https://chiosa.app/papers/dtca-denoising-token-credit-assignment-for-reinforcement-learning-in-diffusion-language-models-2610-35201Chiosaen2026-10-29T14:37:00ZToken-level credit improves diffusion model math traininghttps://chiosa.app/papers/dtca-denoising-token-credit-assignment-for-reinforcement-learning-in-diffusion-language-models-2610-35201?lang=itChiosait2026-10-29T14:37:00ZI crediti assegnati ai token migliorano l’addestramento matematico dei modelli a diffusionehttps://chiosa.app/papers/dtca-denoising-token-credit-assignment-for-reinforcement-learning-in-diffusion-language-models-2610-35201?lang=esChiosaes2026-10-29T14:37:00ZEl crédito por token mejora el entrenamiento matemático de modelos de difusiónhttps://chiosa.app/papers/dtca-denoising-token-credit-assignment-for-reinforcement-learning-in-diffusion-language-models-2610-35201?lang=frChiosafr2026-10-29T14:37:00ZLes crédits par token améliorent l’entraînement mathématique des modèles à diffusionhttps://chiosa.app/papers/efficient-streaming-audio-visual-target-speaker-extraction-for-real-world-acoustic-scenes-2610-32749Chiosaen2026-10-29T14:37:00ZA broader speech test and a single-pass extractorhttps://chiosa.app/papers/efficient-streaming-audio-visual-target-speaker-extraction-for-real-world-acoustic-scenes-2610-32749?lang=itChiosait2026-10-29T14:37:00ZUn test più ampio per le voci e un estrattore a passaggio singolohttps://chiosa.app/papers/efficient-streaming-audio-visual-target-speaker-extraction-for-real-world-acoustic-scenes-2610-32749?lang=esChiosaes2026-10-29T14:37:00ZUna prueba más amplia del habla y un extractor de una pasadahttps://chiosa.app/papers/efficient-streaming-audio-visual-target-speaker-extraction-for-real-world-acoustic-scenes-2610-32749?lang=frChiosafr2026-10-29T14:37:00ZUn test vocal plus large et un extracteur en un seul passagehttps://chiosa.app/papers/omnishowcase-omnidirectional-subject-consistent-video-generation-from-multi-view-images-2610-35684Chiosaen2026-10-29T14:37:00ZA video method uses 3D shape to keep subjects consistenthttps://chiosa.app/papers/omnishowcase-omnidirectional-subject-consistent-video-generation-from-multi-view-images-2610-35684?lang=esChiosaes2026-10-29T14:37:00ZUn método de video usa la forma 3D para mantener la coherencia de los sujetoshttps://chiosa.app/papers/omnishowcase-omnidirectional-subject-consistent-video-generation-from-multi-view-images-2610-35684?lang=frChiosafr2026-10-29T14:37:00ZUne méthode vidéo utilise la 3D pour préserver la cohérence des sujetshttps://chiosa.app/papers/sensorimotor-alignment-a-platonic-proxy-for-embodied-policy-success-2610-31670Chiosaen2026-10-29T14:37:00ZA motion-alignment score tracks robot models’ task successhttps://chiosa.app/papers/sensorimotor-alignment-a-platonic-proxy-for-embodied-policy-success-2610-31670?lang=itChiosait2026-10-29T14:37:00ZUn punteggio di allineamento ai movimenti segue il successo dei modelli roboticihttps://chiosa.app/papers/sensorimotor-alignment-a-platonic-proxy-for-embodied-policy-success-2610-31670?lang=esChiosaes2026-10-29T14:37:00ZUna puntuación de alineación motriz se relaciona con el éxito en tareas robóticashttps://chiosa.app/papers/sensorimotor-alignment-a-platonic-proxy-for-embodied-policy-success-2610-31670?lang=frChiosafr2026-10-29T14:37:00ZUn score d’alignement des mouvements suit la réussite des robotshttps://chiosa.app/papers/tao-tool-aware-joint-scheduling-for-llm-based-agentic-serving-2610-37230Chiosaen2026-10-29T14:37:00ZA scheduler uses tool timing to place waiting AI sessionshttps://chiosa.app/papers/tao-tool-aware-joint-scheduling-for-llm-based-agentic-serving-2610-37230?lang=itChiosait2026-10-29T14:37:00ZUno scheduler usa i tempi degli strumenti per assegnare le sessioni AI in attesahttps://chiosa.app/papers/tao-tool-aware-joint-scheduling-for-llm-based-agentic-serving-2610-37230?lang=esChiosaes2026-10-29T14:37:00ZUn planificador asigna sesiones de IA según los tiempos de las herramientashttps://chiosa.app/papers/tao-tool-aware-joint-scheduling-for-llm-based-agentic-serving-2610-37230?lang=frChiosafr2026-10-29T14:37:00ZUn planificateur utilise le calendrier des outils pour placer les sessions d’IA en attentehttps://chiosa.app/papers/ask-your-advisor-learning-when-to-consult-stronger-models-in-agentic-systems-2610-13870Chiosaen2026-10-29T11:00:41ZARIA learns when a task agent should ask for stronger advicehttps://chiosa.app/papers/bellowskv-one-latent-for-many-layers-expanded-on-demand-2610-35023Chiosaen2026-10-29T11:00:41ZOne shared cache representation serves several model layershttps://chiosa.app/papers/bellowskv-one-latent-for-many-layers-expanded-on-demand-2610-35023?lang=itChiosait2026-10-29T11:00:41ZUna rappresentazione condivisa della cache serve più layer del modellohttps://chiosa.app/papers/bellowskv-one-latent-for-many-layers-expanded-on-demand-2610-35023?lang=esChiosaes2026-10-29T11:00:41ZUna representación de caché compartida sirve a varias capas del modelohttps://chiosa.app/papers/bellowskv-one-latent-for-many-layers-expanded-on-demand-2610-35023?lang=frChiosafr2026-10-29T11:00:41ZUne représentation de cache partagée pour plusieurs coucheshttps://chiosa.app/papers/card-contact-anchored-retargeting-for-dexterous-manipulation-2610-36539Chiosaen2026-10-29T11:00:41ZContact targets help robot hands reproduce human touchhttps://chiosa.app/papers/card-contact-anchored-retargeting-for-dexterous-manipulation-2610-36539?lang=itChiosait2026-10-29T11:00:41ZGli obiettivi di contatto aiutano le mani robotiche a riprodurre il tocco umanohttps://chiosa.app/papers/card-contact-anchored-retargeting-for-dexterous-manipulation-2610-36539?lang=esChiosaes2026-10-29T11:00:41ZLos objetivos de contacto ayudan a las manos robóticas a reproducir el tacto humanohttps://chiosa.app/papers/card-contact-anchored-retargeting-for-dexterous-manipulation-2610-36539?lang=frChiosafr2026-10-29T11:00:41ZDes cibles de contact aident les mains robotiques à reproduire le toucher humainhttps://chiosa.app/papers/copying-is-not-grounding-training-faithful-long-form-rag-with-authored-sentence-credit-2610-18442Chiosaen2026-10-29T11:00:41ZA sentence-level reward helps retrieval models ground their own writinghttps://chiosa.app/papers/copying-is-not-grounding-training-faithful-long-form-rag-with-authored-sentence-credit-2610-18442?lang=itChiosait2026-10-29T11:00:41ZUna ricompensa per frase aiuta i modelli RAG a fondare ciò che scrivonohttps://chiosa.app/papers/copying-is-not-grounding-training-faithful-long-form-rag-with-authored-sentence-credit-2610-18442?lang=esChiosaes2026-10-29T11:00:41ZUna recompensa por oración ayuda a los modelos de recuperación a fundamentar lo que escribenhttps://chiosa.app/papers/copying-is-not-grounding-training-faithful-long-form-rag-with-authored-sentence-credit-2610-18442?lang=frChiosafr2026-10-29T11:00:41ZUne récompense par phrase aide les modèles RAG à étayer leurs formulationshttps://chiosa.app/papers/decision-models-as-judges-for-hallucination-detection-2610-37229Chiosaen2026-10-29T11:00:41ZDecision models catch some hallucinations, but confidence can misleadhttps://chiosa.app/papers/decision-models-as-judges-for-hallucination-detection-2610-37229?lang=itChiosait2026-10-29T11:00:41ZI modelli decisionali rilevano alcune allucinazioni, ma la confidenza può ingannarehttps://chiosa.app/papers/decision-models-as-judges-for-hallucination-detection-2610-37229?lang=esChiosaes2026-10-29T11:00:41ZLos modelos de decisión detectan algunas alucinaciones, pero la confianza puede engañarhttps://chiosa.app/papers/doc2harness-benchmarking-llms-on-long-horizon-harness-engineering-of-coding-agents-2610-20344Chiosaen2026-10-29T11:00:41ZTests reveal gaps in models that build coding-agent softwarehttps://chiosa.app/papers/doc2harness-benchmarking-llms-on-long-horizon-harness-engineering-of-coding-agents-2610-20344?lang=itChiosait2026-10-29T11:00:41ZI test rivelano lacune nei modelli che costruiscono software per agentihttps://chiosa.app/papers/doc2harness-benchmarking-llms-on-long-horizon-harness-engineering-of-coding-agents-2610-20344?lang=esChiosaes2026-10-29T11:00:41ZPruebas revelan las carencias de los modelos que crean software para agentes de programaciónhttps://chiosa.app/papers/doc2harness-benchmarking-llms-on-long-horizon-harness-engineering-of-coding-agents-2610-20344?lang=frChiosafr2026-10-29T11:00:41ZDes tests révèlent les lacunes des modèles qui construisent le logiciel des