{"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/ran/1","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":"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 run it on this task or check it against the task's benchmarks.","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":3,"rows_per_page":100,"rows":[1,100],"of":216,"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/papers/ran/1","prev":null,"next":"/task/mixture-of-experts/papers/ran/2","papers":[{"url":"/paper/minimax-m1-scaling-test-time-compute","slug":"minimax-m1-scaling-test-time-compute","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","date":"2025-06-16","arxiv_id":"2506.13585","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":0,"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/minimax-m1-scaling-test-time-compute#ran","syntology_url":"https://syntology.ai/paper/2506.13585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13585"}},"official":{"repos":["minimax-ai/minimax-m1"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/flashdmoe-fast-distributed-moe-in-a-single#ran","syntology_url":"https://syntology.ai/paper/2506.04667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.04667"}},"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"]}}},{"url":"/paper/space-your-genomic-profile-predictor-is-a","slug":"space-your-genomic-profile-predictor-is-a","title":"SPACE: Your Genomic Profile Predictor is a Powerful DNA Foundation Model","date":"2025-06-02","arxiv_id":"2506.01833","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/space-your-genomic-profile-predictor-is-a#ran","syntology_url":"https://syntology.ai/paper/2506.01833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01833"}},"official":{"repos":["zhujiwei111/space"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/from-knowledge-to-noise-ctim-rover-and-the","slug":"from-knowledge-to-noise-ctim-rover-and-the","title":"From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents","date":"2025-05-29","arxiv_id":"2505.23422","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":3,"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/from-knowledge-to-noise-ctim-rover-and-the#ran","syntology_url":"https://syntology.ai/paper/2505.23422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23422"}},"official":{"repos":["liqs-v2/ctim-rover"],"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/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","repositories_listed":2,"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/hidream-i1-a-high-efficient-image-generative#ran","syntology_url":"https://syntology.ai/paper/2505.22705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22705"}},"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"]}}},{"url":"/paper/wina-weight-informed-neuron-activation-for","slug":"wina-weight-informed-neuron-activation-for","title":"WINA: Weight Informed Neuron Activation for Accelerating Large Language Model Inference","date":"2025-05-26","arxiv_id":"2505.19427","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/wina-weight-informed-neuron-activation-for#ran","syntology_url":"https://syntology.ai/paper/2505.19427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19427"}},"official":{"repos":["microsoft/wina"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-gating-mechanism-in-sparse-moe","slug":"rethinking-gating-mechanism-in-sparse-moe","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","date":"2025-05-26","arxiv_id":"2505.19525","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"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) · 5 unverified","sample_list":"/paper/rethinking-gating-mechanism-in-sparse-moe#ran","syntology_url":"https://syntology.ai/paper/2505.19525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19525"}},"official":{"repos":["icuraslw/official-repository-of-confsmoe"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_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","sample_list":"/paper/i2moe-interpretable-multimodal-interaction#ran","syntology_url":"https://syntology.ai/paper/2505.19190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19190"}},"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"]}}},{"url":"/paper/rankllm-a-python-package-for-reranking-with","slug":"rankllm-a-python-package-for-reranking-with","title":"RankLLM: A Python Package for Reranking with LLMs","date":"2025-05-25","arxiv_id":"2505.19284","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rankllm-a-python-package-for-reranking-with#ran","syntology_url":"https://syntology.ai/paper/2505.19284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19284"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/janusdna-a-powerful-bi-directional-hybrid-dna#ran","syntology_url":"https://syntology.ai/paper/2505.17257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17257"}},"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"]}}},{"url":"/paper/more-brain-routed-mixture-of-experts-for","slug":"more-brain-routed-mixture-of-experts-for","title":"MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding","date":"2025-05-21","arxiv_id":"2505.15946","repositories_listed":0,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 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) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/more-brain-routed-mixture-of-experts-for#ran","syntology_url":"https://syntology.ai/paper/2505.15946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15946"}},"official":null}},{"url":"/paper/competesmoe-statistically-guaranteed-mixture","slug":"competesmoe-statistically-guaranteed-mixture","title":"CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition","date":"2025-05-19","arxiv_id":"2505.13380","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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","sample_list":"/paper/competesmoe-statistically-guaranteed-mixture#ran","syntology_url":"https://syntology.ai/paper/2505.13380","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13380"}},"official":{"repos":["fsoft-aic/competesmoe"],"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":["listed","official","unlocated"]}}},{"url":"/paper/gated-attention-for-large-language-models-non","slug":"gated-attention-for-large-language-models-non","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","date":"2025-05-10","arxiv_id":"2505.06708","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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) · 0 unverified","sample_list":"/paper/gated-attention-for-large-language-models-non#ran","syntology_url":"https://syntology.ai/paper/2505.06708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.06708"}},"official":{"repos":["qiuzh20/gated_attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/noesis-differentially-private-knowledge","slug":"noesis-differentially-private-knowledge","title":"NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation","date":"2025-04-25","arxiv_id":"2504.18147","repositories_listed":0,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/noesis-differentially-private-knowledge#ran","syntology_url":"https://syntology.ai/paper/2504.18147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.18147"}},"official":null}},{"url":"/paper/manifold-induced-biases-for-zero-shot-and-few","slug":"manifold-induced-biases-for-zero-shot-and-few","title":"Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images","date":"2025-04-21","arxiv_id":"2504.15470","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 