{"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":"/task/mixture-of-experts/papers/3","list_of":"/task/mixture-of-experts","task":"Mixture-of-Experts","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":14,"rows_per_page":100,"rows":[201,300],"of":1312,"counts":{"archive_papers_tagged":1312,"with_a_code_link":516,"where_syntology_ran_a_sample":216,"not_listed_spam_title":0,"listed":1312,"listed_where_code_ran":216,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":184,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":184,"listed_every_run_a_failure_of_syntologys_instrument":32,"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":"/task/mixture-of-experts","prev":"/task/mixture-of-experts/papers/2","next":"/task/mixture-of-experts/papers/4","papers":[{"url":"/paper/weakly-supervised-multimodal-learning-on","slug":"weakly-supervised-multimodal-learning-on","title":"Weakly-Supervised Multimodal Learning on MIMIC-CXR","date":"2024-11-15","arxiv_id":"2411.10356","repositories_listed":1,"syntology":null},{"url":"/paper/da-moe-addressing-depth-sensitivity-in-graph","slug":"da-moe-addressing-depth-sensitivity-in-graph","title":"DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts","date":"2024-11-05","arxiv_id":"2411.03025","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 1 unverified","sample_list":"/paper/da-moe-addressing-depth-sensitivity-in-graph#ran","syntology_url":"https://syntology.ai/paper/2411.03025","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03025"}},"official":{"repos":["celin-yao/da-moe"],"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","unlocated"]}}},{"url":"/paper/libmoe-a-library-for-comprehensive","slug":"libmoe-a-library-for-comprehensive","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","date":"2024-11-01","arxiv_id":"2411.00918","repositories_listed":1,"syntology":null},{"url":"/paper/monta-accelerating-mixture-of-experts","slug":"monta-accelerating-mixture-of-experts","title":"MoNTA: Accelerating Mixture-of-Experts Training with Network-Traffc-Aware Parallel Optimization","date":"2024-11-01","arxiv_id":"2411.00662","repositories_listed":1,"syntology":null},{"url":"/paper/sled-self-logits-evolution-decoding-for","slug":"sled-self-logits-evolution-decoding-for","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","date":"2024-11-01","arxiv_id":"2411.02433","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sled-self-logits-evolution-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2411.02433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02433"}},"official":{"repos":["JayZhang42/SLED"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-and-interpretable-grammatical-error","slug":"efficient-and-interpretable-grammatical-error","title":"Efficient and Interpretable Grammatical Error Correction with Mixture of Experts","date":"2024-10-30","arxiv_id":"2410.23507","repositories_listed":1,"syntology":null},{"url":"/paper/dmt-hi-moe-based-hyperbolic-interpretable","slug":"dmt-hi-moe-based-hyperbolic-interpretable","title":"DMT-HI: MOE-based Hyperbolic Interpretable Deep Manifold Transformation for Unspervised Dimensionality Reduction","date":"2024-10-25","arxiv_id":"2410.19504","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-mixture-of-experts-generalizable","slug":"hierarchical-mixture-of-experts-generalizable","title":"Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis","date":"2024-10-25","arxiv_id":"2410.19225","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_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","sample_list":"/paper/read-me-refactorizing-llms-as-router#ran","syntology_url":"https://syntology.ai/paper/2410.19123","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19123"}},"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"]}}},{"url":"/paper/cartesianmoe-boosting-knowledge-sharing-among","slug":"cartesianmoe-boosting-knowledge-sharing-among","title":"CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts","date":"2024-10-21","arxiv_id":"2410.16077","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/generalizing-motion-planners-with-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.15774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15774"}},"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"]}}},{"url":"/paper/lmhaze-intensity-aware-image-dehazing-with-a","slug":"lmhaze-intensity-aware-image-dehazing-with-a","title":"LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset","date":"2024-10-21","arxiv_id":"2410.16095","repositories_listed":1,"syntology":null},{"url":"/paper/lora-ir-taming-low-rank-experts-for-efficient","slug":"lora-ir-taming-low-rank-experts-for-efficient","title":"LoRA-IR: Taming Low-Rank Experts for Efficient All-in-One Image Restoration","date":"2024-10-20","arxiv_id":"2410.15385","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 2 