agentshttps://chiosa.app/papers/execdiffuser-closing-the-sample-to-execution-gap-in-diffusion-planning-2610-36837Chiosaen2026-10-29T11:00:41ZBetter driving options do not always lead to better choiceshttps://chiosa.app/papers/execdiffuser-closing-the-sample-to-execution-gap-in-diffusion-planning-2610-36837?lang=itChiosait2026-10-29T11:00:41ZOpzioni di guida migliori non portano sempre a scelte migliorihttps://chiosa.app/papers/execdiffuser-closing-the-sample-to-execution-gap-in-diffusion-planning-2610-36837?lang=esChiosaes2026-10-29T11:00:41ZMejores opciones de conducción no siempre llevan a mejores eleccioneshttps://chiosa.app/papers/execdiffuser-closing-the-sample-to-execution-gap-in-diffusion-planning-2610-36837?lang=frChiosafr2026-10-29T11:00:41ZDe meilleures trajectoires ne garantissent pas un meilleur choixhttps://chiosa.app/papers/from-detection-to-decision-calibration-and-deferral-for-prompt-injection-detection-2610-20907Chiosaen2026-10-29T11:00:41ZAttack scores alone do not settle prompt-injection decisionshttps://chiosa.app/papers/from-detection-to-decision-calibration-and-deferral-for-prompt-injection-detection-2610-20907?lang=itChiosait2026-10-29T11:00:41ZI punteggi di attacco non bastano per decidere sulla prompt injectionhttps://chiosa.app/papers/from-detection-to-decision-calibration-and-deferral-for-prompt-injection-detection-2610-20907?lang=esChiosaes2026-10-29T11:00:41ZLas puntuaciones de ataque no bastan para decidir sobre la inyección de promptshttps://chiosa.app/papers/from-detection-to-decision-calibration-and-deferral-for-prompt-injection-detection-2610-20907?lang=frChiosafr2026-10-29T11:00:41ZLes scores seuls ne tranchent pas les décisions face aux injections de prompthttps://chiosa.app/papers/generative-representation-learning-for-scalable-latent-tokenization-2610-20533Chiosaen2026-10-29T11:00:41ZA new image tokenizer scales while resisting shortcut featureshttps://chiosa.app/papers/generative-representation-learning-for-scalable-latent-tokenization-2610-20533?lang=itChiosait2026-10-29T11:00:41ZUn nuovo tokenizer di immagini scala e resiste alle scorciatoiehttps://chiosa.app/papers/generative-representation-learning-for-scalable-latent-tokenization-2610-20533?lang=frChiosafr2026-10-29T11:00:41ZUn tokenizer d’images passe à l’échelle en résistant aux raccourcishttps://chiosa.app/papers/periodic-weak-spots-phase-sensitivity-from-chunked-kv-cache-compression-2609-36322Chiosaen2026-10-29T11:00:41ZToken position can weaken retrieval from compressed memoryhttps://chiosa.app/papers/programgym-scaling-training-environments-for-long-horizon-program-reproduction-agents-2610-13395Chiosaen2026-10-29T11:00:41ZProgramGym trains agents to rebuild programs from behaviorhttps://chiosa.app/papers/right-click-wrong-box-grading-gui-grounding-by-what-a-click-does-2610-36831Chiosaen2026-10-29T11:00:41ZBox scores miss clicks that still achieve the requested actionhttps://chiosa.app/papers/right-click-wrong-box-grading-gui-grounding-by-what-a-click-does-2610-36831?lang=itChiosait2026-10-29T11:00:41ZI punteggi basati sui riquadri ignorano clic che eseguono l’azione richiestahttps://chiosa.app/papers/right-click-wrong-box-grading-gui-grounding-by-what-a-click-does-2610-36831?lang=esChiosaes2026-10-29T11:00:41ZLas puntuaciones por cajas pasan por alto clics que realizan la acción solicitadahttps://chiosa.app/papers/rsigen-reciprocal-self-improvement-for-agentic-visual-generation-2610-18688Chiosaen2026-10-29T11:00:41ZRSIgen links learning between image planners and generatorshttps://chiosa.app/papers/rsigen-reciprocal-self-improvement-for-agentic-visual-generation-2610-18688?lang=itChiosait2026-10-29T11:00:41ZRSIgen coordina l’apprendimento tra chi pianifica e chi genera immaginihttps://chiosa.app/papers/rsigen-reciprocal-self-improvement-for-agentic-visual-generation-2610-18688?lang=esChiosaes2026-10-29T11:00:41ZRSIgen conecta el aprendizaje entre agentes planificadores y generadores de imágeneshttps://chiosa.app/papers/rsigen-reciprocal-self-improvement-for-agentic-visual-generation-2610-18688?lang=frChiosafr2026-10-29T11:00:41ZRSIgen relie l’apprentissage des agents et des générateurs d’imageshttps://chiosa.app/papers/simvta-simulation-grounded-video-trajectory-alignment-for-driving-world-action-models-2610-13781Chiosaen2026-10-29T11:00:41ZRendered futures give driving models feedback on new pathshttps://chiosa.app/papers/tapestry-a-single-backbone-for-video-generation-and-robot-control-2610-36823Chiosaen2026-10-29T11:00:41ZA video model can guide robot actions without generating videohttps://chiosa.app/papers/tapestry-a-single-backbone-for-video-generation-and-robot-control-2610-36823?lang=esChiosaes2026-10-29T11:00:41ZUn modelo de video puede guiar acciones robóticas sin generar videohttps://chiosa.app/papers/tapestry-a-single-backbone-for-video-generation-and-robot-control-2610-36823?lang=frChiosafr2026-10-29T11:00:41ZUn modèle vidéo peut guider les actions d’un robot sans générer de vidéohttps://chiosa.app/papers/tulva-practical-asynchronous-threshold-fhe-2610-20521Chiosaen2026-10-29T11:00:41ZTulva lets enough committee members decrypt without being online togetherhttps://chiosa.app/papers/tulva-practical-asynchronous-threshold-fhe-2610-20521?lang=itChiosait2026-10-29T11:00:41ZTulva permette ai partecipanti sufficienti di decifrare senza essere online insiemehttps://chiosa.app/papers/tulva-practical-asynchronous-threshold-fhe-2610-20521?lang=esChiosaes2026-10-29T11:00:41ZTulva permite descifrar a suficientes miembros sin conectarlos a la vezhttps://chiosa.app/papers/tulva-practical-asynchronous-threshold-fhe-2610-20521?lang=frChiosafr2026-10-29T11:00:41ZTulva permet à un nombre suffisant de membres du comité de déchiffrer sans être connectés ensemblehttps://chiosa.app/papers/unit-level-aggregation-breaks-coverage-in-causal-foundation-models-2610-22770Chiosaen2026-10-29T11:00:41ZJoint models improve intervals for group treatment effectshttps://chiosa.app/papers/unit-level-aggregation-breaks-coverage-in-causal-foundation-models-2610-22770?lang=esChiosaes2026-10-29T11:00:41ZModelos conjuntos mejoran los intervalos de efectos grupaleshttps://chiosa.app/papers/what-makes-world-action-models-generalize-an-empirical-study-of-test-time-future-modeling-2609-34981Chiosaen2026-10-29T11:00:41ZNoisy future video can guide robot actions in one passhttps://chiosa.app/papers/when-pointing-becomes-profiling-social-bias-and-refusal-in-text-steerable-visual-encoders-2610-35017Chiosaen2026-10-29T11:00:41ZA text-guided localizer can route attention by stereotypeshttps://chiosa.app/papers/when-pointing-becomes-profiling-social-bias-and-refusal-in-text-steerable-visual-encoders-2610-35017?lang=itChiosait2026-10-29T11:00:41ZUn localizzatore guidato dal testo può seguire stereotipihttps://chiosa.app/papers/when-pointing-becomes-profiling-social-bias-and-refusal-in-text-steerable-visual-encoders-2610-35017?lang=esChiosaes2026-10-29T11:00:41ZUn localizador guiado por texto puede dirigir la atención según estereotiposhttps://chiosa.app/papers/when-pointing-becomes-profiling-social-bias-and-refusal-in-text-steerable-visual-encoders-2610-35017?lang=frChiosafr2026-10-29T11:00:41ZUn localisateur guidé par le texte peut orienter l’attention selon des stéréotypeshttps://chiosa.app/papers/when-to-ask-for-help-a-decision-theoretic-account-and-measurement-standard-for-slow-module-scheduling-in-dual-2610-21160Chiosaen2026-10-29T11:00:41ZA value rule explains when slow corrections are worth their costhttps://chiosa.app/papers/when-to-ask-for-help-a-decision-theoretic-account-and-measurement-standard-for-slow-module-scheduling-in-dual-2610-21160?lang=itChiosait2026-10-29T11:00:41ZUna regola basata sul valore stabilisce quando convengono le correzioni lentehttps://chiosa.app/papers/when-to-ask-for-help-a-decision-theoretic-account-and-measurement-standard-for-slow-module-scheduling-in-dual-2610-21160?lang=esChiosaes2026-10-29T11:00:41ZUna regla basada en el valor indica cuándo compensa una corrección lentahttps://chiosa.app/papers/where-does-the-performance-go-understanding-and-recovering-performance-regressions-in-c-to-rust-translation-2610-23044Chiosaen2026-10-29T11:00:41ZPerfR turns recurring C-to-Rust slowdowns into reusable ruleshttps://chiosa.app/papers/where-does-the-performance-go-understanding-and-recovering-performance-regressions-in-c-to-rust-translation-2610-23044?lang=itChiosait2026-10-29T11:00:41ZPerfR trasforma i rallentamenti ricorrenti da C a Rust in regole