https://chiosa.app/papers/alps-visual-state-encoders-for-world-models-2610-30120Chiosaen2026-10-22T18:08:13ZOne visual encoder links scene state, language, and image detailhttps://chiosa.app/papers/did-the-problem-actually-get-harder-testing-llms-on-paired-p-and-np-complete-problems-hardened-by-adversarial-2610-30103Chiosaen2026-10-22T18:08:13ZModels solve fewer problems after a structural change makes them NP-completehttps://chiosa.app/papers/did-the-problem-actually-get-harder-testing-llms-on-paired-p-and-np-complete-problems-hardened-by-adversarial-2610-30103?lang=esChiosaes2026-10-22T18:08:13ZLos modelos resuelven menos problemas cuando un cambio estructural los vuelve NP-completoshttps://chiosa.app/papers/donic-generalist-dexterous-bimanual-tracking-control-from-human-demonstrations-2610-29997Chiosaen2026-10-22T18:08:13ZOne robot policy tracks two-hand object referenceshttps://chiosa.app/papers/donic-generalist-dexterous-bimanual-tracking-control-from-human-demonstrations-2610-29997?lang=itChiosait2026-10-22T18:08:13ZUna policy robotica segue riferimenti a oggetti con due manihttps://chiosa.app/papers/donic-generalist-dexterous-bimanual-tracking-control-from-human-demonstrations-2610-29997?lang=esChiosaes2026-10-22T18:08:13ZUna política robótica sigue referencias de objetos con dos manoshttps://chiosa.app/papers/donic-generalist-dexterous-bimanual-tracking-control-from-human-demonstrations-2610-29997?lang=frChiosafr2026-10-22T18:08:13ZUn contrôleur robotique suit des références à deux mainshttps://chiosa.app/papers/dynaweave-learning-to-adapt-through-dynamic-scenario-synthesis-2610-29443Chiosaen2026-10-22T18:08:13ZDynaWeave turns static tool tasks into changing scenarioshttps://chiosa.app/papers/dynaweave-learning-to-adapt-through-dynamic-scenario-synthesis-2610-29443?lang=esChiosaes2026-10-22T18:08:13ZDynaWeave convierte tareas estáticas con herramientas en escenarios cambianteshttps://chiosa.app/papers/encoded-but-unused-bounding-the-sources-of-vlm-errors-2610-29241Chiosaen2026-10-22T18:08:13ZMany tested object-attribute errors show detectable visual evidencehttps://chiosa.app/papers/environment-duels-a-microcosm-of-llm-co-evolution-2610-30116Chiosaen2026-10-22T18:08:13ZModels that solve best are not always the best task authorshttps://chiosa.app/papers/environment-duels-a-microcosm-of-llm-co-evolution-2610-30116?lang=itChiosait2026-10-22T18:08:13ZI modelli che risolvono meglio non sono sempre i migliori autori di compitihttps://chiosa.app/papers/asymmetric-on-policy-distillation-learns-in-context-exploration-2610-30105Chiosaen2026-10-22T15:13:17ZASTEROID teaches partial-view agents to explore from experiencehttps://chiosa.app/papers/asymmetric-on-policy-distillation-learns-in-context-exploration-2610-30105?lang=esChiosaes2026-10-22T15:13:17ZASTEROID enseña a agentes con visión parcial a explorar a partir de la experienciahttps://chiosa.app/papers/asymmetric-on-policy-distillation-learns-in-context-exploration-2610-30105?lang=frChiosafr2026-10-22T15:13:17ZASTEROID apprend aux agents à vue partielle à explorer par l’expériencehttps://chiosa.app/papers/auditing-conformal-prediction-for-language-models-under-inference-time-model-shift-2610-28937Chiosaen2026-10-22T15:13:17ZChanging model settings can reduce prediction coveragehttps://chiosa.app/papers/automating-ml-for-science-can-frontier-agents-climb-scientific-hills-in-the-wild-2610-28763Chiosaen2026-10-22T15:13:17ZA testbed measures coding-agent gains on science modelshttps://chiosa.app/papers/behavior-beyond-text-evaluating-refusal-transfer-failure-in-llm-agents-2610-28982Chiosaen2026-10-22T15:13:17ZChat refusals often fail to prevent unsafe tool callshttps://chiosa.app/papers/better-policies-worse-verifier-audits-2610-29029Chiosaen2026-10-22T15:13:17ZWhen whole-task audits misjudge component checkershttps://chiosa.app/papers/bridge-an-acceptance-gate-to-block-false-improvements-in-model-updates-with-a-retrospective-clinical-evaluati-2610-29515Chiosaen2026-10-22T15:13:17ZA gate checks whether model updates really improvehttps://chiosa.app/papers/bridge-an-acceptance-gate-to-block-false-improvements-in-model-updates-with-a-retrospective-clinical-evaluati-2610-29515?lang=itChiosait2026-10-22T15:13:17ZUn criterio verifica se gli aggiornamenti migliorano davverohttps://chiosa.app/papers/bridge-an-acceptance-gate-to-block-false-improvements-in-model-updates-with-a-retrospective-clinical-evaluati-2610-29515?lang=esChiosaes2026-10-22T15:13:17ZUn filtro comprueba si las actualizaciones de modelos mejoranhttps://chiosa.app/papers/bridge-an-acceptance-gate-to-block-false-improvements-in-model-updates-with-a-retrospective-clinical-evaluati-2610-29515?lang=frChiosafr2026-10-22T15:13:17ZUn filtre vérifie si les mises à jour améliorent vraiment les