[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82964-en":3,"doc-seo-82964-105":30,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82964,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","EquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation","Foundation machine-learning force fields (MLFFs) such as MACE-MP-0 and UMA achieve near-DFT accuracy over broad chemical space, yet assume equilibrium ground-state physics and cannot natively represent externally induced electronic changes like charging, applied fields, or excitation. EquiFiLM introduces a lightweight, per-layer Feature-wise Linear Modulation (FiLM) adapter that adds continuous charge conditioning to any equivariant foundation MLFF while preserving E(3)-equivariance exactly. On charged liquid water, EquiFiLM substantially reduces force and per-atom energy errors and remains stable in molecular dynamics.","arXiv :2607 .05559v 1 [ cs .LG] 6 Jul 2026  \nEquiFiLM: Charge-Conditioned Equivariant Force Fields via Feature-wise Linear Modulation  \nSamuel Sahel-Schackis 1 ,2 ,3∗, Ken-ichi Nomura4 , Aiichiro Nakano4 , Matthias F. Kling3 ,5 , Thomas Linker2 ,3  \n1Department of Physics, Stanford University  \n2Linac Coherent Light Source, SLAC National Accelerator Laboratory  \n3 Stanford PULSE Institute, SLAC National Accelerator Laboratory  \n4 Collaboratory for Advanced Computing and Simulation, University of Southern California  \n5Department of Applied Physics, Stanford University  \n∗ [samss@slac.stanford.edu](samss@slac.stanford.edu)  \nAbstract  \nFoundation machine learning force fields (MLFFs) such as MACE-MP-0 and UMA cover broad chemical space at near density functional theory (DFT) accuracy.  \nHowever, they assume equilibrium ground-state physics and do not natively handle externally induced changes to the electronic state, such as charging, applied fields, or electronic excitation, which limits their use for driven processes such as photoexcitation and charge injection. We propose EquiFiLM, a lightweight extension that adds continuous external conditioning to any equivariant foundation MLFF via a per-layer Feature-wise Linear Modulation (FiLM) block, learning externally driven changes to the potential energy surface from minimal training data. The block modulates only scalar channels and preserves E(3)-equivariance exactly.  \nWe demonstrate the recipe on charged liquid water with the foundation model MACE-MatPES as the backbone, yielding E-MACE. On the four training charges, E-MACE delivers a 3.1 × reduction in force RMSE (21 .3 to 6.96 meV/Å) and a 61 × reduction in per-atom energy RMSE (6 .1 to 0.1 meV/atom) over a baseline without EquiFiLM trained on the same data, at indistinguishable inference cost.  \nAcross seven held-out interpolation and extrapolation charges, force RMSE stays within 18 − 61 meV/Å and energy RMSE within 0.7 − 5.4 meV/atom. The model runs stable molecular dynamics across the full range tested and predicts the chargedependent first-shell response of the reduced pair distribution function probed by ultrafast electron diffraction. Adding this conditioning axis to the foundation requires only a few thousand DFT-labeled frames, against the ≈ 108 structures of a charge-aware foundation trained from scratch. The recipe is backbone-and conditioning-agnostic: it applies without architectural change to any equivariant MLFF with scalar interaction-layer channels.  \nPreprint.  \n1 Introduction  \nAtomistic simulation under continuous external control, conditioned by total charge, temperature, applied field, hydrostatic pressure or doping fraction, is central to electrochemistry, photochemistry, doped-materials design and many other practical applications. Foundation machine-learning force fields (MLFFs) such as MACE-MP-0 [1] and UMA [2] now reach near-DFT accuracy across most of the periodic table, alongside other state-of-the-art interatomic potentials including the strictly equivariant architectures MACE-MatPES [3], EquiformerV3 [4], eSEN [5] and SevenNet-Omni [6], and the non-equivariant or rotationally-unconstrained alternatives Orb-v3 [7] and PET-MAD [8] . In their standard formulations, these condition exclusively on atomic positions and species. The model has no input pathway through which a per-graph external scalar can propagate, so two systems that share a geometry but differ in their conditioning produce bit-identical predictions.  \nCurrent approaches to bringing external conditioning into MLFFs trade off generalization against added architectural and training cost. A foundation MLFF that ignores charge degrades quickly as charge is added, with force errors rising into the hundreds of meV/Å on charged liquid water (Figure 1) . Per-state specialists (one model per charge) reach acceptable accuracy on their training charge but cannot generalize to unseen charges (Appendix A) . Physics-grounded charge-aware foundati","cbCainDmcSmy2bU0","https://ap.wps.com/l/cbCainDmcSmy2bU0","pdf",4511795,6,1,23,"English","en",105,"# Abstract\n# Introduction\n## Motivation: limitations of standard foundation MLFFs\n## Proposed method: EquiFiLM via per-layer FiLM\n## Demonstration on charged liquid water","[{\"question\":\"What problem does EquiFiLM address in foundation MLFFs?\",\"answer\":\"Standard equivariant foundation MLFFs condition only on atomic positions and species, so their predictions do not change when the system’s electronic state is externally modified (e.g., by charging or applied fields). EquiFiLM adds a conditioning pathway to capture such changes.\"},{\"question\":\"How does EquiFiLM incorporate external conditioning into an equivariant MLFF?\",\"answer\":\"EquiFiLM uses a per-layer Feature-wise Linear Modulation (FiLM) block whose gating parameters are generated by a per-graph MLP from the conditioning input. The modulation affects only scalar channels and preserves E(3)-equivariance exactly.\"},{\"question\":\"What experimental or simulation results are reported for charged liquid water?\",\"answer\":\"Applied to the MACE-MatPES backbone, the resulting E-MACE model greatly reduces force RMSE and per-atom energy RMSE on the training charges, matches accuracy comparable to a larger charge-aware foundation fine-tuned on the same data, and generalizes across interpolation and extrapolation charges while running stable molecular dynamics.\"}]",1784184358,58,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"equifilm-charge-conditioned-equivariant-force-fields-via-feature-wise-linear-modulation","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/equifilm-charge-conditioned-equivariant-force-fields-via-feature-wise-linear-modulation/82964/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does EquiFiLM address in foundation MLFFs?","Question",{"text":76,"@type":77},"Standard equivariant foundation MLFFs condition only on atomic positions and species, so their predictions do not change when the system’s electronic state is externally modified (e.g., by charging or applied fields). EquiFiLM adds a conditioning pathway to capture such changes.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does EquiFiLM incorporate external conditioning into an equivariant MLFF?",{"text":81,"@type":77},"EquiFiLM uses a per-layer Feature-wise Linear Modulation (FiLM) block whose gating parameters are generated by a per-graph MLP from the conditioning input. The modulation affects only scalar channels and preserves E(3)-equivariance exactly.",{"name":83,"@type":74,"acceptedAnswer":84},"What experimental or simulation results are reported for charged liquid water?",{"text":85,"@type":77},"Applied to the MACE-MatPES backbone, the resulting E-MACE model greatly reduces force RMSE and per-atom energy RMSE on the training charges, matches accuracy comparable to a larger charge-aware foundation fine-tuned on the same data, and generalizes across interpolation and extrapolation charges while running stable molecular dynamics.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]