riutilizzabilihttps://chiosa.app/papers/where-does-the-performance-go-understanding-and-recovering-performance-regressions-in-c-to-rust-translation-2610-23044?lang=esChiosaes2026-10-29T11:00:41ZPerfR convierte la lentitud recurrente de C a Rust en reglas reutilizableshttps://chiosa.app/papers/where-does-the-performance-go-understanding-and-recovering-performance-regressions-in-c-to-rust-translation-2610-23044?lang=frChiosafr2026-10-29T11:00:41ZPerfR transforme les ralentissements C-Rust récurrents en règles réutilisableshttps://chiosa.app/papers/habit-bench-evaluating-habit-induction-from-longitudinal-weak-evidence-in-agent-memory-2610-24520Chiosaen2026-10-28T19:27:59ZMemory systems struggle to turn user history into sound choiceshttps://chiosa.app/papers/habit-bench-evaluating-habit-induction-from-longitudinal-weak-evidence-in-agent-memory-2610-24520?lang=itChiosait2026-10-28T19:27:59ZI sistemi di memoria faticano a trasformare la cronologia in scelte validehttps://chiosa.app/papers/habit-bench-evaluating-habit-induction-from-longitudinal-weak-evidence-in-agent-memory-2610-24520?lang=esChiosaes2026-10-28T19:27:59ZA los sistemas de memoria les cuesta convertir el historial del usuario en buenas decisioneshttps://chiosa.app/papers/habit-bench-evaluating-habit-induction-from-longitudinal-weak-evidence-in-agent-memory-2610-24520?lang=frChiosafr2026-10-28T19:27:59ZLes systèmes de mémoire peinent à tirer de bons choix de l’historique utilisateurhttps://chiosa.app/papers/hy-nomas-towards-free-form-interactive-world-generation-2610-36729Chiosaen2026-10-28T19:27:59ZA video model carries scenes and actions across turnshttps://chiosa.app/papers/hy-nomas-towards-free-form-interactive-world-generation-2610-36729?lang=itChiosait2026-10-28T19:27:59ZUn modello video conserva scene e azioni tra più turnihttps://chiosa.app/papers/hy-nomas-towards-free-form-interactive-world-generation-2610-36729?lang=esChiosaes2026-10-28T19:27:59ZUn modelo de vídeo conserva escenas y acciones entre turnoshttps://chiosa.app/papers/hy-nomas-towards-free-form-interactive-world-generation-2610-36729?lang=frChiosafr2026-10-28T19:27:59ZUn modèle vidéo conserve scènes et actions au fil des tourshttps://chiosa.app/papers/memory-tax-dissecting-the-net-value-of-agent-memory-2610-34073Chiosaen2026-10-28T19:27:59ZMany agent memory systems lose to direct history searchhttps://chiosa.app/papers/memory-tax-dissecting-the-net-value-of-agent-memory-2610-34073?lang=itChiosait2026-10-28T19:27:59ZMolti sistemi di memoria per agenti perdono contro la ricerca direttahttps://chiosa.app/papers/memory-tax-dissecting-the-net-value-of-agent-memory-2610-34073?lang=esChiosaes2026-10-28T19:27:59ZMuchos sistemas de memoria para agentes pierden frente a la búsqueda directahttps://chiosa.app/papers/memory-tax-dissecting-the-net-value-of-agent-memory-2610-34073?lang=frChiosafr2026-10-28T19:27:59ZDe nombreux systèmes de mémoire pour agents sont battus par la recherche directe dans l’historiquehttps://chiosa.app/papers/representation-redistribution-in-sparse-autoencoders-2610-21240Chiosaen2026-10-28T19:27:59ZA method finds feature changes that recur across promptshttps://chiosa.app/papers/representation-redistribution-in-sparse-autoencoders-2610-21240?lang=itChiosait2026-10-28T19:27:59ZUn metodo individua cambiamenti delle caratteristiche che ricorrono tra prompthttps://chiosa.app/papers/representation-redistribution-in-sparse-autoencoders-2610-21240?lang=frChiosafr2026-10-28T19:27:59ZUne méthode repère les changements de caractéristiques récurrents dans les promptshttps://chiosa.app/papers/spatial-audio-generation-and-editing-with-executable-plans-and-self-distilling-transfusion-2610-34415Chiosaen2026-10-28T19:27:59ZOne framework plans and edits spatial audio sceneshttps://chiosa.app/papers/spatial-audio-generation-and-editing-with-executable-plans-and-self-distilling-transfusion-2610-34415?lang=itChiosait2026-10-28T19:27:59ZUn framework pianifica e modifica scene audio spazialihttps://chiosa.app/papers/spatial-audio-generation-and-editing-with-executable-plans-and-self-distilling-transfusion-2610-34415?lang=esChiosaes2026-10-28T19:27:59ZUn marco para planificar y editar escenas de audio espacialhttps://chiosa.app/papers/spatial-audio-generation-and-editing-with-executable-plans-and-self-distilling-transfusion-2610-34415?lang=frChiosafr2026-10-28T19:27:59ZUn cadre unique pour planifier et modifier des scènes audio spatialeshttps://chiosa.app/papers/work-agents-systems-capabilities-and-optimization-2610-35845Chiosaen2026-10-28T19:27:59ZA framework connects digital work agents to the work they must finishhttps://chiosa.app/papers/work-agents-systems-capabilities-and-optimization-2610-35845?lang=itChiosait2026-10-28T19:27:59ZUn quadro collega gli agenti digitali al lavoro da completarehttps://chiosa.app/papers/work-agents-systems-capabilities-and-optimization-2610-35845?lang=esChiosaes2026-10-28T19:27:59ZUn marco relaciona los agentes de trabajo digital con las tareas que deben completarhttps://chiosa.app/papers/work-agents-systems-capabilities-and-optimization-2610-35845?lang=frChiosafr2026-10-28T19:27:59ZUn cadre relie les agents numériques au travail qu’ils doivent acheverhttps://chiosa.app/papers/worldcast-world-consistent-character-video-generation-with-large-angle-camera-control-2610-33135Chiosaen2026-10-28T19:27:59ZWorldCast keeps characters coherent through large camera moveshttps://chiosa.app/papers/worldcast-world-consistent-character-video-generation-with-large-angle-camera-control-2610-33135?lang=esChiosaes2026-10-28T19:27:59ZWorldCast mantiene coherentes a los personajes con grandes movimientos de cámarahttps://chiosa.app/papers/worldcast-world-consistent-character-video-generation-with-large-angle-camera-control-2610-33135?lang=frChiosafr2026-10-28T19:27:59ZWorldCast préserve la cohérence des personnages lors des grands mouvements de camérahttps://chiosa.app/papers/balanced-state-subspaces-for-mamba-2-state-compression-2610-36617Chiosaen2026-10-28T15:18:30ZMamba-2 compression preserves jointly useful state directionshttps://chiosa.app/papers/balanced-state-subspaces-for-mamba-2-state-compression-2610-36617?lang=itChiosait2026-10-28T15:18:30ZLa compressione di Mamba-2 conserva direzioni utili dello statohttps://chiosa.app/papers/balanced-state-subspaces-for-mamba-2-state-compression-2610-36617?lang=esChiosaes2026-10-28T15:18:30ZLa compresión de Mamba-2 conserva direcciones útiles del estado que actúan en conjuntohttps://chiosa.app/papers/balanced-state-subspaces-for-mamba-2-state-compression-2610-36617?lang=frChiosafr2026-10-28T15:18:30ZLa compression de Mamba-2 préserve les directions d’état utiles conjointementhttps://chiosa.app/papers/benchmeup-building-software-engineering-benchmarks-from-natural-language-specifications-2610-37283Chiosaen2026-10-28T15:18:30ZBenchMeUp turns research specifications into runnable benchmarkshttps://chiosa.app/papers/benchmeup-building-software-engineering-benchmarks-from-natural-language-specifications-2610-37283?lang=itChiosait2026-10-28T15:18:30ZBenchMeUp trasforma specifiche di ricerca in benchmark eseguibilihttps://chiosa.app/papers/benchmeup-building-software-engineering-benchmarks-from-natural-language-specifications-2610-37283?lang=esChiosaes2026-10-28T15:18:30ZBenchMeUp convierte especificaciones de investigación en benchmarks ejecutableshttps://chiosa.app/papers/benchmeup-building-software-engineering-benchmarks-from-natural-language-specifications-2610-37283?lang=frChiosafr2026-10-28T15:18:30ZBenchMeUp transforme des spécifications de recherche en benchmarks exécutableshttps://chiosa.app/papers/can-discrete-tokens-serve-as-semantically-lossless-representations-of-visual-signals-2610-37662Chiosaen2026-10-28T15:18:30ZA visual tokenizer keeps discrete features informativehttps://chiosa.app/papers/can-discrete-tokens-serve-as-semantically-lossless-representations-of-visual-signals-2610-37662?lang=itChiosait2026-10-28T15:18:30ZUn tokenizer visivo mantiene informative le caratteristiche discretehttps://chiosa.app/papers/can-discrete-tokens-serve-as-semantically-lossless-representations-of-visual-signals-2610-37662?lang=esChiosaes2026-10-28T15:18:30ZUn tokenizador visual mantiene informativas las características discretashttps://chiosa.app/papers/can-test-time-memory-evolution-outperform-test-time-training-for-scientific-discovery-2610-32046Chiosaen2026-10-28T15:18:30ZExternal memory helps models find better mathematical solutionshttps://chiosa.app/papers/can-test-time-memory-evolution-outperform-test-time-training-for-scientific-discovery-2610-32046?lang=itChiosait2026-10-28T15:18:30ZLa