{"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/2","list_of":"/task/mixture-of-experts","task":"Mixture-of-Experts","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":14,"rows_per_page":100,"rows":[101,200],"of":1312,"counts":{"archive_papers_tagged":1312,"with_a_code_link":516,"where_syntology_ran_a_sample":216,"not_listed_spam_title":0,"listed":1312,"listed_where_code_ran":216,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":184,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":184,"listed_every_run_a_failure_of_syntologys_instrument":32,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/mixture-of-experts","prev":"/task/mixture-of-experts","next":"/task/mixture-of-experts/papers/3","papers":[{"url":"/paper/thanora-task-heterogeneity-aware-multi-task","slug":"thanora-task-heterogeneity-aware-multi-task","title":"ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation","date":"2025-05-24","arxiv_id":"2505.18640","repositories_listed":1,"syntology":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/cola-collaborative-low-rank-adaptation","slug":"cola-collaborative-low-rank-adaptation","title":"CoLA: Collaborative Low-Rank Adaptation","date":"2025-05-21","arxiv_id":"2505.15471","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-models-suit-expert-offloading-on","slug":"not-all-models-suit-expert-offloading-on","title":"Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models","date":"2025-05-21","arxiv_id":"2505.16056","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-cultural-safety-evaluation","slug":"multimodal-cultural-safety-evaluation","title":"Multimodal Cultural Safety: Evaluation Frameworks and Alignment Strategies","date":"2025-05-20","arxiv_id":"2505.14972","repositories_listed":1,"syntology":null},{"url":"/paper/towards-rehearsal-free-continual-relation","slug":"towards-rehearsal-free-continual-relation","title":"Towards Rehearsal-Free Continual Relation Extraction: Capturing Within-Task Variance with Adaptive Prompting","date":"2025-05-20","arxiv_id":"2505.13944","repositories_listed":1,"syntology":null},{"url":"/paper/u-sam-an-audio-language-model-for-unified","slug":"u-sam-an-audio-language-model-for-unified","title":"U-SAM: An audio language Model for Unified Speech, Audio, and Music Understanding","date":"2025-05-20","arxiv_id":"2505.13880","repositories_listed":1,"syntology":null},{"url":"/paper/occult-optimizing-collaborative-communication","slug":"occult-optimizing-collaborative-communication","title":"Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference","date":"2025-05-19","arxiv_id":"2505.13345","repositories_listed":1,"syntology":null},{"url":"/paper/multi-modal-collaborative-optimization-and","slug":"multi-modal-collaborative-optimization-and","title":"Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition","date":"2025-05-17","arxiv_id":"2505.12007","repositories_listed":1,"syntology":null},{"url":"/paper/pt-moe-an-efficient-finetuning-framework-for","slug":"pt-moe-an-efficient-finetuning-framework-for","title":"PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning","date":"2025-05-14","arxiv_id":"2505.09519","repositories_listed":1,"syntology":null},{"url":"/paper/emotion-qwen-training-hybrid-experts-for","slug":"emotion-qwen-training-hybrid-experts-for","title":"Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding","date":"2025-05-10","arxiv_id":"2505.06685","repositories_listed":1,"syntology":null},{"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/mxmoe-mixed-precision-quantization-for-moe","slug":"mxmoe-mixed-precision-quantization-for-moe","title":"MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design","date":"2025-05-09","arxiv_id":"2505.05799","repositories_listed":1,"syntology":null},{"url":"/paper/llm-e-guess-can-llms-capabilities-advance","slug":"llm-e-guess-can-llms-capabilities-advance","title":"LLM-e Guess: Can LLMs Capabilities Advance Without Hardware Progress?","date":"2025-05-07","arxiv_id":"2505.04075","repositories_listed":1,"syntology":null},{"url":"/paper/finger-pose-estimation-for-under-screen","slug":"finger-pose-estimation-for-under-screen","title":"Finger Pose Estimation for Under-screen Fingerprint