[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82666-en":3,"doc-seo-82666-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82666,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Stable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates","Quantum Fast-Weight Programmers (QFWPs) store temporal information in dynamically programmed variational-circuit parameters instead of nonlinear recurrent hidden states, enabling practical quantum sequence modeling. Self-Modulating QFWP further uses input-dependent gates for both new fast-weight updates and accumulated fast-weight state, yet the original unbounded old-state multiplier can diverge for long sequences. This work introduces a bounded old-state modulation rule using a sign-preserving tanh gate on the recurrent memory branch only, leaving additive and new-update modulation unchanged.","arXiv :2607 .02363v1 [ quant-ph] 2 Jul 2026  \nStable Self-Modulating Quantum Fast-Weight Programmers with Bounded Memory Gates  \nKuo-Chung Peng 1[0009−0001−8342−2481], Jiun-Cheng Jiang 1[0009−0005−1134−4962], Chun-Hua Lin 1[0009−0002−4383−0453], Yifeng Peng2[0009−0007−3306−9417], Junghoon Justin Park3[0000−0001−8982−0387], Huan-Hsin Tseng4[0000−0001−9544−4226], Hsin-Yi Lin4[0000−0001−5731−2353], Kuan-Cheng Chen5[0000−0002−6575−7034], Chen-Yu Liu 1[0000−0002−5437−5188], Shinjae Yoo4[0000−0003−4378−6448], and Samuel Yen-Chi Chen6[0000−0003−0114−4826]  \n1 National Taiwan University, Taiwan  \n2 Stevens Institute of Technology, NJ, USA  \n3 Seoul National University, Korea  \n4 Brookhaven National Laboratory, NY, USA  \n5 Imperial College London, UK  \n6 Wells Fargo, NY, USA  \n[ycchen1989@ieee.org](ycchen1989@ieee.org)  \nAbstract. Quantum Fast-Weight Programmers (QFWPs) store temporal information in dynamically programmed variational-circuit parameters rather than in nonlinear recurrent hidden states, offering a practical route to quantum sequence modeling. Self-Modulating QFWP improves this framework by using input-dependent gates for both new fast-weight updates and the accumulated fast-weight state, but its unbounded oldstate multiplier can diverge in long-sequence regimes. We propose abounded old-state modulation rule that applies a sign-preserving tanh gate only to the recurrent memory branch while leaving the additive update and new-update modulation unchanged. We evaluate standard QFWP, full Self-Modulating QFWP, Only-New, and Only-Old variantson two CUDA-Q quantum-dynamics forecasting tasks and on Milan SMS telecommunication activity prediction. The quantum-dynamics results show that old-state modulation is the most consistent source of improvement over Standard QFWP, and that bounding the old-state gate removes long-sequence divergence while improving aggregate robustness. On Milan SMS forecasting, the original unbounded Self-Modulating QFWP converges across the tested grid and shows its clearest gains at longer input windows, with behavior close to the Only-Old ablation. These findings identify accumulated-memory modulation as the key mechanism of Self-Modulating QFWP and bounded old-state gating as a targeted stabilization strategy.  \nKeywords: Quantum Fast-Weight Programmer · Self-Modulating QFWP  \n· Bounded Memory Gate · Quantum Time-Series Forecasting  \n2 K.-C. Peng et al.  \n1 Introduction  \nQuantum sequence models have become a promising direction for learning temporal dependencies with hybrid quantum–classical architectures[6, 1 ,3] . A representative starting point is the Quantum Long Short-Term Memory (QLSTM) model, which replaces parts of the classical LSTM cell with variational quantum circuits and has shown promising empirical behavior on temporal learning tasks [9,7 ,31 , 10] . These studies suggest that variational quantum circuits can act as compact nonlinear processors for temporal data, but recurrent quantum models still inherit a central limitation during training. Models with nonlinear recurrence must propagate gradients through a time-ordered nonlinear state evolution.  \nQuantum Fast Weight Programmers (QFWPs) were introduced to address this bottleneck by moving memory from a recurrent hidden state into dynamically programmed circuit parameters [8] . In QFWP, a classical slow programmer reads each input and generates an update to the parameters of a variational quantum circuit, which acts as the fast programmer. Because the temporal state is represented by accumulated fast weights rather than by a nonlinear recurrent hidden state, the model avoids backpropagation through time (BPTT) across a quantum recurrent cell and admits a simpler, more parallelizable gradient path [24] . This makes QFWP an attractive framework for quantum time-series prediction and sequential control, where circuit-evaluation cost and gradient depth are major practical constraints.  \nThe recent Self-Modulating QFWP extends this framewo","cbCaiftCGRGtMNlu","https://ap.wps.com/l/cbCaiftCGRGtMNlu","pdf",1105619,1,16,"English","en",105,"# Abstract\n# Introduction","[{\"question\":\"What problem does Self-Modulating QFWP address, and what limitation remains?\",\"answer\":\"It improves QFWP by adding input-dependent multiplicative modulation for both new updates and accumulated fast-weight state. The original old-state multiplier is unbounded, which can diverge in long-sequence regimes.\"},{\"question\":\"What is the key architectural change in the proposed method?\",\"answer\":\"The method introduces a bounded old-state modulation rule by applying a sign-preserving tanh gate to the recurrent memory branch. Additive update and new-update modulation remain unchanged.\"},{\"question\":\"How is the proposed approach evaluated and what do the results indicate?\",\"answer\":\"Experiments compare Standard QFWP, full Self-Modulating QFWP, and Only-New/Only-Old variants on CUDA-Q quantum-dynamics forecasting tasks and on Milan SMS telecommunication activity prediction. Old-state modulation is the most consistent improvement source, and bounding the old-state gate removes long-sequence divergence while improving robustness.\"}]",1784182163,40,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"stable-self-modulating-quantum-fast-weight-programmers-with-bounded-memory-gates","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/stable-self-modulating-quantum-fast-weight-programmers-with-bounded-memory-gates/82666/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does Self-Modulating QFWP address, and what limitation remains?","Question",{"text":75,"@type":76},"It improves QFWP by adding input-dependent multiplicative modulation for both new updates and accumulated fast-weight state. The original old-state multiplier is unbounded, which can diverge in long-sequence regimes.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the key architectural change in the proposed method?",{"text":80,"@type":76},"The method introduces a bounded old-state modulation rule by applying a sign-preserving tanh gate to the recurrent memory branch. Additive update and new-update modulation remain unchanged.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the proposed approach evaluated and what do the results indicate?",{"text":84,"@type":76},"Experiments compare Standard QFWP, full Self-Modulating QFWP, and Only-New/Only-Old variants on CUDA-Q quantum-dynamics forecasting tasks and on Milan SMS telecommunication activity prediction. Old-state modulation is the most consistent improvement source, and bounding the old-state gate removes long-sequence divergence while improving robustness.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":28,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]