memoria esterna aiuta i modelli a trovare soluzioni matematiche migliorihttps://chiosa.app/papers/can-test-time-memory-evolution-outperform-test-time-training-for-scientific-discovery-2610-32046?lang=esChiosaes2026-10-28T15:18:30ZLa memoria externa ayuda a encontrar mejores soluciones matemáticashttps://chiosa.app/papers/can-test-time-memory-evolution-outperform-test-time-training-for-scientific-discovery-2610-32046?lang=frChiosafr2026-10-28T15:18:30ZLa mémoire externe aide les modèles à trouver de meilleures solutions mathématiqueshttps://chiosa.app/papers/channel-selection-for-mixture-of-experts-decoding-needs-no-calibration-data-2610-37386Chiosaen2026-10-28T15:18:30ZFrozen MoE decoding can select channels without calibrationhttps://chiosa.app/papers/channel-selection-for-mixture-of-experts-decoding-needs-no-calibration-data-2610-37386?lang=itChiosait2026-10-28T15:18:30ZLa decodifica MoE congelata può selezionare canali senza calibrazionehttps://chiosa.app/papers/channel-selection-for-mixture-of-experts-decoding-needs-no-calibration-data-2610-37386?lang=frChiosafr2026-10-28T15:18:30ZLe décodage MoE figé peut sélectionner les canaux sans calibrationhttps://chiosa.app/papers/chronoreplay-one-answer-interface-is-not-enough-for-streaming-spatial-intelligence-2610-34283Chiosaen2026-10-28T15:18:30ZChronoReplay trains video models to answer spatial questionshttps://chiosa.app/papers/chronoreplay-one-answer-interface-is-not-enough-for-streaming-spatial-intelligence-2610-34283?lang=itChiosait2026-10-28T15:18:30ZChronoReplay addestra modelli video a rispondere a domande spazialihttps://chiosa.app/papers/chronoreplay-one-answer-interface-is-not-enough-for-streaming-spatial-intelligence-2610-34283?lang=esChiosaes2026-10-28T15:18:30ZChronoReplay entrena modelos de video para responder preguntas espacialeshttps://chiosa.app/papers/chronoreplay-one-answer-interface-is-not-enough-for-streaming-spatial-intelligence-2610-34283?lang=frChiosafr2026-10-28T15:18:30ZChronoReplay entraîne les modèles vidéo à répondre aux questions spatialeshttps://chiosa.app/papers/closed-loop-aware-planning-via-imitation-free-speed-scoring-for-end-to-end-autonomous-driving-2610-36079Chiosaen2026-10-28T15:18:30ZA driving model learns to follow requested speedshttps://chiosa.app/papers/closed-loop-aware-planning-via-imitation-free-speed-scoring-for-end-to-end-autonomous-driving-2610-36079?lang=itChiosait2026-10-28T15:18:30ZUn modello di guida impara a seguire la velocità richiestahttps://chiosa.app/papers/closed-loop-aware-planning-via-imitation-free-speed-scoring-for-end-to-end-autonomous-driving-2610-36079?lang=esChiosaes2026-10-28T15:18:30ZUn modelo de conducción aprende a seguir velocidades solicitadashttps://chiosa.app/papers/codecap-bench-can-code-serve-as-a-good-video-caption-2610-37341Chiosaen2026-10-28T15:18:30ZExecutable code can preserve details in video captionshttps://chiosa.app/papers/codecap-bench-can-code-serve-as-a-good-video-caption-2610-37341?lang=itChiosait2026-10-28T15:18:30ZIl codice eseguibile può conservare dettagli nelle descrizioni videohttps://chiosa.app/papers/codecap-bench-can-code-serve-as-a-good-video-caption-2610-37341?lang=esChiosaes2026-10-28T15:18:30ZEl código ejecutable puede conservar detalles en los pies de videohttps://chiosa.app/papers/codecap-bench-can-code-serve-as-a-good-video-caption-2610-37341?lang=frChiosafr2026-10-28T15:18:30ZLe code exécutable peut préserver les détails des légendes vidéohttps://chiosa.app/papers/concordat-typed-sessions-for-llm-agents-2610-37461Chiosaen2026-10-28T15:18:30ZA protocol gate stopped unconfirmed airline changes under pressurehttps://chiosa.app/papers/concordat-typed-sessions-for-llm-agents-2610-37461?lang=itChiosait2026-10-28T15:18:30ZUn blocco basato sul protocollo ha fermato le modifiche aeree senza conferma sotto pressionehttps://chiosa.app/papers/concordat-typed-sessions-for-llm-agents-2610-37461?lang=esChiosaes2026-10-28T15:18:30ZUn control de protocolo evitó cambios de aerolínea sin confirmar bajo presiónhttps://chiosa.app/papers/concordat-typed-sessions-for-llm-agents-2610-37461?lang=frChiosafr2026-10-28T15:18:30ZUn contrôle par protocole bloque les modifications aériennes sans accord sous pressionhttps://chiosa.app/papers/crisp-co-designing-pruning-and-scheduling-for-efficient-moe-inference-on-edge-servers-2610-37442Chiosaen2026-10-28T15:18:30ZCRISP coordinates pruning and scheduling for edge MoEhttps://chiosa.app/papers/crisp-co-designing-pruning-and-scheduling-for-efficient-moe-inference-on-edge-servers-2610-37442?lang=itChiosait2026-10-28T15:18:30ZCRISP coordina pruning e scheduling per i modelli MoE edgehttps://chiosa.app/papers/crisp-co-designing-pruning-and-scheduling-for-efficient-moe-inference-on-edge-servers-2610-37442?lang=esChiosaes2026-10-28T15:18:30ZCRISP coordina la poda y la planificación para MoE en dispositivos periféricoshttps://chiosa.app/papers/crisp-co-designing-pruning-and-scheduling-for-efficient-moe-inference-on-edge-servers-2610-37442?lang=frChiosafr2026-10-28T15:18:30ZCRISP associe élagage et ordonnancement pour les MoE en périphériehttps://chiosa.app/papers/do-we-need-an-llm-to-know-why-sources-conflict-decision-models-for-knowledge-conflict-typing-in-rag-2610-36915Chiosaen2026-10-28T15:18:30ZMost tested models match an older language model at classifying search conflictshttps://chiosa.app/papers/do-we-need-an-llm-to-know-why-sources-conflict-decision-models-for-knowledge-conflict-typing-in-rag-2610-36915?lang=itChiosait2026-10-28T15:18:30ZLa maggior parte dei modelli testati eguaglia un modello linguistico precedente nel classificare i conflitti tra risultati di ricercahttps://chiosa.app/papers/do-we-need-an-llm-to-know-why-sources-conflict-decision-models-for-knowledge-conflict-typing-in-rag-2610-36915?lang=esChiosaes2026-10-28T15:18:30ZLa mayoría de los modelos probados iguala a un modelo de lenguaje anterior al clasificar conflictos de búsquedahttps://chiosa.app/papers/do-we-need-an-llm-to-know-why-sources-conflict-decision-models-for-knowledge-conflict-typing-in-rag-2610-36915?lang=frChiosafr2026-10-28T15:18:30ZLa plupart des modèles testés égalent un ancien modèle de langage pour classer les conflits entre résultats de recherchehttps://chiosa.app/papers/efficient-quantization-training-with-stochastic-rounding-via-structured-subspace-randomness-2610-36587Chiosaen2026-10-28T15:18:30ZShared rounding thresholds speed training when errors are correctedhttps://chiosa.app/papers/efficient-quantization-training-with-stochastic-rounding-via-structured-subspace-randomness-2610-36587?lang=itChiosait2026-10-28T15:18:30ZLe soglie di arrotondamento condivise accelerano l’addestramento se l’errore viene correttohttps://chiosa.app/papers/efficient-quantization-training-with-stochastic-rounding-via-structured-subspace-randomness-2610-36587?lang=esChiosaes2026-10-28T15:18:30ZCompartir umbrales de redondeo acelera el entrenamiento si se corrigen los erroreshttps://chiosa.app/papers/efficient-quantization-training-with-stochastic-rounding-via-structured-subspace-randomness-2610-36587?lang=frChiosafr2026-10-28T15:18:30ZDes seuils d’arrondi partagés accélèrent l’entraînement si l’erreur est corrigéehttps://chiosa.app/papers/evolving-agent-teams-2610-36848Chiosaen2026-10-28T15:18:30ZA supervisor helps coding teams rethink GPU kernelshttps://chiosa.app/papers/evolving-agent-teams-2610-36848?lang=itChiosait2026-10-28T15:18:30ZUn supervisore aiuta i team di agenti a ripensare i kernel GPUhttps://chiosa.app/papers/evolving-agent-teams-2610-36848?lang=esChiosaes2026-10-28T15:18:30ZUn supervisor ayuda a los equipos de programación a replantear los kernels de GPUhttps://chiosa.app/papers/evolving-agent-teams-2610-36848?lang=frChiosafr2026-10-28T15:18:30ZUn superviseur aide les équipes à repenser les GPU kernelshttps://chiosa.app/papers/featurearc-benchmarking-coding-agents-on-evolving-features-2610-37434Chiosaen2026-10-28T15:18:30ZCoding agents often lose feature correctness across stageshttps://chiosa.app/papers/featurearc-benchmarking-coding-agents-on-evolving-features-2610-37434?lang=itChiosait2026-10-28T15:18:30ZGli agenti di coding spesso perdono correttezza tra le fasihttps://chiosa.app/papers/follow-the-gradient-tracing-safety-degradation-back-to-training-data-2610-37481Chiosaen2026-10-28T15:18:30ZGradient filtering removes risky training exampleshttps://chiosa.app/papers/follow-the-gradient-tracing-safety-degradation-back-to-training-data-2610-37481?lang=itChiosait2026-10-28T15:18:30ZIl