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; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/manifold-induced-biases-for-zero-shot-and-few#ran","syntology_url":"https://syntology.ai/paper/2504.15470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.15470"}},"official":{"repos":["jonathanbrok/manifold-induced-biases-for-zero-shot-and-few-shot-detection-of-generated-images"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/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","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":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","sample_list":"/paper/dense-backpropagation-improves-training-for#ran","syntology_url":"https://syntology.ai/paper/2504.12463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.12463"}},"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"]}}},{"url":"/paper/plasticity-aware-mixture-of-experts-for","slug":"plasticity-aware-mixture-of-experts-for","title":"Plasticity-Aware Mixture of Experts for Learning Under QoE Shifts in Adaptive Video Streaming","date":"2025-04-14","arxiv_id":"2504.09906","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 3 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","sample_list":"/paper/plasticity-aware-mixture-of-experts-for#ran","syntology_url":"https://syntology.ai/paper/2504.09906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.09906"}},"official":null}},{"url":"/paper/spmtrack-spatio-temporal-parameter-efficient","slug":"spmtrack-spatio-temporal-parameter-efficient","title":"SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking","date":"2025-03-24","arxiv_id":"2503.18338","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 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","sample_list":"/paper/spmtrack-spatio-temporal-parameter-efficient#ran","syntology_url":"https://syntology.ai/paper/2503.18338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18338"}},"official":{"repos":["wenruicai/spmtrack"],"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/mixture-of-lookup-experts","slug":"mixture-of-lookup-experts","title":"Mixture of Lookup Experts","date":"2025-03-20","arxiv_id":"2503.15798","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mixture-of-lookup-experts#ran","syntology_url":"https://syntology.ai/paper/2503.15798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15798"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_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","sample_list":"/paper/resmoe-space-efficient-compression-of-mixture#ran","syntology_url":"https://syntology.ai/paper/2503.06881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06881"}},"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"]}}},{"url":"/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","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/a-comprehensive-survey-of-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2503.07137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07137"}},"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"]}}},{"url":"/paper/proper-a-progressive-learning-framework-for","slug":"proper-a-progressive-learning-framework-for","title":"PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation","date":"2025-03-03","arxiv_id":"2503.01303","repositories_listed":0,"syntology":{"n":5,"n_ran":3,"n_constructed":2,"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 2 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/proper-a-progressive-learning-framework-for#ran","syntology_url":"https://syntology.ai/paper/2503.01303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01303"}},"official":null}},{"url":"/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","repositories_listed":4,"syntology":{"n":20,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_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","sample_list":"/paper/comet-fine-grained-computation-communication#ran","syntology_url":"https://syntology.ai/paper/2502.19811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19811"}},"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"]}}},{"url":"/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","repositories_listed":0,"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":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","sample_list":"/paper/drop-upcycling-training-sparse-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2502.19261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19261"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":3,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/make-lora-great-again-boosting-lora-with#ran","syntology_url":"https://syntology.ai/paper/2502.16894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.16894"}},"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"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/delta-decompression-for-moe-based-llms#ran","syntology_url":"https://syntology.ai/paper/2502.17298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17298"}},"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"]}}},{"url":"/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","repositories_listed":0,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_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","sample_list":"/paper/the-empirical-impact-of-reducing-symmetries#ran","syntology_url":"https://syntology.ai/paper/2502.17391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17391"}},"official":null}},{"url":"/paper/moba-mixture-of-block-attention-for-long","slug":"moba-mixture-of-block-attention-for-long","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","date":"2025-02-18","arxiv_id":"2502.13189","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/moba-mixture-of-block-attention-for-long#ran","syntology_url":"https://syntology.ai/paper/2502.13189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13189"}},"official":{"repos":["moonshotai/moba"],"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/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","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_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","sample_list":"/paper/training-sparse-mixture-of-experts-text#ran","syntology_url":"https://syntology.ai/paper/2502.07972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07972"}},"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"]}}},{"url":"/paper/mol-moe-training-preference-guided-routers","slug":"mol-moe-training-preference-guided-routers","title":"Mol-MoE: Training Preference-Guided Routers for Molecule Generation","date":"2025-02-08","arxiv_id":"2502.05633","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":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) · 0 unverified","sample_list":"/paper/mol-moe-training-preference-guided-routers#ran","syntology_url":"https://syntology.ai/paper/2502.05633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05633"}},"official":{"repos":["ddidacus/mol-moe"],"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/distribution-aware-fairness-learning-in","slug":"distribution-aware-fairness-learning-in","title":"Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective","date":"2025-02-02","arxiv_id":"2502.00619","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"4 