama-moe-v2-exploring-sparsity-of-llama-from","slug":"llama-moe-v2-exploring-sparsity-of-llama-from","title":"LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training","date":"2024-11-24","arxiv_id":"2411.15708","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opensparsellms/llama-moe-v2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/read-me-refactorizing-llms-as-router","slug":"read-me-refactorizing-llms-as-router","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","date":"2024-10-24","arxiv_id":"2410.19123","n_code_links":1,"syntology":{"ran":11,"of":16,"n_ran_checked":10,"n_instrument":1,"unverified":5,"pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["vita-group/read-me"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/generalizing-motion-planners-with-mixture-of","slug":"generalizing-motion-planners-with-mixture-of","title":"Generalizing Motion Planners with Mixture of Experts for Autonomous Driving","date":"2024-10-21","arxiv_id":"2410.15774","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tsinghua-mars-lab/statetransformer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/momentumsmoe-integrating-momentum-into-sparse","slug":"momentumsmoe-integrating-momentum-into-sparse","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","date":"2024-10-18","arxiv_id":"2410.14574","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["rachtsy/momentumsmoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficiently-democratizing-medical-llms-for-50","slug":"efficiently-democratizing-medical-llms-for-50","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","date":"2024-10-14","arxiv_id":"2410.10626","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["freedomintelligence/apollomoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/your-mixture-of-experts-llm-is-secretly-an","slug":"your-mixture-of-experts-llm-is-secretly-an","title":"Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free","date":"2024-10-14","arxiv_id":"2410.10814","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":1,"n_instrument":5,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tianyi-lab/moe-embedding"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/flex-moe-modeling-arbitrary-modality","slug":"flex-moe-modeling-arbitrary-modality","title":"Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts","date":"2024-10-10","arxiv_id":"2410.08245","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["unites-lab/flex-moe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/moe-accelerating-mixture-of-experts-methods","slug":"moe-accelerating-mixture-of-experts-methods","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","date":"2024-10-09","arxiv_id":"2410.07348","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["skyworkai/moe-plus-plus"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/exploring-the-benefit-of-activation-sparsity","slug":"exploring-the-benefit-of-activation-sparsity","title":"Exploring the Benefit of Activation Sparsity in Pre-training","date":"2024-10-04","arxiv_id":"2410.03440","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thunlp/moefication"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/searching-for-efficient-linear-layers-over-a","slug":"searching-for-efficient-linear-layers-over-a","title":"Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices","date":"2024-10-03","arxiv_id":"2410.02117","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["andpotap/einsum-search"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/clip-moe-towards-building-mixture-of-experts","slug":"clip-moe-towards-building-mixture-of-experts","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","date":"2024-09-28","arxiv_id":"2409.19291","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["OpenSparseLLMs/CLIP-MoE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/alt-moe-multimodal-alignment-via-alternating","slug":"alt-moe-multimodal-alignment-via-alternating","title":"M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework","date":"2024-09-09","arxiv_id":"2409.05929","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["HongyangLL/M3-JEPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/olmoe-open-mixture-of-experts-language-models","slug":"olmoe-open-mixture-of-experts-language-models","title":"OLMoE: Open Mixture-of-Experts Language Models","date":"2024-09-03","arxiv_id":"2409.02060","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["allenai/OLMoE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/adapmoe-adaptive-sensitivity-based-expert","slug":"adapmoe-adaptive-sensitivity-based-expert","title":"AdapMoE: Adaptive Sensitivity-based Expert Gating and Management for Efficient MoE Inference","date":"2024-08-19","arxiv_id":"2408.10284","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["pku-sec-lab/adapmoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/moextend-tuning-new-experts-for-modality-and","slug":"moextend-tuning-new-experts-for-modality-and","title":"MoExtend: Tuning New Experts for Modality and Task