filtraggio basato sui gradienti rimuove esempi rischiosi dai dati di addestramentohttps://chiosa.app/papers/follow-the-gradient-tracing-safety-degradation-back-to-training-data-2610-37481?lang=esChiosaes2026-10-28T15:18:30ZEl filtrado por gradientes retira ejemplos de entrenamiento riesgososhttps://chiosa.app/papers/gas-pfn-graph-aware-spatiotemporal-prior-data-fitted-networks-for-zero-shot-traffic-forecasting-2610-37598Chiosaen2026-10-28T15:18:30ZA graph-aware model forecasts traffic without retraininghttps://chiosa.app/papers/gas-pfn-graph-aware-spatiotemporal-prior-data-fitted-networks-for-zero-shot-traffic-forecasting-2610-37598?lang=itChiosait2026-10-28T15:18:30ZUn modello con grafi prevede il traffico senza riaddestramentohttps://chiosa.app/papers/gas-pfn-graph-aware-spatiotemporal-prior-data-fitted-networks-for-zero-shot-traffic-forecasting-2610-37598?lang=esChiosaes2026-10-28T15:18:30ZUn modelo con grafos predice el tráfico sin reentrenarsehttps://chiosa.app/papers/gas-pfn-graph-aware-spatiotemporal-prior-data-fitted-networks-for-zero-shot-traffic-forecasting-2610-37598?lang=frChiosafr2026-10-28T15:18:30ZUn modèle tenant compte des routes prévoit le trafic sans réentraînementhttps://chiosa.app/papers/governed-sovereign-rag-for-public-administration-tripartite-epistemic-routing-facet-guided-clarification-and-2610-36561Chiosaen2026-10-28T15:18:30ZA government assistant checks generated numbers against procedureshttps://chiosa.app/papers/governed-sovereign-rag-for-public-administration-tripartite-epistemic-routing-facet-guided-clarification-and-2610-36561?lang=itChiosait2026-10-28T15:18:30ZUn assistente pubblico verifica le cifre generate sulle procedurehttps://chiosa.app/papers/governed-sovereign-rag-for-public-administration-tripartite-epistemic-routing-facet-guided-clarification-and-2610-36561?lang=esChiosaes2026-10-28T15:18:30ZUn asistente público coteja las cifras generadas con los trámiteshttps://chiosa.app/papers/heads-of-security-learned-attention-gates-improve-prompt-injection-robustness-2610-37657Chiosaen2026-10-28T15:18:30ZLearned attention gates reduce prompt injection in two open modelshttps://chiosa.app/papers/heads-of-security-learned-attention-gates-improve-prompt-injection-robustness-2610-37657?lang=itChiosait2026-10-28T15:18:30ZGate di attenzione appresi riducono la prompt injection in due modelli open-weighthttps://chiosa.app/papers/heads-of-security-learned-attention-gates-improve-prompt-injection-robustness-2610-37657?lang=esChiosaes2026-10-28T15:18:30ZCompuertas de atención aprendidas reducen la inyección en dos modelos abiertoshttps://chiosa.app/papers/heads-of-security-learned-attention-gates-improve-prompt-injection-robustness-2610-37657?lang=frChiosafr2026-10-28T15:18:30ZDes portes d’attention apprises réduisent l’injection d’instructions dans deux modèles ouvertshttps://chiosa.app/papers/how-much-can-best-of-n-help-a-world-action-model-measuring-selectable-headroom-and-realizing-it-in-closed-loo-2610-37196Chiosaen2026-10-28T15:18:30ZRobot action selection gains depend on candidate designhttps://chiosa.app/papers/how-much-can-best-of-n-help-a-world-action-model-measuring-selectable-headroom-and-realizing-it-in-closed-loo-2610-37196?lang=itChiosait2026-10-28T15:18:30ZIl guadagno nella scelta delle azioni robotiche dipende dai candidatihttps://chiosa.app/papers/how-much-can-best-of-n-help-a-world-action-model-measuring-selectable-headroom-and-realizing-it-in-closed-loo-2610-37196?lang=esChiosaes2026-10-28T15:18:30ZLa mejora al elegir acciones robóticas depende de cómo se generan las opcioneshttps://chiosa.app/papers/how-much-can-best-of-n-help-a-world-action-model-measuring-selectable-headroom-and-realizing-it-in-closed-loo-2610-37196?lang=frChiosafr2026-10-28T15:18:30ZLes gains du choix d’actions robotiques dépendent des candidatshttps://chiosa.app/papers/hqclethe-streaming-hqc-encapsulation-for-tiny-stateless-servers-2610-36808Chiosaen2026-10-28T15:18:30ZHqcLethe streams HQC keys without per-client memoryhttps://chiosa.app/papers/hqclethe-streaming-hqc-encapsulation-for-tiny-stateless-servers-2610-36808?lang=itChiosait2026-10-28T15:18:30ZHqcLethe trasmette chiavi HQC senza memoria per clienthttps://chiosa.app/papers/hqclethe-streaming-hqc-encapsulation-for-tiny-stateless-servers-2610-36808?lang=esChiosaes2026-10-28T15:18:30ZHqcLethe transmite claves HQC sin memoria por clientehttps://chiosa.app/papers/hqclethe-streaming-hqc-encapsulation-for-tiny-stateless-servers-2610-36808?lang=frChiosafr2026-10-28T15:18:30ZHqcLethe traite les clés HQC sans mémoire par clienthttps://chiosa.app/papers/infradev-can-coding-agents-develop-ai-infrastructure-and-how-can-we-tell-2610-36589Chiosaen2026-10-28T15:18:30ZHidden checks expose coding agents’ incomplete infrastructure changeshttps://chiosa.app/papers/infradev-can-coding-agents-develop-ai-infrastructure-and-how-can-we-tell-2610-36589?lang=itChiosait2026-10-28T15:18:30ZI controlli nascosti rivelano modifiche incomplete all’infrastruttura AI realizzate dagli agenti di programmazionehttps://chiosa.app/papers/infradev-can-coding-agents-develop-ai-infrastructure-and-how-can-we-tell-2610-36589?lang=esChiosaes2026-10-28T15:18:30ZLas pruebas ocultas revelan cambios incompletos en infraestructura hechos por agentes de programaciónhttps://chiosa.app/papers/infradev-can-coding-agents-develop-ai-infrastructure-and-how-can-we-tell-2610-36589?lang=frChiosafr2026-10-28T15:18:30ZDes contrôles cachés révèlent les modifications incomplètes de l’infrastructure par les agents de programmationhttps://chiosa.app/papers/know-then-draw-a-new-learning-paradigm-for-visual-generation-2610-37626Chiosaen2026-10-28T15:18:30ZA two-stage method separates visual learning from renderinghttps://chiosa.app/papers/know-then-draw-a-new-learning-paradigm-for-visual-generation-2610-37626?lang=itChiosait2026-10-28T15:18:30ZUn metodo in due fasi separa l’apprendimento visivo dalla generazionehttps://chiosa.app/papers/know-then-draw-a-new-learning-paradigm-for-visual-generation-2610-37626?lang=esChiosaes2026-10-28T15:18:30ZUn método de dos etapas separa el aprendizaje visual de la generaciónhttps://chiosa.app/papers/know-then-draw-a-new-learning-paradigm-for-visual-generation-2610-37626?lang=frChiosafr2026-10-28T15:18:30ZUne méthode en deux étapes sépare apprentissage visuel et renduhttps://chiosa.app/papers/learning-visuomotor-quadrotor-flight-through-dynamic-narrow-gaps-via-differentiable-simulation-2610-37557Chiosaen2026-10-28T15:18:30ZQuadrotors learn to cross moving gaps in simulationhttps://chiosa.app/papers/learning-visuomotor-quadrotor-flight-through-dynamic-narrow-gaps-via-differentiable-simulation-2610-37557?lang=itChiosait2026-10-28T15:18:30ZI quadrotori imparano in simulazione ad attraversare varchi mobilihttps://chiosa.app/papers/learning-visuomotor-quadrotor-flight-through-dynamic-narrow-gaps-via-differentiable-simulation-2610-37557?lang=esChiosaes2026-10-28T15:18:30ZLos cuadricópteros aprenden en simulación a cruzar huecos móvileshttps://chiosa.app/papers/learning-visuomotor-quadrotor-flight-through-dynamic-narrow-gaps-via-differentiable-simulation-2610-37557?lang=frChiosafr2026-10-28T15:18:30ZDes quadricoptères apprennent en simulation à franchir des ouvertures mobileshttps://chiosa.app/papers/linmix-data-mixing-as-linear-domain-attribution-2610-37390Chiosaen2026-10-28T15:18:30ZVertex sampling helps mix many language-model data domainshttps://chiosa.app/papers/linmix-data-mixing-as-linear-domain-attribution-2610-37390?lang=itChiosait2026-10-28T15:18:30ZIl campionamento ai vertici aiuta a combinare molti domini di dati linguisticihttps://chiosa.app/papers/linmix-data-mixing-as-linear-domain-attribution-2610-37390?lang=esChiosaes2026-10-28T15:18:30ZEl muestreo de vértices ayuda a mezclar muchos dominios de datos para modelos de lenguajehttps://chiosa.app/papers/linmix-data-mixing-as-linear-domain-attribution-2610-37390?lang=frChiosafr2026-10-28T15:18:30ZL’échantillonnage aux sommets aide à mélanger de nombreux domaines de données pour les modèles de languehttps://chiosa.app/papers/lossless-compression-of-proximity-graph-indexes-for-efficient-approximate-nearest-neighbors-search-2610-37176Chiosaen2026-10-28T15:18:30ZHNSW graph compression cuts storage with little latency costhttps://chiosa.app/papers/lossless-compression-of-proximity-graph-indexes-for-efficient-approximate-nearest-neighbors-search-2610-37176?lang=esChiosaes2026-10-28T15:18:30ZLa