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/distribution-aware-fairness-learning-in#ran","syntology_url":"https://syntology.ai/paper/2502.00619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00619"}},"official":{"repos":["tvseg/dmoe"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pm-moe-mixture-of-experts-on-private-model","slug":"pm-moe-mixture-of-experts-on-private-model","title":"PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning","date":"2025-02-01","arxiv_id":"2502.00354","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/pm-moe-mixture-of-experts-on-private-model#ran","syntology_url":"https://syntology.ai/paper/2502.00354","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00354"}},"official":{"repos":["dannis97500/pm-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"]}}},{"url":"/paper/adaptive-prompt-unlocking-the-power-of-visual","slug":"adaptive-prompt-unlocking-the-power-of-visual","title":"Adaptive Prompt: Unlocking the Power of Visual Prompt Tuning","date":"2025-01-31","arxiv_id":"2501.18936","repositories_listed":0,"syntology":{"n":12,"n_ran":7,"n_constructed":6,"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 6 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/adaptive-prompt-unlocking-the-power-of-visual#ran","syntology_url":"https://syntology.ai/paper/2501.18936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18936"}},"official":null}},{"url":"/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","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/hierarchical-time-aware-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2501.14269","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.14269"}},"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"]}}},{"url":"/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","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":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","sample_list":"/paper/minimax-01-scaling-foundation-models-with#ran","syntology_url":"https://syntology.ai/paper/2501.08313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08313"}},"official":null}},{"url":"/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","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/transforming-vision-transformer-towards#ran","syntology_url":"https://syntology.ai/paper/2501.06884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06884"}},"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"]}}},{"url":"/paper/move-kd-knowledge-distillation-for-vlms-with","slug":"move-kd-knowledge-distillation-for-vlms-with","title":"MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoders","date":"2025-01-03","arxiv_id":"2501.01709","repositories_listed":0,"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/move-kd-knowledge-distillation-for-vlms-with#ran","syntology_url":"https://syntology.ai/paper/2501.01709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.01709"}},"official":null}},{"url":"/paper/deepseek-v3-technical-report","slug":"deepseek-v3-technical-report","title":"DeepSeek-V3 Technical Report","date":"2024-12-27","arxiv_id":"2412.19437","repositories_listed":4,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/deepseek-v3-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.19437","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19437"}},"official":{"repos":["deepseek-ai/deepseek-v3"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/remoe-fully-differentiable-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2412.14711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14711"}},"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"]}}},{"url":"/paper/qwen2-5-technical-report","slug":"qwen2-5-technical-report","title":"Qwen2.5 Technical Report","date":"2024-12-19","arxiv_id":"2412.15115","repositories_listed":6,"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/qwen2-5-technical-report#ran","syntology_url":"https://syntology.ai/paper/2412.15115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15115"}},"official":{"repos":["qwenlm/qwen2.5"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/medcot-medical-chain-of-thought-via","slug":"medcot-medical-chain-of-thought-via","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","date":"2024-12-18","arxiv_id":"2412.13736","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":2,"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/medcot-medical-chain-of-thought-via#ran","syntology_url":"https://syntology.ai/paper/2412.13736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13736"}},"official":{"repos":["jxliu-ai/medcot"],"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/demo-decoupled-feature-based-mixture-of","slug":"demo-decoupled-feature-based-mixture-of","title":"DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification","date":"2024-12-14","arxiv_id":"2412.10650","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/demo-decoupled-feature-based-mixture-of#ran","syntology_url":"https://syntology.ai/paper/2412.10650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10650"}},"official":{"repos":["924973292/demo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/deepseek-vl2-mixture-of-experts-vision","slug":"deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","date":"2024-12-13","arxiv_id":"2412.10302","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/deepseek-vl2-mixture-of-experts-vision#ran","syntology_url":"https://syntology.ai/paper/2412.10302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10302"}},"official":{"repos":["deepseek-ai/deepseek-vl2"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/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","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/towards-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.09278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09278"}},"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"]}}},{"url":"/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","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":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","sample_list":"/paper/llama-moe-v2-exploring-sparsity-of-llama-from#ran","syntology_url":"https://syntology.ai/paper/2411.15708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15708"}},"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"]}}},{"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/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/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/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/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/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/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/moh-multi-head-attention-as-mixture-of-head","slug":"moh-multi-head-attention-as-mixture-of-head","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","date":"2024-10-15","arxiv_id":"2410.11842","repositories_listed":3,"syntology":{"n":18,"n_ran":14,"n_constructed":5,"n_ran_checked":6,"n_instrument":8,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"14 