unverified","sample_list":"/paper/lora-ir-taming-low-rank-experts-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2410.15385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15385"}},"official":{"repos":["shallowdream204/lora-ir"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/momentumsmoe-integrating-momentum-into-sparse#ran","syntology_url":"https://syntology.ai/paper/2410.14574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14574"}},"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"]}}},{"url":"/paper/st-moe-bert-a-spatial-temporal-mixture-of","slug":"st-moe-bert-a-spatial-temporal-mixture-of","title":"ST-MoE-BERT: A Spatial-Temporal Mixture-of-Experts Framework for Long-Term Cross-City Mobility Prediction","date":"2024-10-18","arxiv_id":"2410.14099","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/st-moe-bert-a-spatial-temporal-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.14099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14099"}},"official":{"repos":["he-h/HuMob"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/gavamoe-gaussian-variational-gated-mixture-of","slug":"gavamoe-gaussian-variational-gated-mixture-of","title":"GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendation","date":"2024-10-15","arxiv_id":"2410.11841","repositories_listed":1,"syntology":null},{"url":"/paper/alphalora-assigning-lora-experts-based-on","slug":"alphalora-assigning-lora-experts-based-on","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","date":"2024-10-14","arxiv_id":"2410.10054","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/alphalora-assigning-lora-experts-based-on#ran","syntology_url":"https://syntology.ai/paper/2410.10054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10054"}},"official":{"repos":["morelife2017/alphalora"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/efficiently-democratizing-medical-llms-for-50#ran","syntology_url":"https://syntology.ai/paper/2410.10626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10626"}},"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"]}}},{"url":"/paper/mixture-of-experts-made-personalized","slug":"mixture-of-experts-made-personalized","title":"Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models","date":"2024-10-14","arxiv_id":"2410.10114","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/mixture-of-experts-made-personalized#ran","syntology_url":"https://syntology.ai/paper/2410.10114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10114"}},"official":{"repos":["ljaiverson/pfedmoap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/moirai-moe-empowering-time-series-foundation","slug":"moirai-moe-empowering-time-series-foundation","title":"Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts","date":"2024-10-14","arxiv_id":"2410.10469","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_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","sample_list":"/paper/your-mixture-of-experts-llm-is-secretly-an#ran","syntology_url":"https://syntology.ai/paper/2410.10814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10814"}},"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"]}}},{"url":"/paper/retraining-free-merging-of-sparse-mixture-of","slug":"retraining-free-merging-of-sparse-mixture-of","title":"Retraining-Free Merging of Sparse MoE via Hierarchical Clustering","date":"2024-10-11","arxiv_id":"2410.08589","repositories_listed":1,"syntology":{"n":22,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/retraining-free-merging-of-sparse-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.08589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08589"}},"official":{"repos":["wazenmai/hc-smoe"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-dictionary-learning-with-switch","slug":"efficient-dictionary-learning-with-switch","title":"Efficient Dictionary Learning with Switch Sparse Autoencoders","date":"2024-10-10","arxiv_id":"2410.08201","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/efficient-dictionary-learning-with-switch#ran","syntology_url":"https://syntology.ai/paper/2410.08201","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08201"}},"official":{"repos":["amudide/switch_sae"],"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_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","sample_list":"/paper/flex-moe-modeling-arbitrary-modality#ran","syntology_url":"https://syntology.ai/paper/2410.08245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08245"}},"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"]}}},{"url":"/paper/more-experts-than-galaxies-conditionally","slug":"more-experts-than-galaxies-conditionally","title":"More Experts Than Galaxies: Conditionally-overlapping Experts With Biologically-Inspired Fixed