Extension","date":"2024-08-07","arxiv_id":"2408.03511","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["zhongshsh/moextend"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/scaling-diffusion-transformers-to-16-billion","slug":"scaling-diffusion-transformers-to-16-billion","title":"Scaling Diffusion Transformers to 16 Billion Parameters","date":"2024-07-16","arxiv_id":"2407.11633","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":6,"n_instrument":6,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","official":{"repos":["feizc/dit-moe"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/low-rank-interconnected-adaptation-across","slug":"low-rank-interconnected-adaptation-across","title":"Low-Rank Interconnected Adaptation across Layers","date":"2024-07-13","arxiv_id":"2407.09946","n_code_links":1,"syntology":{"ran":9,"of":13,"n_ran_checked":6,"n_instrument":3,"unverified":4,"pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["yibozhong/lily"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixture-of-a-million-experts","slug":"mixture-of-a-million-experts","title":"Mixture of A Million Experts","date":"2024-07-04","arxiv_id":"2407.04153","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/let-the-expert-stick-to-his-last-expert","slug":"let-the-expert-stick-to-his-last-expert","title":"Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models","date":"2024-07-02","arxiv_id":"2407.01906","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["deepseek-ai/esft"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/adamoe-token-adaptive-routing-with-null","slug":"adamoe-token-adaptive-routing-with-null","title":"AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models","date":"2024-06-19","arxiv_id":"2406.13233","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cengzihao/adamoe"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/dynamic-data-mixing-maximizes-instruction","slug":"dynamic-data-mixing-maximizes-instruction","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","date":"2024-06-17","arxiv_id":"2406.11256","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["spico197/moe-sft"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/examining-post-training-quantization-for","slug":"examining-post-training-quantization-for","title":"Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark","date":"2024-06-12","arxiv_id":"2406.08155","n_code_links":1,"syntology":{"ran":1,"of":6,"n_ran_checked":0,"n_instrument":1,"unverified":5,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["unites-lab/moe-quantization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/moe-jetpack-from-dense-checkpoints-to","slug":"moe-jetpack-from-dense-checkpoints-to","title":"MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks","date":"2024-06-07","arxiv_id":"2406.04801","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":5,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["adlith/moe-jetpack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/demystifying-the-compression-of-mixture-of","slug":"demystifying-the-compression-of-mixture-of","title":"Demystifying the Compression of Mixture-of-Experts Through a Unified Framework","date":"2024-06-04","arxiv_id":"2406.02500","n_code_links":1,"syntology":{"ran":5,"of":11,"n_ran_checked":5,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["daizedong/unified-moe-compression"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/parrot-multilingual-visual-instruction-tuning","slug":"parrot-multilingual-visual-instruction-tuning","title":"Parrot: Multilingual Visual Instruction Tuning","date":"2024-06-04","arxiv_id":"2406.02539","n_code_links":2,"syntology":{"ran":3,"of":7,"n_ran_checked":0,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["aidc-ai/parrot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/leveraging-visual-tokens-for-extended-text","slug":"leveraging-visual-tokens-for-extended-text","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","date":"2024-06-04","arxiv_id":"2406.02547","n_code_links":1,"syntology":{"ran":9,"of":14,"n_ran_checked":9,"n_instrument":0,"unverified":5,"pointer_only":14,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["showlab/VisInContext"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/skywork-moe-a-deep-dive-into-training","slug":"skywork-moe-a-deep-dive-into-training","title":"Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models","date":"2024-06-03","arxiv_id":"2406.06563","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/unchosen-experts-can-contribute-too","slug":"unchosen-experts-can-contribute-too","title":"Unchosen Experts Can Contribute Too: Unleashing MoE Models' Power by