Sensor","date":"2025-05-05","arxiv_id":"2505.02481","repositories_listed":1,"syntology":null},{"url":"/paper/learning-heterogeneous-mixture-of-scene","slug":"learning-heterogeneous-mixture-of-scene","title":"Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields","date":"2025-05-04","arxiv_id":"2505.02005","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-sparse-attention-content-based","slug":"mixture-of-sparse-attention-content-based","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","date":"2025-05-01","arxiv_id":"2505.00315","repositories_listed":1,"syntology":null},{"url":"/paper/micarvlmoe-a-modern-gated-cross-aligned","slug":"micarvlmoe-a-modern-gated-cross-aligned","title":"MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation","date":"2025-04-29","arxiv_id":"2504.20343","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-hidden-movie-genre-and-user","slug":"unveiling-the-hidden-movie-genre-and-user","title":"Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection","date":"2025-04-24","arxiv_id":"2504.17834","repositories_listed":1,"syntology":null},{"url":"/paper/distribution-aware-forgetting-compensation","slug":"distribution-aware-forgetting-compensation","title":"Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification","date":"2025-04-21","arxiv_id":"2504.15041","repositories_listed":1,"syntology":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/c3po-critical-layer-core-expert-collaborative","slug":"c3po-critical-layer-core-expert-collaborative","title":"C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing","date":"2025-04-10","arxiv_id":"2504.07964","repositories_listed":1,"syntology":null},{"url":"/paper/cluster-driven-expert-pruning-for-mixture-of","slug":"cluster-driven-expert-pruning-for-mixture-of","title":"Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models","date":"2025-04-10","arxiv_id":"2504.07807","repositories_listed":1,"syntology":null},{"url":"/paper/kimi-vl-technical-report","slug":"kimi-vl-technical-report","title":"Kimi-VL Technical Report","date":"2025-04-10","arxiv_id":"2504.07491","repositories_listed":1,"syntology":null},{"url":"/paper/moediff-sr-mixture-of-experts-guided","slug":"moediff-sr-mixture-of-experts-guided","title":"MoEDiff-SR: Mixture of Experts-Guided Diffusion Model for Region-Adaptive MRI Super-Resolution","date":"2025-04-09","arxiv_id":"2504.07308","repositories_listed":1,"syntology":null},{"url":"/paper/hybrimoe-hybrid-cpu-gpu-scheduling-and-cache","slug":"hybrimoe-hybrid-cpu-gpu-scheduling-and-cache","title":"HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference","date":"2025-04-08","arxiv_id":"2504.05897","repositories_listed":1,"syntology":null},{"url":"/paper/milo-efficient-quantized-moe-inference-with","slug":"milo-efficient-quantized-moe-inference-with","title":"MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators","date":"2025-04-03","arxiv_id":"2504.02658","repositories_listed":1,"syntology":null},{"url":"/paper/dynmole-boosting-mixture-of-lora-experts-fine","slug":"dynmole-boosting-mixture-of-lora-experts-fine","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","date":"2025-04-01","arxiv_id":"2504.00661","repositories_listed":1,"syntology":null},{"url":"/paper/a-multi-scale-lithium-ion-battery-capacity","slug":"a-multi-scale-lithium-ion-battery-capacity","title":"A multi-scale lithium-ion battery capacity prediction using mixture of experts and patch-based MLP","date":"2025-03-26","arxiv_id":"2504.03706","repositories_listed":1,"syntology":null},{"url":"/paper/modality-independent-brain-lesion","slug":"modality-independent-brain-lesion","title":"Modality-Independent Brain Lesion Segmentation with Privacy-aware Continual Learning","date":"2025-03-26","arxiv_id":"2503.20326","repositories_listed":1,"syntology":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/fast-filtering-of-non-gaussian-models-using","slug":"fast-filtering-of-non-gaussian-models-using","title":"Fast filtering of non-Gaussian models using Amortized Optimal Transport Maps","date":"2025-03-16","arxiv_id":"2503.12633","repositories_listed":1,"syntology":null},{"url":"/paper/molex-mixture-of-layer-experts-for-finetuning","slug":"molex-mixture-of-layer-experts-for-finetuning","title":"MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling","date":"2025-03-14","arxiv_id":"2503.11144","repositories_listed":1,"syntology":null},{"url":"/paper/samoyeds-accelerating-moe-models-with","slug":"samoyeds-accelerating-moe-models-with","title":"Samoyeds: Accelerating MoE Models with Structured Sparsity Leveraging Sparse Tensor