Routing","date":"2024-10-10","arxiv_id":"2410.08003","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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","sample_list":"/paper/more-experts-than-galaxies-conditionally#ran","syntology_url":"https://syntology.ai/paper/2410.08003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08003"}},"official":{"repos":["shaier/comet"],"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"]}}},{"url":"/paper/aria-an-open-multimodal-native-mixture-of","slug":"aria-an-open-multimodal-native-mixture-of","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","date":"2024-10-08","arxiv_id":"2410.05993","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/aria-an-open-multimodal-native-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.05993","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05993"}},"official":{"repos":["rhymes-ai/aria"],"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"]}}},{"url":"/paper/mc-moe-mixture-compressor-for-mixture-of","slug":"mc-moe-mixture-compressor-for-mixture-of","title":"MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More","date":"2024-10-08","arxiv_id":"2410.06270","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"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) · 3 unverified","sample_list":"/paper/mc-moe-mixture-compressor-for-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2410.06270","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06270"}},"official":{"repos":["aaronhuang-778/mc-moe"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/model-glue-democratized-llm-scaling-for-a","slug":"model-glue-democratized-llm-scaling-for-a","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","date":"2024-10-07","arxiv_id":"2410.05357","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":4,"n_ran_checked":6,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"10 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/model-glue-democratized-llm-scaling-for-a#ran","syntology_url":"https://syntology.ai/paper/2410.05357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05357"}},"official":{"repos":["model-glue/model-glue"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":4,"n_ran_no_instrument_failure":6,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-fusion-strategies-for-mapping","slug":"multimodal-fusion-strategies-for-mapping","title":"Multimodal Fusion Strategies for Mapping Biophysical Landscape Features","date":"2024-10-07","arxiv_id":"2410.04833","repositories_listed":1,"syntology":null},{"url":"/paper/mlp-kan-unifying-deep-representation-and","slug":"mlp-kan-unifying-deep-representation-and","title":"MLP-KAN: Unifying Deep Representation and Function Learning","date":"2024-10-03","arxiv_id":"2410.03027","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/searching-for-efficient-linear-layers-over-a#ran","syntology_url":"https://syntology.ai/paper/2410.02117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02117"}},"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"]}}},{"url":"/paper/open-rag-enhanced-retrieval-augmented","slug":"open-rag-enhanced-retrieval-augmented","title":"Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models","date":"2024-10-02","arxiv_id":"2410.01782","repositories_listed":1,"syntology":null},{"url":"/paper/robust-traffic-forecasting-against-spatial","slug":"robust-traffic-forecasting-against-spatial","title":"Robust Traffic Forecasting against Spatial Shift over Years","date":"2024-10-01","arxiv_id":"2410.00373","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/robust-traffic-forecasting-against-spatial#ran","syntology_url":"https://syntology.ai/paper/2410.00373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00373"}},"official":{"repos":["dreamzz5/st-expert"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/clip-moe-towards-building-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2409.19291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19291"}},"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"]}}},{"url":"/paper/a-time-series-is-worth-five-experts-1","slug":"a-time-series-is-worth-five-experts-1","title":"A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction","date":"2024-09-26","arxiv_id":"2409.17440","repositories_listed":1,"syntology":null},{"url":"/paper/uni-med-a-unified-medical-generalist","slug":"uni-med-a-unified-medical-generalist","title":"Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE","date":"2024-09-26","arxiv_id":"2409.17508","repositories_listed":1,"syntology":null},{"url":"/paper/time-moe-billion-scale-time-series-foundation","slug":"time-moe-billion-scale-time-series-foundation","title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","date":"2024-09-24","arxiv_id":"2409.16040","repositories_listed":1,"syntology":{"n":20,"n_ran":14,"n_constructed":9,"n_ran_checked":11,"n_instrument":3,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/time-moe-billion-scale-time-series-foundation#ran","syntology_url":"https://syntology.ai/paper/2409.16040","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16040"}},"official":{"repos":["time-moe/time-moe"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":9,"n_ran_no_instrument_failure":11,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/a-gated-residual-kolmogorov-arnold-networks","slug":"a-gated-residual-kolmogorov-arnold-networks","title":"A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Experts","date":"2024-09-23","arxiv_id":"2409.15161","repositories_listed":1,"syntology":null},{"url":"/paper/on-device-collaborative-language-modeling-via","slug":"on-device-collaborative-language-modeling-via","title":"On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists","date":"2024-09-20","arxiv_id":"2409.13931","repositories_listed":1,"syntology":null},{"url":"/paper/lola-an-open-source-massively-multilingual","slug":"lola-an-open-source-massively-multilingual","title":"LOLA -- An Open-Source Massively Multilingual Large Language Model","date":"2024-09-17","arxiv_id":"2409.11272","repositories_listed":1,"syntology":null},{"url":"/paper/minidrive-more-efficient-vision-language","slug":"minidrive-more-efficient-vision-language","title":"MiniDrive: More Efficient Vision-Language Models with Multi-Level 2D Features as Text Tokens for Autonomous Driving","date":"2024-09-11","arxiv_id":"2409.07267","repositories_listed":1,"syntology":null},{"url":"/paper/ve-modeling-multivariate-time-series","slug":"ve-modeling-multivariate-time-series","title":"VE: Modeling Multivariate Time Series Correlation with Variate Embedding","date":"2024-09-10","arxiv_id":"2409.06169","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/alt-moe-multimodal-alignment-via-alternating#ran","syntology_url":"https://syntology.ai/paper/2409.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05929"}},"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"]}}},{"url":"/paper/gradient-free-variational-learning-with","slug":"gradient-free-variational-learning-with","title":"Gradient-free variational learning with conditional mixture networks","date":"2024-08-29","arxiv_id":"2408.16429","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"1 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/gradient-free-variational-learning-with#ran","syntology_url":"https://syntology.ai/paper/2408.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16429"}},"official":{"repos":["versestech/cavi-cmn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-mod-making-llava-tiny-via-moe-knowledge","slug":"llava-mod-making-llava-tiny-via-moe-knowledge","title":"LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation","date":"2024-08-28","arxiv_id":"2408.15881","repositories_listed":1,"syntology":{"n":12,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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) · 6 unverified","sample_list":"/paper/llava-mod-making-llava-tiny-via-moe-knowledge#ran","syntology_url":"https://syntology.ai/paper/2408.15881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15881"}},"official":{"repos":["shufangxun/llava-mod"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/dutytte-deciphering-uncertainty-in-origin","slug":"dutytte-deciphering-uncertainty-in-origin","title":"DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation","date":"2024-08-23","arxiv_id":"2408.12809","repositories_listed":1,"syntology":null},{"url":"/paper/improving-factuality-in-large-language-models","slug":"improving-factuality-in-large-language-models","title":"Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators","date":"2024-08-22","arxiv_id":"2408.12325","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-factuality-in-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2408.12325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12325"}},"official":{"repos":["ydk122024/cdt"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kan4tsf-are-kan-and-kan-based-models","slug":"kan4tsf-are-kan-and-kan-based-models","title":"KAN4TSF: Are KAN and KAN-based models Effective for Time Series Forecasting?","date":"2024-08-21","arxiv_id":"2408.11306","repositories_listed":1,"syntology":null},{"url":"/paper/anygraph-graph-foundation-model-in-the-wild","slug":"anygraph-graph-foundation-model-in-the-wild","title":"AnyGraph: Graph Foundation Model in the Wild","date":"2024-08-20","arxiv_id":"2408.10700","repositories_listed":1,"syntology":null},{"url":"/paper/navigating-spatio-temporal-heterogeneity-a","slug":"navigating-spatio-temporal-heterogeneity-a","title":"Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting","date":"2024-08-20","arxiv_id":"2408.10822","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/adapmoe-adaptive-sensitivity-based-expert#ran","syntology_url":"https://syntology.ai/paper/2408.10284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10284"}},"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"]}}},{"url":"/paper/customizing-language-models-with-instance","slug":"customizing-language-models-with-instance","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","date":"2024-08-19","arxiv_id":"2408.10159","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":7,"n_ran_checked":7,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":13,"phrase":"8 