Self-Contrast","date":"2024-05-23","arxiv_id":"2405.14507","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["davidfanzz/scmoe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/meteora-multiple-tasks-embedded-lora-for","slug":"meteora-multiple-tasks-embedded-lora-for","title":"MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models","date":"2024-05-19","arxiv_id":"2405.13053","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":5,"n_instrument":3,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["paragonlight/meteor-of-lora"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/uni-moe-scaling-unified-multimodal-llms-with","slug":"uni-moe-scaling-unified-multimodal-llms-with","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","date":"2024-05-18","arxiv_id":"2405.11273","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":3,"n_instrument":3,"unverified":2,"pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hitsz-tmg/umoe-scaling-unified-multimodal-llms"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/harnessing-hierarchical-label-distribution","slug":"harnessing-hierarchical-label-distribution","title":"Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition","date":"2024-05-13","arxiv_id":"2405.07780","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["scongl/dirmixe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":6,"n_instrument":5,"unverified":1,"pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mvmoe-multi-task-vehicle-routing-solver-with","slug":"mvmoe-multi-task-vehicle-routing-solver-with","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","date":"2024-05-02","arxiv_id":"2405.01029","n_code_links":2,"syntology":{"ran":4,"of":5,"n_ran_checked":2,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["ai4co/awesome-fm4co","royalskye/routing-mvmoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/xft-unlocking-the-power-of-code-instruction","slug":"xft-unlocking-the-power-of-code-instruction","title":"XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts","date":"2024-04-23","arxiv_id":"2404.15247","n_code_links":1,"syntology":{"ran":11,"of":14,"n_ran_checked":9,"n_instrument":2,"unverified":3,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ise-uiuc/xft"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/mixlora-enhancing-large-language-models-fine","slug":"mixlora-enhancing-large-language-models-fine","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","date":"2024-04-22","arxiv_id":"2404.15159","n_code_links":2,"syntology":{"ran":6,"of":11,"n_ran_checked":6,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["TUDB-Labs/MixLoRA","mikecovlee/mLoRA"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/moe-tinymed-mixture-of-experts-for-tiny","slug":"moe-tinymed-mixture-of-experts-for-tiny","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","date":"2024-04-16","arxiv_id":"2404.10237","n_code_links":2,"syntology":{"ran":7,"of":12,"n_ran_checked":4,"n_instrument":3,"unverified":5,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["jiangsongtao/med-moe","jiangsongtao/tinymed"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/moe-ffd-mixture-of-experts-for-generalized","slug":"moe-ffd-mixture-of-experts-for-generalized","title":"MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection","date":"2024-04-12","arxiv_id":"2404.08452","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lovesiamesecat/moe-ffd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/prompt-prompted-mixture-of-experts-for","slug":"prompt-prompted-mixture-of-experts-for","title":"Prompt-prompted Adaptive Structured Pruning for Efficient LLM Generation","date":"2024-04-01","arxiv_id":"2404.01365","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hdong920/griffin"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mini-gemini-mining-the-potential-of-multi","slug":"mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","arxiv_id":"2403.18814","n_code_links":2,"syntology":{"ran":8,"of":8,"n_ran_checked":5,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dvlab-research/minigemini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/multi-task-dense-prediction-via-mixture-of","slug":"multi-task-dense-prediction-via-mixture-of","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","date":"2024-03-26","arxiv_id":"2403.17749","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":7,"n_instrument":2,"unverified":2,"pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["yuqiyang213/mlore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/boosting-continual-learning-of-vision","slug":"boosting-continual-learning-of-vision","title":"Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters","date":"2024-03-18","arxiv_id":"2403.11549","n_code_links":2,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["jiazuoyu/moe-adapters4cl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/harder-tasks-need-more-experts-dynamic","slug":"harder-tasks-need-more-experts-dynamic","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","date":"2024-03-12","arxiv_id":"2403.07652","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhenweian/dynamic_moe"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/designing-effective-sparse-expert-models","slug":"designing-effective-sparse-expert-models","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","date":"2022-02-17","arxiv_id":"2202.08906","n_code_links":3,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tensorflow/mesh"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"record_sha256":"790b3325d35e006545bd8b950645b73d81b5145d2fbbf0eea1b8683cc2cdf5ea","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}