compresión de grafos HNSW reduce el espacio con poco coste de latenciahttps://chiosa.app/papers/lossless-compression-of-proximity-graph-indexes-for-efficient-approximate-nearest-neighbors-search-2610-37176?lang=frChiosafr2026-10-28T15:18:30ZLa compression des graphes HNSW réduit le stockage avec peu de coût en latencehttps://chiosa.app/papers/mle-world-predicting-machine-learning-experiment-outcomes-with-a-learned-world-model-2610-37175Chiosaen2026-10-28T15:18:30ZPredicted program feedback helps agents search for solutionshttps://chiosa.app/papers/mle-world-predicting-machine-learning-experiment-outcomes-with-a-learned-world-model-2610-37175?lang=itChiosait2026-10-28T15:18:30ZLe previsioni sui programmi guidano la ricerca degli agentihttps://chiosa.app/papers/mle-world-predicting-machine-learning-experiment-outcomes-with-a-learned-world-model-2610-37175?lang=esChiosaes2026-10-28T15:18:30ZLas predicciones de ejecución ayudan a los agentes a buscar solucioneshttps://chiosa.app/papers/mle-world-predicting-machine-learning-experiment-outcomes-with-a-learned-world-model-2610-37175?lang=frChiosafr2026-10-28T15:18:30ZDes résultats d’exécution prédits aident les agents à chercher des solutionshttps://chiosa.app/papers/multi-agent-reinforcement-learning-of-co-adaptive-hip-exoskeleton-control-marl-exo-for-metabolic-energy-reduc-2610-37441Chiosaen2026-10-28T15:18:30ZA hip exoskeleton lowers walking energy versus a passive device in a small testhttps://chiosa.app/papers/multi-agent-reinforcement-learning-of-co-adaptive-hip-exoskeleton-control-marl-exo-for-metabolic-energy-reduc-2610-37441?lang=itChiosait2026-10-28T15:18:30ZIn un piccolo test, un esoscheletro per l’anca riduce il costo della camminata rispetto al dispositivo passivohttps://chiosa.app/papers/multi-agent-reinforcement-learning-of-co-adaptive-hip-exoskeleton-control-marl-exo-for-metabolic-energy-reduc-2610-37441?lang=esChiosaes2026-10-28T15:18:30ZUn exoesqueleto de cadera reduce el gasto al caminar frente al modo pasivo en una prueba pequeñahttps://chiosa.app/papers/multi-agent-reinforcement-learning-of-co-adaptive-hip-exoskeleton-control-marl-exo-for-metabolic-energy-reduc-2610-37441?lang=frChiosafr2026-10-28T15:18:30ZUn exosquelette de hanche réduit l’effort par rapport au mode passif dans un petit essaihttps://chiosa.app/papers/multi-state-linear-attention-with-generalized-second-order-routing-2610-37645Chiosaen2026-10-28T15:18:30ZMerlin helps long-context models weight useful segmentshttps://chiosa.app/papers/multi-state-linear-attention-with-generalized-second-order-routing-2610-37645?lang=itChiosait2026-10-28T15:18:30ZMerlin aiuta i modelli a contesto lungo a pesare i segmenti utilihttps://chiosa.app/papers/multi-state-linear-attention-with-generalized-second-order-routing-2610-37645?lang=esChiosaes2026-10-28T15:18:30ZMerlin ayuda a modelos de contexto largo a ponderar segmentos útileshttps://chiosa.app/papers/multi-state-linear-attention-with-generalized-second-order-routing-2610-37645?lang=frChiosafr2026-10-28T15:18:30ZMerlin aide les modèles à long contexte à pondérer les segments utileshttps://chiosa.app/papers/pailitaommsearch2-0-technical-report-scaling-generative-retrieval-to-unified-end-to-end-multimodal-search-2610-36958Chiosaen2026-10-28T15:18:30ZOne model handles three kinds of shopping searchhttps://chiosa.app/papers/pailitaommsearch2-0-technical-report-scaling-generative-retrieval-to-unified-end-to-end-multimodal-search-2610-36958?lang=itChiosait2026-10-28T15:18:30ZUn modello per tre tipi di ricerca per gli acquistihttps://chiosa.app/papers/pailitaommsearch2-0-technical-report-scaling-generative-retrieval-to-unified-end-to-end-multimodal-search-2610-36958?lang=esChiosaes2026-10-28T15:18:30ZUn modelo para tres tipos de búsqueda de productoshttps://chiosa.app/papers/pailitaommsearch2-0-technical-report-scaling-generative-retrieval-to-unified-end-to-end-multimodal-search-2610-36958?lang=frChiosafr2026-10-28T15:18:30ZUn modèle pour trois types de recherche d’achathttps://chiosa.app/papers/pdrvla-a-vision-language-action-model-with-physical-dynamics-representations-2610-37381Chiosaen2026-10-28T15:18:30ZA robot model learns scene changes without predicting videohttps://chiosa.app/papers/pdrvla-a-vision-language-action-model-with-physical-dynamics-representations-2610-37381?lang=itChiosait2026-10-28T15:18:30ZUn modello robotico apprende i cambiamenti della scena senza generare videohttps://chiosa.app/papers/pdrvla-a-vision-language-action-model-with-physical-dynamics-representations-2610-37381?lang=esChiosaes2026-10-28T15:18:30ZUn modelo robótico aprende cambios de escena sin predecir videohttps://chiosa.app/papers/pdrvla-a-vision-language-action-model-with-physical-dynamics-representations-2610-37381?lang=frChiosafr2026-10-28T15:18:30ZUn modèle robotique apprend l’évolution des scènes sans générer de vidéohttps://chiosa.app/papers/pipelink-contract-guided-linking-of-gpu-kernel-components-2610-37200Chiosaen2026-10-28T15:18:30ZPipeLink lets separately built GPU kernel parts work togetherhttps://chiosa.app/papers/pipelink-contract-guided-linking-of-gpu-kernel-components-2610-37200?lang=itChiosait2026-10-28T15:18:30ZPipeLink collega parti di kernel GPU compilate separatamentehttps://chiosa.app/papers/pipelink-contract-guided-linking-of-gpu-kernel-components-2610-37200?lang=esChiosaes2026-10-28T15:18:30ZPipeLink permite combinar partes de kernels GPU compiladas por separadohttps://chiosa.app/papers/pipelink-contract-guided-linking-of-gpu-kernel-components-2610-37200?lang=frChiosafr2026-10-28T15:18:30ZPipeLink assemble des composants de noyaux GPU compilés séparémenthttps://chiosa.app/papers/pneuma-a-large-scale-real-world-time-series-benchmark-for-commercial-aircraft-predictive-maintenance-2610-37563Chiosaen2026-10-28T15:18:30ZA public aircraft dataset exposes limits in early fault detectionhttps://chiosa.app/papers/pneuma-a-large-scale-real-world-time-series-benchmark-for-commercial-aircraft-predictive-maintenance-2610-37563?lang=itChiosait2026-10-28T15:18:30ZUn dataset pubblico sugli aerei mostra i limiti del rilevamento precoce dei guastihttps://chiosa.app/papers/pneuma-a-large-scale-real-world-time-series-benchmark-for-commercial-aircraft-predictive-maintenance-2610-37563?lang=esChiosaes2026-10-28T15:18:30ZUn conjunto público de datos de aeronaves muestra límites en la detección temprana de falloshttps://chiosa.app/papers/pneuma-a-large-scale-real-world-time-series-benchmark-for-commercial-aircraft-predictive-maintenance-2610-37563?lang=frChiosafr2026-10-28T15:18:30ZUn jeu de données public révèle les limites de la détection précoce des pannes d’avionhttps://chiosa.app/papers/pushing-dexterity-and-safety-for-in-hand-object-pose-reaching-that-works-remarkably-well-2610-37652Chiosaen2026-10-28T15:18:30ZA robot hand reaches poses while dropping fewer objectshttps://chiosa.app/papers/pushing-dexterity-and-safety-for-in-hand-object-pose-reaching-that-works-remarkably-well-2610-37652?lang=itChiosait2026-10-28T15:18:30ZUna mano robotica raggiunge le pose facendo cadere meno oggettihttps://chiosa.app/papers/pushing-dexterity-and-safety-for-in-hand-object-pose-reaching-that-works-remarkably-well-2610-37652?lang=esChiosaes2026-10-28T15:18:30ZUna mano robótica alcanza posiciones y deja caer menos objetoshttps://chiosa.app/papers/pushing-dexterity-and-safety-for-in-hand-object-pose-reaching-that-works-remarkably-well-2610-37652?lang=frChiosafr2026-10-28T15:18:30ZUne main robotique atteint des poses en faisant moins tomber les objetshttps://chiosa.app/papers/rendering-free-event-frame-simulation-for-fast-reinforcement-learning-of-autonomous-robot-navigation-2610-37543Chiosaen2026-10-28T15:18:30ZA rendering-free simulator trains drone navigation policies in minuteshttps://chiosa.app/papers/rendering-free-event-frame-simulation-for-fast-reinforcement-learning-of-autonomous-robot-navigation-2610-37543?lang=itChiosait2026-10-28T15:18:30ZUn simulatore senza rendering addestra in pochi minuti i controllori di navigazione dei dronihttps://chiosa.app/papers/rendering-free-event-frame-simulation-for-fast-reinforcement-learning-of-autonomous-robot-navigation-2610-37543?lang=esChiosaes2026-10-28T15:18:30ZUn simulador sin renderizado entrena la navegación de drones en minutoshttps://chiosa.app/papers/rendering-free-event-frame-simulation-for-fast-reinforcement-learning-of-autonomous-robot-navigation-2610-37543?lang=frChiosafr2026-10-28T15:18:30ZUn simulateur sans rendu entraîne