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/customizing-language-models-with-instance#ran","syntology_url":"https://syntology.ai/paper/2408.10159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10159"}},"official":{"repos":["akalikong/ilora"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/fedkim-adaptive-federated-knowledge-injection","slug":"fedkim-adaptive-federated-knowledge-injection","title":"FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models","date":"2024-08-17","arxiv_id":"2408.10276","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fedkim-adaptive-federated-knowledge-injection#ran","syntology_url":"https://syntology.ai/paper/2408.10276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10276"}},"official":{"repos":["XiaochenWang-PSU/FedKIM"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/integrating-multi-view-analysis-multi-view","slug":"integrating-multi-view-analysis-multi-view","title":"Integrating Multi-view Analysis: Multi-view Mixture-of-Expert for Textual Personality Detection","date":"2024-08-16","arxiv_id":"2408.08551","repositories_listed":1,"syntology":null},{"url":"/paper/factorllm-factorizing-knowledge-via-mixture","slug":"factorllm-factorizing-knowledge-via-mixture","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","date":"2024-08-15","arxiv_id":"2408.11855","repositories_listed":1,"syntology":null},{"url":"/paper/aquilamoe-efficient-training-for-moe-models","slug":"aquilamoe-efficient-training-for-moe-models","title":"AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies","date":"2024-08-13","arxiv_id":"2408.06567","repositories_listed":1,"syntology":null},{"url":"/paper/layerwise-recurrent-router-for-mixture-of","slug":"layerwise-recurrent-router-for-mixture-of","title":"Layerwise Recurrent Router for Mixture-of-Experts","date":"2024-08-13","arxiv_id":"2408.06793","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-the-performance-and-estimating","slug":"understanding-the-performance-and-estimating","title":"Understanding the Performance and Estimating the Cost of LLM Fine-Tuning","date":"2024-08-08","arxiv_id":"2408.04693","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/moextend-tuning-new-experts-for-modality-and#ran","syntology_url":"https://syntology.ai/paper/2408.03511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03511"}},"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"]}}},{"url":"/paper/mixture-of-nested-experts-adaptive-processing","slug":"mixture-of-nested-experts-adaptive-processing","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","date":"2024-07-29","arxiv_id":"2407.19985","repositories_listed":1,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mixture-of-nested-experts-adaptive-processing#ran","syntology_url":"https://syntology.ai/paper/2407.19985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19985"}},"official":null}},{"url":"/paper/mixture-of-modular-experts-distilling","slug":"mixture-of-modular-experts-distilling","title":"Mixture of Modular Experts: Distilling Knowledge from a Multilingual Teacher into Specialized Modular Language Models","date":"2024-07-28","arxiv_id":"2407.19610","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-language-group-based-moe-enhancing","slug":"dynamic-language-group-based-moe-enhancing","title":"Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","date":"2024-07-26","arxiv_id":"2407.18581","repositories_listed":1,"syntology":null},{"url":"/paper/moose-multi-orientation-sharing-experts-for","slug":"moose-multi-orientation-sharing-experts-for","title":"MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition","date":"2024-07-26","arxiv_id":"2407.18616","repositories_listed":1,"syntology":null},{"url":"/paper/m4-multi-proxy-multi-gate-mixture-of-experts","slug":"m4-multi-proxy-multi-gate-mixture-of-experts","title":"M4: Multi-Proxy Multi-Gate Mixture of Experts Network for Multiple Instance Learning in Histopathology Image Analysis","date":"2024-07-24","arxiv_id":"2407.17267","repositories_listed":1,"syntology":null},{"url":"/paper/norface-improving-facial-expression-analysis","slug":"norface-improving-facial-expression-analysis","title":"Norface: Improving Facial Expression Analysis by Identity Normalization","date":"2024-07-22","arxiv_id":"2407.15617","repositories_listed":1,"syntology":null},{"url":"/paper/stretching-each-dollar-diffusion-training","slug":"stretching-each-dollar-diffusion-training","title":"Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget","date":"2024-07-22","arxiv_id":"2407.15811","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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","sample_list":"/paper/stretching-each-dollar-diffusion-training#ran","syntology_url":"https://syntology.ai/paper/2407.15811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15811"}},"official":{"repos":["sonyresearch/micro_diffusion"],"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"]}}},{"url":"/paper/maskmoe-boosting-token-level-learning-via","slug":"maskmoe-boosting-token-level-learning-via","title":"MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts","date":"2024-07-13","arxiv_id":"2407.09816","repositories_listed":1,"syntology":null},{"url":"/paper/moveint-mixture-of-variational-experts-for","slug":"moveint-mixture-of-variational-experts-for","title":"MoVEInt: Mixture of Variational Experts for Learning Human-Robot Interactions from Demonstrations","date":"2024-07-10","arxiv_id":"2407.07636","repositories_listed":1,"syntology":null},{"url":"/paper/swin-smt-global-sequential-modeling-in-3d","slug":"swin-smt-global-sequential-modeling-in-3d","title":"Swin SMT: Global Sequential Modeling in 3D Medical Image Segmentation","date":"2024-07-10","arxiv_id":"2407.07514","repositories_listed":1,"syntology":null},{"url":"/paper/completed-feature-disentanglement-learning","slug":"completed-feature-disentanglement-learning","title":"Completed Feature Disentanglement Learning for Multimodal MRIs Analysis","date":"2024-07-06","arxiv_id":"2407.04916","repositories_listed":1,"syntology":null},{"url":"/paper/yourmt3-multi-instrument-music-transcription","slug":"yourmt3-multi-instrument-music-transcription","title":"YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentation","date":"2024-07-05","arxiv_id":"2407.04822","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_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","sample_list":"/paper/mixture-of-a-million-experts#ran","syntology_url":"https://syntology.ai/paper/2407.04153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04153"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/let-the-expert-stick-to-his-last-expert#ran","syntology_url":"https://syntology.ai/paper/2407.01906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01906"}},"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"]}}},{"url":"/paper/efficient-expert-pruning-for-sparse-mixture","slug":"efficient-expert-pruning-for-sparse-mixture","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","date":"2024-07-01","arxiv_id":"2407.00945","repositories_listed":1,"syntology":null},{"url":"/paper/solving-token-gradient-conflict-in-mixture-of","slug":"solving-token-gradient-conflict-in-mixture-of","title":"Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model","date":"2024-06-28","arxiv_id":"2406.19905","repositories_listed":1,"syntology":null},{"url":"/paper/a-teacher-is-worth-a-million-instructions","slug":"a-teacher-is-worth-a-million-instructions","title":"A Teacher Is Worth A Million Instructions","date":"2024-06-27","arxiv_id":"2406.19112","repositories_listed":1,"syntology":null},{"url":"/paper/a-closer-look-into-mixture-of-experts-in","slug":"a-closer-look-into-mixture-of-experts-in","title":"A Closer Look into Mixture-of-Experts in Large Language Models","date":"2024-06-26","arxiv_id":"2406.18219","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-mixture-of-experts","slug":"a-survey-on-mixture-of-experts","title":"A Survey on Mixture of Experts","date":"2024-06-26","arxiv_id":"2407.06204","repositories_listed":1,"syntology":null},{"url":"/paper/otce-hybrid-ssm-and-attention-with-cross","slug":"otce-hybrid-ssm-and-attention-with-cross","title":"OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser","date":"2024-06-24","arxiv_id":"2406.16495","repositories_listed":1,"syntology":null},{"url":"/paper/peirce-in-the-machine-how-mixture-of-experts","slug":"peirce-in-the-machine-how-mixture-of-experts","title":"Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Construction","date":"2024-06-24","arxiv_id":"2406.17150","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/adamoe-token-adaptive-routing-with-null#ran","syntology_url":"https://syntology.ai/paper/2406.13233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13233"}},"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"]}}},{"url":"/paper/gw-moe-resolving-uncertainty-in-moe-router","slug":"gw-moe-resolving-uncertainty-in-moe-router","title":"GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory","date":"2024-06-18","arxiv_id":"2406.12375","repositories_listed":1,"syntology":null},{"url":"/paper/deepseek-coder-v2-breaking-the-barrier-of","slug":"deepseek-coder-v2-breaking-the-barrier-of","title":"DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence","date":"2024-06-17","arxiv_id":"2406.11931","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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","sample_list":"/paper/dynamic-data-mixing-maximizes-instruction#ran","syntology_url":"https://syntology.ai/paper/2406.11256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11256"}},"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"]}}},{"url":"/paper/graph-knowledge-distillation-to-mixture-of","slug":"graph-knowledge-distillation-to-mixture-of","title":"Graph Knowledge Distillation to Mixture of