Cores","date":"2025-03-13","arxiv_id":"2503.10725","repositories_listed":1,"syntology":null},{"url":"/paper/stablefusion-continual-video-retrieval-via","slug":"stablefusion-continual-video-retrieval-via","title":"StableFusion: Continual Video Retrieval via Frame Adaptation","date":"2025-03-13","arxiv_id":"2503.10111","repositories_listed":1,"syntology":null},{"url":"/paper/towards-robust-multimodal-representation-a","slug":"towards-robust-multimodal-representation-a","title":"Towards Robust Multimodal Representation: A Unified Approach with Adaptive Experts and Alignment","date":"2025-03-12","arxiv_id":"2503.09498","repositories_listed":1,"syntology":null},{"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/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/swift-hydra-self-reinforcing-generative","slug":"swift-hydra-self-reinforcing-generative","title":"Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models","date":"2025-03-09","arxiv_id":"2503.06413","repositories_listed":1,"syntology":null},{"url":"/paper/linear-moe-linear-sequence-modeling-meets","slug":"linear-moe-linear-sequence-modeling-meets","title":"Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts","date":"2025-03-07","arxiv_id":"2503.05447","repositories_listed":1,"syntology":null},{"url":"/paper/question-aware-gaussian-experts-for-audio","slug":"question-aware-gaussian-experts-for-audio","title":"Question-Aware Gaussian Experts for Audio-Visual Question Answering","date":"2025-03-06","arxiv_id":"2503.04459","repositories_listed":1,"syntology":null},{"url":"/paper/small-but-mighty-enhancing-time-series","slug":"small-but-mighty-enhancing-time-series","title":"Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs","date":"2025-03-05","arxiv_id":"2503.03594","repositories_listed":1,"syntology":null},{"url":"/paper/voicegrpo-modern-moe-transformers-with-group","slug":"voicegrpo-modern-moe-transformers-with-group","title":"VoiceGRPO: Modern MoE Transformers with Group Relative Policy Optimization GRPO for AI Voice Health Care Applications on Voice Pathology Detection","date":"2025-03-05","arxiv_id":"2503.03797","repositories_listed":1,"syntology":null},{"url":"/paper/mx-font-mixture-of-heterogeneous-aggregation","slug":"mx-font-mixture-of-heterogeneous-aggregation","title":"MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation","date":"2025-03-04","arxiv_id":"2503.02799","repositories_listed":1,"syntology":null},{"url":"/paper/union-of-experts-adapting-hierarchical","slug":"union-of-experts-adapting-hierarchical","title":"Union of Experts: Adapting Hierarchical Routing to Equivalently Decomposed Transformer","date":"2025-03-04","arxiv_id":"2503.02495","repositories_listed":1,"syntology":null},{"url":"/paper/r2-t2-re-routing-in-test-time-for-multimodal","slug":"r2-t2-re-routing-in-test-time-for-multimodal","title":"R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts","date":"2025-02-27","arxiv_id":"2502.20395","repositories_listed":1,"syntology":null},{"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/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/binary-integer-programming-based-algorithm","slug":"binary-integer-programming-based-algorithm","title":"Binary-Integer-Programming Based Algorithm for Expert Load Balancing in Mixture-of-Experts Models","date":"2025-02-21","arxiv_id":"2502.15451","repositories_listed":1,"syntology":null},{"url":"/paper/tight-clusters-make-specialized-experts","slug":"tight-clusters-make-specialized-experts","title":"Tight Clusters Make Specialized Experts","date":"2025-02-21","arxiv_id":"2502.15315","repositories_listed":1,"syntology":null},{"url":"/paper/chatvla-unified-multimodal-understanding-and","slug":"chatvla-unified-multimodal-understanding-and","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model","date":"2025-02-20","arxiv_id":"2502.14420","repositories_listed":1,"syntology":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/accurate-expert-predictions-in-moe-inference","slug":"accurate-expert-predictions-in-moe-inference","title":"Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate","date":"2025-02-17","arxiv_id":"2502.12224","repositories_listed":1,"syntology":null},{"url":"/paper/eidetic-learning-an-efficient-and-provable","slug":"eidetic-learning-an-efficient-and-provable","title":"Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting","date":"2025-02-13","arxiv_id":"2502.09500","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-mixture-of-experts-for-remote","slug":"heterogeneous-mixture-of-experts-for-remote","title":"Heterogeneous