la navigation des drones en quelques minuteshttps://chiosa.app/papers/resple2-inertial-informed-recursive-non-uniform-spline-estimation-for-multi-sensor-odometry-with-global-refin-2610-37602Chiosaen2026-10-28T15:18:30ZRESPLE2 predicts robot motion from inertial datahttps://chiosa.app/papers/resple2-inertial-informed-recursive-non-uniform-spline-estimation-for-multi-sensor-odometry-with-global-refin-2610-37602?lang=itChiosait2026-10-28T15:18:30ZRESPLE2 predice il movimento dei robot con dati inerzialihttps://chiosa.app/papers/resple2-inertial-informed-recursive-non-uniform-spline-estimation-for-multi-sensor-odometry-with-global-refin-2610-37602?lang=esChiosaes2026-10-28T15:18:30ZRESPLE2 predice el movimiento del robot con datos inercialeshttps://chiosa.app/papers/resple2-inertial-informed-recursive-non-uniform-spline-estimation-for-multi-sensor-odometry-with-global-refin-2610-37602?lang=frChiosafr2026-10-28T15:18:30ZRESPLE2 prédit le mouvement d’un robot à partir de données inertielleshttps://chiosa.app/papers/roboauto-autonomous-robot-program-search-through-multi-level-physical-understanding-2610-36533Chiosaen2026-10-28T15:18:30ZRoboAuto grounds robot programs in physical scene knowledgehttps://chiosa.app/papers/roboauto-autonomous-robot-program-search-through-multi-level-physical-understanding-2610-36533?lang=itChiosait2026-10-28T15:18:30ZRoboAuto collega i programmi robotici alla conoscenza fisica della scenahttps://chiosa.app/papers/roboauto-autonomous-robot-program-search-through-multi-level-physical-understanding-2610-36533?lang=esChiosaes2026-10-28T15:18:30ZRoboAuto adapta los programas robóticos al conocimiento físico de la escenahttps://chiosa.app/papers/roboauto-autonomous-robot-program-search-through-multi-level-physical-understanding-2610-36533?lang=frChiosafr2026-10-28T15:18:30ZRoboAuto ancre les programmes de robots dans la connaissance de la scène physiquehttps://chiosa.app/papers/rollback-experience-backtracking-in-world-models-for-policy-improvement-2610-36068Chiosaen2026-10-28T15:18:30ZRollback helps robots learn by revisiting key actionshttps://chiosa.app/papers/rollback-experience-backtracking-in-world-models-for-policy-improvement-2610-36068?lang=itChiosait2026-10-28T15:18:30ZRollback migliora l’apprendimento dei robot rivedendo le azionihttps://chiosa.app/papers/rollback-experience-backtracking-in-world-models-for-policy-improvement-2610-36068?lang=esChiosaes2026-10-28T15:18:30ZRollback ayuda a los robots a aprender al revisar acciones clavehttps://chiosa.app/papers/rollback-experience-backtracking-in-world-models-for-policy-improvement-2610-36068?lang=frChiosafr2026-10-28T15:18:30ZRollback aide les robots à apprendre en revisitant leurs décisionshttps://chiosa.app/papers/scaling-laws-for-tool-use-agents-via-controllable-environment-synthesis-2610-37648Chiosaen2026-10-28T15:18:30ZMore varied tool training data helps as budgets growhttps://chiosa.app/papers/secdmp-provably-secure-data-memory-dependent-prefetching-extended-version-2610-37454Chiosaen2026-10-28T15:18:30ZA hardware defense keeps prefetchers from scanning secret datahttps://chiosa.app/papers/secdmp-provably-secure-data-memory-dependent-prefetching-extended-version-2610-37454?lang=itChiosait2026-10-28T15:18:30ZUna difesa hardware impedisce ai prefetcher di esaminare dati segretihttps://chiosa.app/papers/secdmp-provably-secure-data-memory-dependent-prefetching-extended-version-2610-37454?lang=esChiosaes2026-10-28T15:18:30ZUna defensa de hardware impide que los prefetchers examinen datos secretoshttps://chiosa.app/papers/secdmp-provably-secure-data-memory-dependent-prefetching-extended-version-2610-37454?lang=frChiosafr2026-10-28T15:18:30ZUne protection matérielle empêche les préchargeurs d’examiner les secretshttps://chiosa.app/papers/select-ttt-query-conditioned-selective-fast-weight-updates-for-in-place-test-time-training-2610-36794Chiosaen2026-10-28T15:18:30ZSelect-TTT directs memory updates toward relevant texthttps://chiosa.app/papers/select-ttt-query-conditioned-selective-fast-weight-updates-for-in-place-test-time-training-2610-36794?lang=itChiosait2026-10-28T15:18:30ZSelect-TTT concentra gli aggiornamenti di memoria sul testo rilevantehttps://chiosa.app/papers/select-ttt-query-conditioned-selective-fast-weight-updates-for-in-place-test-time-training-2610-36794?lang=esChiosaes2026-10-28T15:18:30ZSelect-TTT dirige las actualizaciones de memoria al texto relevantehttps://chiosa.app/papers/spine-compiling-subtask-trees-into-structured-context-for-long-horizon-coding-agents-2610-37224Chiosaen2026-10-28T15:18:30ZSpine helps coding agents track nested workhttps://chiosa.app/papers/spine-compiling-subtask-trees-into-structured-context-for-long-horizon-coding-agents-2610-37224?lang=itChiosait2026-10-28T15:18:30ZSpine aiuta gli agenti di programmazione a seguire il lavoro annidatohttps://chiosa.app/papers/spine-compiling-subtask-trees-into-structured-context-for-long-horizon-coding-agents-2610-37224?lang=esChiosaes2026-10-28T15:18:30ZSpine ayuda a los agentes de programación a seguir el trabajo anidadohttps://chiosa.app/papers/spine-compiling-subtask-trees-into-structured-context-for-long-horizon-coding-agents-2610-37224?lang=frChiosafr2026-10-28T15:18:30ZSpine aide les agents de programmation à suivre les tâches imbriquéeshttps://chiosa.app/papers/teach-reality-not-ethics-a-drop-in-continued-pretraining-corpus-installs-coupled-human-biosphere-ai-welfare-d-2610-37484Chiosaen2026-10-28T15:18:30ZTraining helps models resist pressure to approve ecological harmhttps://chiosa.app/papers/teach-reality-not-ethics-a-drop-in-continued-pretraining-corpus-installs-coupled-human-biosphere-ai-welfare-d-2610-37484?lang=frChiosafr2026-10-28T15:18:30ZL’entraînement aide les modèles à résister aux pressions favorisant les dommages écologiqueshttps://chiosa.app/papers/tessera-structure-completed-evidence-units-for-web-retrieval-augmented-generation-2610-37080Chiosaen2026-10-28T15:18:30ZTessera gets webpage evidence into the reader’s contexthttps://chiosa.app/papers/tessera-structure-completed-evidence-units-for-web-retrieval-augmented-generation-2610-37080?lang=itChiosait2026-10-28T15:18:30ZTessera porta le prove delle pagine Web nel contesto del lettorehttps://chiosa.app/papers/tessera-structure-completed-evidence-units-for-web-retrieval-augmented-generation-2610-37080?lang=esChiosaes2026-10-28T15:18:30ZTessera lleva pruebas de páginas web al contexto del lectorhttps://chiosa.app/papers/tessera-structure-completed-evidence-units-for-web-retrieval-augmented-generation-2610-37080?lang=frChiosafr2026-10-28T15:18:30ZTessera transmet les preuves des pages Web au contexte du lecteurhttps://chiosa.app/papers/the-structure-gap-when-more-data-cannot-replace-structured-reasoning-2610-37523Chiosaen2026-10-28T15:18:30ZKnown task structure can resolve gaps left by exampleshttps://chiosa.app/papers/the-structure-gap-when-more-data-cannot-replace-structured-reasoning-2610-37523?lang=itChiosait2026-10-28T15:18:30ZLa struttura nota del compito può colmare i vuoti lasciati dagli esempihttps://chiosa.app/papers/the-structure-gap-when-more-data-cannot-replace-structured-reasoning-2610-37523?lang=esChiosaes2026-10-28T15:18:30ZLa estructura conocida de una tarea puede resolver lo que los ejemplos dejan abiertohttps://chiosa.app/papers/the-structure-gap-when-more-data-cannot-replace-structured-reasoning-2610-37523?lang=frChiosafr2026-10-28T15:18:30ZLa structure connue d’une tâche peut lever les limites des exempleshttps://chiosa.app/papers/the-trinity-capability-driven-recursive-self-improvement-for-multimodal-agents-2610-36077Chiosaen2026-10-28T15:18:30ZAgents can improve their tools by grouping shared abilitieshttps://chiosa.app/papers/the-trinity-capability-driven-recursive-self-improvement-for-multimodal-agents-2610-36077?lang=itChiosait2026-10-28T15:18:30ZGli agenti possono migliorare i propri strumenti raggruppando capacità condivisehttps://chiosa.app/papers/the-trinity-capability-driven-recursive-self-improvement-for-multimodal-agents-2610-36077?lang=esChiosaes2026-10-28T15:18:30ZLos agentes pueden mejorar sus herramientas agrupando capacidades compartidashttps://chiosa.app/papers/the-trinity-capability-driven-recursive-self-improvement-for-multimodal-agents-2610-36077?lang=frChiosafr2026-10-28T15:18:30ZLes agents peuvent améliorer leurs outils en regroupant les capacités communeshttps://chiosa.app/papers/thinkworld-world-imagination-reinforces-chain-of-dynamics-reasoning-2610-37666Chiosaen2026-10-28T15:18:30ZRobot