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/moh-multi-head-attention-as-mixture-of-head#ran","syntology_url":"https://syntology.ai/paper/2410.11842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11842"}},"official":{"repos":["skyworkai/moh"],"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":["listed","official","unlocated"]}}},{"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/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/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/gets-ensemble-temperature-scaling-for","slug":"gets-ensemble-temperature-scaling-for","title":"GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networks","date":"2024-10-12","arxiv_id":"2410.09570","repositories_listed":0,"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/gets-ensemble-temperature-scaling-for#ran","syntology_url":"https://syntology.ai/paper/2410.09570","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09570"}},"official":null}},{"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/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/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/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","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/moe-accelerating-mixture-of-experts-methods#ran","syntology_url":"https://syntology.ai/paper/2410.07348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07348"}},"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"]}}},{"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/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/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/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/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/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","repositories_listed":2,"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/olmoe-open-mixture-of-experts-language-models#ran","syntology_url":"https://syntology.ai/paper/2409.02060","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02060"}},"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"]}}},{"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/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/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/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/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/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/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/moe-diffir-task-customized-diffusion-priors","slug":"moe-diffir-task-customized-diffusion-priors","title":"MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration","date":"2024-07-15","arxiv_id":"2407.10833","repositories_listed":0,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/moe-diffir-task-customized-diffusion-priors#ran","syntology_url":"https://syntology.ai/paper/2407.10833","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10833"}},"official":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/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/interpretable-preferences-via-multi-objective","slug":"interpretable-preferences-via-multi-objective","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","date":"2024-06-18","arxiv_id":"2406.12845","repositories_listed":2,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_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) · 0 unverified","sample_list":"/paper/interpretable-preferences-via-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.12845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12845"}},"official":{"repos":["RLHFlow/RLHF-Reward-Modeling"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"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/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/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/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/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/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","repositories_listed":2,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/parrot-multilingual-visual-instruction-tuning#ran","syntology_url":"https://syntology.ai/paper/2406.02539","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02539"}},"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"]}}},{"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/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/decomposing-the-neurons-activation-sparsity","slug":"decomposing-the-neurons-activation-sparsity","title":"Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation","date":"2024-05-26","arxiv_id":"2405.16486","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/decomposing-the-neurons-activation-sparsity#ran","syntology_url":"https://syntology.ai/paper/2405.16486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16486"}},"official":{"repos":["royzry98/moase-pytorch"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/moeut-mixture-of-experts-universal","slug":"moeut-mixture-of-experts-universal","title":"MoEUT: Mixture-of-Experts Universal Transformers","date":"2024-05-25","arxiv_id":"2405.16039","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/moeut-mixture-of-experts-universal#ran","syntology_url":"https://syntology.ai/paper/2405.16039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16039"}},"official":{"repos":["robertcsordas/moeut"],"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/mixture-of-experts-meets-prompt-based","slug":"mixture-of-experts-meets-prompt-based","title":"Mixture of Experts Meets Prompt-Based Continual Learning","date":"2024-05-23","arxiv_id":"2405.14124","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mixture-of-experts-meets-prompt-based#ran","syntology_url":"https://syntology.ai/paper/2405.14124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14124"}},"official":{"repos":["minhchuyentoancbn/moe_promptcl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/graph-sparsification-via-mixture-of-graphs","slug":"graph-sparsification-via-mixture-of-graphs","title":"Graph Sparsification via Mixture of Graphs","date":"2024-05-23","arxiv_id":"2405.14260","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 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","sample_list":"/paper/graph-sparsification-via-mixture-of-graphs#ran","syntology_url":"https://syntology.ai/paper/2405.14260","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14260"}},"official":{"repos":["yanweiyue/mog"],"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/dynamic-mixture-of-experts-an-auto-tuning","slug":"dynamic-mixture-of-experts-an-auto-tuning","title":"Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models","date":"2024-05-23","arxiv_id":"2405.14297","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":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamic-mixture-of-experts-an-auto-tuning#ran","syntology_url":"https://syntology.ai/paper/2405.14297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14297"}},"official":{"repos":["lins-lab/dynmoe"],"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/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","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unchosen-experts-can-contribute-too#ran","syntology_url":"https://syntology.ai/paper/2405.14507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14507"}},"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"]}}},{"url":"/paper/xrag-extreme-context-compression-for","slug":"xrag-extreme-context-compression-for","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","date":"2024-05-22","arxiv_id":"2405.13792","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/xrag-extreme-context-compression-for#ran","syntology_url":"https://syntology.ai/paper/2405.13792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13792"}},"official":{"repos":["Hannibal046/xRAG"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"ea2ca8230c08ed5545a5a031cb66a5f651721a3a3468c3a7484f3021bb8b9bc4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}