Experts","date":"2024-06-17","arxiv_id":"2406.11919","repositories_listed":1,"syntology":null},{"url":"/paper/not-eliminate-but-aggregate-post-hoc-control","slug":"not-eliminate-but-aggregate-post-hoc-control","title":"Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding","date":"2024-06-17","arxiv_id":"2406.12060","repositories_listed":1,"syntology":null},{"url":"/paper/texttt-moe-rbench-towards-building-reliable","slug":"texttt-moe-rbench-towards-building-reliable","title":"$\\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts","date":"2024-06-17","arxiv_id":"2406.11353","repositories_listed":1,"syntology":null},{"url":"/paper/towards-efficient-pareto-set-approximation","slug":"towards-efficient-pareto-set-approximation","title":"Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion","date":"2024-06-14","arxiv_id":"2406.09770","repositories_listed":1,"syntology":null},{"url":"/paper/deepunifiedmom-unified-time-series-momentum","slug":"deepunifiedmom-unified-time-series-momentum","title":"DeepUnifiedMom: Unified Time-series Momentum Portfolio Construction via Multi-Task Learning with Multi-Gate Mixture of Experts","date":"2024-06-13","arxiv_id":"2406.08742","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/examining-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.08155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08155"}},"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"]}}},{"url":"/paper/turbo-sparse-achieving-llm-sota-performance","slug":"turbo-sparse-achieving-llm-sota-performance","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","date":"2024-06-10","arxiv_id":"2406.05955","repositories_listed":1,"syntology":null},{"url":"/paper/meft-memory-efficient-fine-tuning-through","slug":"meft-memory-efficient-fine-tuning-through","title":"MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter","date":"2024-06-07","arxiv_id":"2406.04984","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"7 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; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/meft-memory-efficient-fine-tuning-through#ran","syntology_url":"https://syntology.ai/paper/2406.04984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04984"}},"official":{"repos":["currentf/meft"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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","sample_list":"/paper/moe-jetpack-from-dense-checkpoints-to#ran","syntology_url":"https://syntology.ai/paper/2406.04801","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04801"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_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","sample_list":"/paper/demystifying-the-compression-of-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2406.02500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02500"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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","sample_list":"/paper/skywork-moe-a-deep-dive-into-training#ran","syntology_url":"https://syntology.ai/paper/2406.06563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06563"}},"official":null}},{"url":"/paper/reservoir-history-matching-of-the-norne-field","slug":"reservoir-history-matching-of-the-norne-field","title":"Reservoir History Matching of the Norne field with generative exotic priors and a coupled Mixture of Experts -- Physics Informed Neural Operator Forward Model","date":"2024-06-02","arxiv_id":"2406.00889","repositories_listed":1,"syntology":null},{"url":"/paper/a-gaussian-process-based-streaming-algorithm","slug":"a-gaussian-process-based-streaming-algorithm","title":"A Gaussian Process-based Streaming Algorithm for Prediction of Time Series With Regimes and Outliers","date":"2024-06-01","arxiv_id":"2406.00570","repositories_listed":1,"syntology":null},{"url":"/paper/learning-mixture-of-experts-for-general","slug":"learning-mixture-of-experts-for-general","title":"Learning Mixture-of-Experts for General-Purpose Black-Box Discrete Optimization","date":"2024-05-29","arxiv_id":"2405.18884","repositories_listed":1,"syntology":null},{"url":"/paper/yuan-2-0-m32-mixture-of-experts-with","slug":"yuan-2-0-m32-mixture-of-experts-with","title":"Yuan 2.0-M32: Mixture of Experts with Attention Router","date":"2024-05-28","arxiv_id":"2405.17976","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/yuan-2-0-m32-mixture-of-experts-with#ran","syntology_url":"https://syntology.ai/paper/2405.17976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17976"}},"official":{"repos":["ieit-yuan/yuan2.0-m32"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-fast-feed-forward-networks-with","slug":"enhancing-fast-feed-forward-networks-with","title":"Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf Node","date":"2024-05-27","arxiv_id":"2405.16836","repositories_listed":1,"syntology":null}],"record_sha256":"b0a1379d62ff9486dad8db632a18cb278ae1ea19bfd39e82d4a50bcad2ce482d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}