learning uses video to ground motion reasoninghttps://chiosa.app/papers/thinkworld-world-imagination-reinforces-chain-of-dynamics-reasoning-2610-37666?lang=itChiosait2026-10-28T15:18:30ZI video aiutano i robot a ragionare sul movimentohttps://chiosa.app/papers/thinkworld-world-imagination-reinforces-chain-of-dynamics-reasoning-2610-37666?lang=esChiosaes2026-10-28T15:18:30ZLos robots aprenden a razonar sobre el movimiento con videoshttps://chiosa.app/papers/thinkworld-world-imagination-reinforces-chain-of-dynamics-reasoning-2610-37666?lang=frChiosafr2026-10-28T15:18:30ZLes vidéos aident les robots à raisonner sur le mouvementhttps://chiosa.app/papers/tops-reshaping-flow-source-and-transport-for-multi-task-robot-manipulation-2610-36694Chiosaen2026-10-28T15:18:30ZTOPS improves robot task success with task-specific flow pathshttps://chiosa.app/papers/tops-reshaping-flow-source-and-transport-for-multi-task-robot-manipulation-2610-36694?lang=itChiosait2026-10-28T15:18:30ZTOPS migliora il successo dei robot con percorsi di flow specificihttps://chiosa.app/papers/tops-reshaping-flow-source-and-transport-for-multi-task-robot-manipulation-2610-36694?lang=esChiosaes2026-10-28T15:18:30ZTOPS mejora el éxito robótico con trayectorias de flujo por tareahttps://chiosa.app/papers/tops-reshaping-flow-source-and-transport-for-multi-task-robot-manipulation-2610-36694?lang=frChiosafr2026-10-28T15:18:30ZTOPS améliore la réussite des tâches robotiques avec des trajectoires adaptées à chaque tâchehttps://chiosa.app/papers/trident-seq-profile-matched-prefix-future-contrast-for-label-efficient-payment-risk-modeling-2610-37365Chiosaen2026-10-28T15:18:30ZMatching payment histories helps risk models learn from fewer labelshttps://chiosa.app/papers/trident-seq-profile-matched-prefix-future-contrast-for-label-efficient-payment-risk-modeling-2610-37365?lang=itChiosait2026-10-28T15:18:30ZAbbinare le cronologie di pagamento aiuta i modelli di rischio con meno etichettehttps://chiosa.app/papers/trident-seq-profile-matched-prefix-future-contrast-for-label-efficient-payment-risk-modeling-2610-37365?lang=esChiosaes2026-10-28T15:18:30ZEmparejar historiales de pago ayuda a aprender con menos etiquetashttps://chiosa.app/papers/vibevideobench-evaluating-multimodal-agents-on-code-driven-video-generation-2610-35864Chiosaen2026-10-28T15:18:30ZA new test shows where video-making agents still fall shorthttps://chiosa.app/papers/vibevideobench-evaluating-multimodal-agents-on-code-driven-video-generation-2610-35864?lang=itChiosait2026-10-28T15:18:30ZUn nuovo test mostra dove gli agenti che creano video sono ancora carentihttps://chiosa.app/papers/vibevideobench-evaluating-multimodal-agents-on-code-driven-video-generation-2610-35864?lang=esChiosaes2026-10-28T15:18:30ZUna nueva prueba muestra qué les falta a los agentes que crean videoshttps://chiosa.app/papers/vibevideobench-evaluating-multimodal-agents-on-code-driven-video-generation-2610-35864?lang=frChiosafr2026-10-28T15:18:30ZUn nouveau test révèle les limites des agents vidéohttps://chiosa.app/papers/vision-language-action-or-world-action-just-action-models-2610-37219Chiosaen2026-10-28T15:18:30ZRobot policies can learn from the future without generating images (F1, F3)https://chiosa.app/papers/vision-language-action-or-world-action-just-action-models-2610-37219?lang=itChiosait2026-10-28T15:18:30ZLe policy robotiche possono imparare dal futuro senza generare immagini (F1, F3)https://chiosa.app/papers/vision-language-action-or-world-action-just-action-models-2610-37219?lang=esChiosaes2026-10-28T15:18:30ZLas políticas robóticas pueden aprender del futuro sin generar imágenes (F1, F3)https://chiosa.app/papers/vision-language-action-or-world-action-just-action-models-2610-37219?lang=frChiosafr2026-10-28T15:18:30ZLes politiques robotiques peuvent apprendre du futur sans générer d’images (F1, F3)https://chiosa.app/papers/watermark-basins-black-box-detection-of-distilled-llms-2610-37266Chiosaen2026-10-28T15:18:30ZA text-only test traces watermarked training into student modelshttps://chiosa.app/papers/watermark-basins-black-box-detection-of-distilled-llms-2610-37266?lang=itChiosait2026-10-28T15:18:30ZUn test basato sul testo rintraccia l’addestramento con watermark nei modelli studentihttps://chiosa.app/papers/watermark-basins-black-box-detection-of-distilled-llms-2610-37266?lang=esChiosaes2026-10-28T15:18:30ZUna prueba basada solo en texto rastrea el entrenamiento con marcas de agua en modelos estudianteshttps://chiosa.app/papers/watermark-basins-black-box-detection-of-distilled-llms-2610-37266?lang=frChiosafr2026-10-28T15:18:30ZUn test fondé sur le texte repère l’entraînement avec filigrane dans les modèles étudiantshttps://chiosa.app/papers/when-does-perturbation-consistency-add-information-beyond-softmax-confidence-theory-and-evidence-for-the-deci-2610-36640Chiosaen2026-10-28T15:18:30ZPerturbation consistency adds little to clean image error checkshttps://chiosa.app/papers/when-does-perturbation-consistency-add-information-beyond-softmax-confidence-theory-and-evidence-for-the-deci-2610-36640?lang=itChiosait2026-10-28T15:18:30ZLa coerenza alle perturbazioni aggiunge poco al rilevamento degli errori nelle immagini pulitehttps://chiosa.app/papers/when-does-perturbation-consistency-add-information-beyond-softmax-confidence-theory-and-evidence-for-the-deci-2610-36640?lang=frChiosafr2026-10-28T15:18:30ZLa cohérence aux perturbations apporte peu à la détection d’erreurs sur images non modifiéeshttps://chiosa.app/papers/whether-is-not-when-separating-occurrence-from-timing-in-polymarket-prices-2610-36639Chiosaen2026-10-28T15:18:30ZPrediction prices reveal more about whether than whenhttps://chiosa.app/papers/whether-is-not-when-separating-occurrence-from-timing-in-polymarket-prices-2610-36639?lang=itChiosait2026-10-28T15:18:30ZI prezzi predittivi rivelano più se un evento accadrà che quandohttps://chiosa.app/papers/whether-is-not-when-separating-occurrence-from-timing-in-polymarket-prices-2610-36639?lang=frChiosafr2026-10-28T15:18:30ZLes prix prédisent davantage si un événement survient que quandhttps://chiosa.app/papers/workfactory-turning-professional-intents-into-executable-work-for-scalable-agent-training-2610-37161Chiosaen2026-10-28T15:18:30ZA task-building framework checks whether work tasks can be solvedhttps://chiosa.app/papers/workfactory-turning-professional-intents-into-executable-work-for-scalable-agent-training-2610-37161?lang=itChiosait2026-10-28T15:18:30ZUn framework verifica se le attività di lavoro si possono svolgerehttps://chiosa.app/papers/workfactory-turning-professional-intents-into-executable-work-for-scalable-agent-training-2610-37161?lang=esChiosaes2026-10-28T15:18:30ZUn marco para comprobar si las tareas de trabajo se pueden resolverhttps://chiosa.app/papers/workfactory-turning-professional-intents-into-executable-work-for-scalable-agent-training-2610-37161?lang=frChiosafr2026-10-28T15:18:30ZUn cadre vérifie si les tâches professionnelles peuvent être résolueshttps://chiosa.app/papers/world-dreamer-v5-lite-a-multi-robot-world-action-model-with-one-dreamer-2610-37518Chiosaen2026-10-28T15:18:30ZA shared spatial map helps robots coordinate across viewshttps://chiosa.app/papers/world-dreamer-v5-lite-a-multi-robot-world-action-model-with-one-dreamer-2610-37518?lang=itChiosait2026-10-28T15:18:30ZUna mappa spaziale condivisa aiuta i robot a coordinarsihttps://chiosa.app/papers/world-dreamer-v5-lite-a-multi-robot-world-action-model-with-one-dreamer-2610-37518?lang=esChiosaes2026-10-28T15:18:30ZUn mapa espacial compartido ayuda a coordinar robotshttps://chiosa.app/papers/world-dreamer-v5-lite-a-multi-robot-world-action-model-with-one-dreamer-2610-37518?lang=frChiosafr2026-10-28T15:18:30ZUne représentation spatiale commune aide les robots à coordonner leurs vueshttps://chiosa.app/papers/your-policy-is-secretly-a-harness-the-decision-geometry-of-agent-interfaces-2610-37255Chiosaen2026-10-28T15:18:30ZA harness can hurt a frozen agent and help it after retraininghttps://chiosa.app/papers/your-policy-is-secretly-a-harness-the-decision-geometry-of-agent-interfaces-2610-37255?lang=esChiosaes2026-10-28T15:18:30ZUn entorno puede perjudicar a un agente congelado y ayudarlo tras reentrenarlohttps://chiosa.app/papers/your-policy-is-secretly-a-harness-the-decision-geometry-of-agent-interfaces-2610-37255?lang=frChiosafr2026-10-28T15:18:30ZUn cadre peut nuire à un agent figé, puis l’aider après réentraînement