Mixture of Experts for Remote Sensing Image Super-Resolution","date":"2025-02-12","arxiv_id":"2502.09654","repositories_listed":1,"syntology":null},{"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/jakiro-boosting-speculative-decoding-with","slug":"jakiro-boosting-speculative-decoding-with","title":"Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE","date":"2025-02-10","arxiv_id":"2502.06282","repositories_listed":1,"syntology":null},{"url":"/paper/klotski-efficient-mixture-of-expert-inference","slug":"klotski-efficient-mixture-of-expert-inference","title":"Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline","date":"2025-02-09","arxiv_id":"2502.06888","repositories_listed":1,"syntology":null},{"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/cmoe-fast-carving-of-mixture-of-experts-for","slug":"cmoe-fast-carving-of-mixture-of-experts-for","title":"CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference","date":"2025-02-06","arxiv_id":"2502.04416","repositories_listed":1,"syntology":null},{"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/unigraph2-learning-a-unified-embedding-space","slug":"unigraph2-learning-a-unified-embedding-space","title":"UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs","date":"2025-02-02","arxiv_id":"2502.00806","repositories_listed":1,"syntology":null},{"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/freqmoe-enhancing-time-series-forecasting","slug":"freqmoe-enhancing-time-series-forecasting","title":"FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts","date":"2025-01-25","arxiv_id":"2501.15125","repositories_listed":1,"syntology":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/modality-interactive-mixture-of-experts-for","slug":"modality-interactive-mixture-of-experts-for","title":"Modality Interactive Mixture-of-Experts for Fake News Detection","date":"2025-01-21","arxiv_id":"2501.12431","repositories_listed":1,"syntology":null},{"url":"/paper/mogernn-an-inductive-traffic-predictor-for","slug":"mogernn-an-inductive-traffic-predictor-for","title":"MoGERNN: An Inductive Traffic Predictor for Unobserved Locations in Dynamic Sensing Networks","date":"2025-01-21","arxiv_id":"2501.12281","repositories_listed":1,"syntology":null},{"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/a-multi-modal-deep-learning-framework-for-pan","slug":"a-multi-modal-deep-learning-framework-for-pan","title":"A Multi-Modal Deep Learning Framework for Pan-Cancer Prognosis","date":"2025-01-13","arxiv_id":"2501.07016","repositories_listed":1,"syntology":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/tamer-a-test-time-adaptive-moe-driven","slug":"tamer-a-test-time-adaptive-moe-driven","title":"TAMER: A Test-Time Adaptive MoE-Driven Framework for EHR Representation Learning","date":"2025-01-10","arxiv_id":"2501.05661","repositories_listed":1,"syntology":null},{"url":"/paper/limoe-mixture-of-lidar-representation","slug":"limoe-mixture-of-lidar-representation","title":"LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes","date":"2025-01-07","arxiv_id":"2501.04004","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-experts-graph-transformers-for","slug":"mixture-of-experts-graph-transformers-for","title":"Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection","date":"2025-01-06","arxiv_id":"2501.03432","repositories_listed":1,"syntology":null},{"url":"/paper/superposition-in-transformers-a-novel-way-of","slug":"superposition-in-transformers-a-novel-way-of","title":"Superposition in Transformers: A Novel Way of Building Mixture of Experts","date":"2024-12-31","arxiv_id":"2501.00530","repositories_listed":1,"syntology":null},{"url":"/paper/unirestorer-universal-image-restoration-via","slug":"unirestorer-universal-image-restoration-via","title":"UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper Granularity","date":"2024-12-28","arxiv_id":"2412.20157","repositories_listed":1,"syntology":null},{"url":"/paper/askchart-universal-chart-understanding","slug":"askchart-universal-chart-understanding","title":"AskChart: Universal Chart Understanding through Textual Enhancement","date":"2024-12-26","arxiv_id":"2412.19146","repositories_listed":1,"syntology":null},{"url":"/paper/big-moe-bypass-isolated-gating-moe-for","slug":"big-moe-bypass-isolated-gating-moe-for","title":"BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing","date":"2024-12-24","arxiv_id":"2412.18065","repositories_listed":1,"syntology":null},{"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/a-survey-on-inference-optimization-techniques","slug":"a-survey-on-inference-optimization-techniques","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","date":"2024-12-18","arxiv_id":"2412.14219","repositories_listed":1,"syntology":null},{"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/seke-specialised-experts-for-keyword","slug":"seke-specialised-experts-for-keyword","title":"SEKE: Specialised Experts for Keyword Extraction","date":"2024-12-18","arxiv_id":"2412.14087","repositories_listed":1,"syntology":null},{"url":"/paper/smose-sparse-mixture-of-shallow-experts-for","slug":"smose-sparse-mixture-of-shallow-experts-for","title":"SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks","date":"2024-12-17","arxiv_id":"2412.13053","repositories_listed":1,"syntology":null},{"url":"/paper/daop-data-aware-offloading-and-predictive-pre","slug":"daop-data-aware-offloading-and-predictive-pre","title":"DAOP: Data-Aware Offloading and Predictive Pre-Calculation for Efficient MoE Inference","date":"2024-12-16","arxiv_id":"2501.10375","repositories_listed":1,"syntology":null},{"url":"/paper/towards-adversarial-robustness-of-model-level","slug":"towards-adversarial-robustness-of-model-level","title":"Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation","date":"2024-12-16","arxiv_id":"2412.11608","repositories_listed":1,"syntology":null},{"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/llama-3-meets-moe-efficient-upcycling","slug":"llama-3-meets-moe-efficient-upcycling","title":"Llama 3 Meets MoE: Efficient Upcycling","date":"2024-12-13","arxiv_id":"2412.09952","repositories_listed":1,"syntology":null},{"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/mixture-of-experts-meets-decoupled-message","slug":"mixture-of-experts-meets-decoupled-message","title":"Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification","date":"2024-12-11","arxiv_id":"2412.08193","repositories_listed":1,"syntology":null},{"url":"/paper/object-detection-using-event-camera-a-moe","slug":"object-detection-using-event-camera-a-moe","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","date":"2024-12-09","arxiv_id":"2412.06647","repositories_listed":1,"syntology":null},{"url":"/paper/rsunivlm-a-unified-vision-language-model-for","slug":"rsunivlm-a-unified-vision-language-model-for","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","date":"2024-12-07","arxiv_id":"2412.05679","repositories_listed":1,"syntology":null},{"url":"/paper/same-learning-generic-language-guided-visual","slug":"same-learning-generic-language-guided-visual","title":"SAME: Learning Generic Language-Guided Visual Navigation with State-Adaptive Mixture of Experts","date":"2024-12-07","arxiv_id":"2412.05552","repositories_listed":1,"syntology":null},{"url":"/paper/monet-mixture-of-monosemantic-experts-for","slug":"monet-mixture-of-monosemantic-experts-for","title":"Monet: Mixture of Monosemantic Experts for Transformers","date":"2024-12-05","arxiv_id":"2412.04139","repositories_listed":1,"syntology":null},{"url":"/paper/condense-don-t-just-prune-enhancing","slug":"condense-don-t-just-prune-enhancing","title":"Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning","date":"2024-11-26","arxiv_id":"2412.00069","repositories_listed":1,"syntology":null},{"url":"/paper/h-3-fusion-helpful-harmless-honest-fusion-of","slug":"h-3-fusion-helpful-harmless-honest-fusion-of","title":"$H^3$Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs","date":"2024-11-26","arxiv_id":"2411.17792","repositories_listed":1,"syntology":null},{"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/cnmbert-a-model-for-hanyu-pinyin-abbreviation","slug":"cnmbert-a-model-for-hanyu-pinyin-abbreviation","title":"CNMBERT: A Model for Converting Hanyu Pinyin Abbreviations to Chinese Characters","date":"2024-11-18","arxiv_id":"2411.11770","repositories_listed":1,"syntology":null},{"url":"/paper/awaker2-5-vl-stably-scaling-mllms-with","slug":"awaker2-5-vl-stably-scaling-mllms-with","title":"Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts","date":"2024-11-16","arxiv_id":"2411.10669","repositories_listed":1,"syntology":null}],"record_sha256":"f1ab186aaca38a874365c52c6c40e058a4d99326c4211bb10b36574279327cc8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}