modèleshttps://chiosa.app/papers/certmoe-robustness-certification-for-mixture-of-experts-llms-via-routing-aware-smoothing-2610-29395Chiosaen2026-10-22T15:13:17ZCertifying robustness when language model routes changehttps://chiosa.app/papers/certmoe-robustness-certification-for-mixture-of-experts-llms-via-routing-aware-smoothing-2610-29395?lang=itChiosait2026-10-22T15:13:17ZCertificare la robustezza quando cambia il routing del modellohttps://chiosa.app/papers/certmoe-robustness-certification-for-mixture-of-experts-llms-via-routing-aware-smoothing-2610-29395?lang=esChiosaes2026-10-22T15:13:17ZCertificar robustez cuando cambian las rutas del modelohttps://chiosa.app/papers/characterizing-and-defending-utility-hijacking-in-instruction-tuning-data-selection-2610-29886Chiosaen2026-10-22T15:13:17ZHow harmful records can evade data selectorshttps://chiosa.app/papers/characterizing-and-defending-utility-hijacking-in-instruction-tuning-data-selection-2610-29886?lang=itChiosait2026-10-22T15:13:17ZCome i dati dannosi possono eludere i selettorihttps://chiosa.app/papers/characterizing-and-defending-utility-hijacking-in-instruction-tuning-data-selection-2610-29886?lang=esChiosaes2026-10-22T15:13:17ZCómo evaden los registros dañinos los selectores de datoshttps://chiosa.app/papers/characterizing-and-defending-utility-hijacking-in-instruction-tuning-data-selection-2610-29886?lang=frChiosafr2026-10-22T15:13:17ZComment des exemples nuisibles peuvent contourner les sélecteurshttps://chiosa.app/papers/compaction-laundering-provenance-destruction-in-context-compacting-coding-agents-2610-29869Chiosaen2026-10-22T15:13:17ZForged labels can turn tool text into user instructionshttps://chiosa.app/papers/compaction-laundering-provenance-destruction-in-context-compacting-coding-agents-2610-29869?lang=esChiosaes2026-10-22T15:13:17ZLas etiquetas falsificadas pueden convertir texto de herramientas en instrucciones del usuariohttps://chiosa.app/papers/constrained-tagging-for-span-labeling-2610-28922Chiosaen2026-10-22T15:13:17ZInline tags help language models locate text spanshttps://chiosa.app/papers/deciding-scale-placement-in-mxfp4-dot-products-with-integer-arithmetic-2610-29445Chiosaen2026-10-22T15:13:17ZWhen compilers can safely move MXFP4 scaleshttps://chiosa.app/papers/deciding-scale-placement-in-mxfp4-dot-products-with-integer-arithmetic-2610-29445?lang=itChiosait2026-10-22T15:13:17ZQuando i compilatori possono spostare in sicurezza le scale MXFP4https://chiosa.app/papers/deciding-scale-placement-in-mxfp4-dot-products-with-integer-arithmetic-2610-29445?lang=esChiosaes2026-10-22T15:13:17ZCuándo puede un compilador mover escalas MXFP4https://chiosa.app/papers/deciding-scale-placement-in-mxfp4-dot-products-with-integer-arithmetic-2610-29445?lang=frChiosafr2026-10-22T15:13:17ZQuand un compilateur peut déplacer les échelles MXFP4 sans risquehttps://chiosa.app/papers/echo-emergent-common-mode-hidden-offsets-drive-vocabulary-collapse-in-preference-optimization-2610-29410Chiosaen2026-10-22T15:13:17ZWhy preference ranking can improve as text generation collapseshttps://chiosa.app/papers/echo-emergent-common-mode-hidden-offsets-drive-vocabulary-collapse-in-preference-optimization-2610-29410?lang=itChiosait2026-10-22T15:13:17ZPerché il ranking delle preferenze può migliorare mentre la generazione collassahttps://chiosa.app/papers/echo-emergent-common-mode-hidden-offsets-drive-vocabulary-collapse-in-preference-optimization-2610-29410?lang=esChiosaes2026-10-22T15:13:17ZPor qué mejora la clasificación por preferencias mientras colapsa la generación de textohttps://chiosa.app/papers/events-not-pixels-where-world-models-get-the-return-wrong-2610-29435Chiosaen2026-10-22T15:13:17ZWorld models can miss events in frames that look accuratehttps://chiosa.app/papers/events-not-pixels-where-world-models-get-the-return-wrong-2610-29435?lang=esChiosaes2026-10-22T15:13:17ZLos modelos del mundo pueden pasar por alto eventos en fotogramas que parecen precisoshttps://chiosa.app/papers/events-not-pixels-where-world-models-get-the-return-wrong-2610-29435?lang=frChiosafr2026-10-22T15:13:17ZLes modèles du monde peuvent manquer des événements dans des images pourtant fidèleshttps://chiosa.app/papers/frontiercs-2-a-benchmark-for-computer-science-r-d-2610-29932Chiosaen2026-10-22T15:13:17ZAgents can improve research code, but many tasks stump allhttps://chiosa.app/papers/frontiercs-2-a-benchmark-for-computer-science-r-d-2610-29932?lang=frChiosafr2026-10-22T15:13:17ZLes agents peuvent améliorer le code de recherche, mais de nombreuses tâches ont laissé tous les agents sans solutionhttps://chiosa.app/papers/huayu-global-skillful-real-time-quasi-global-precipitation-retrieval-2610-29213Chiosaen2026-10-22T15:13:17ZA satellite system brings stronger rainfall detection into real timehttps://chiosa.app/papers/is-2-4-sparsity-still-worth-it-semi-structured-sparsity-versus-quantization-in-llm-inference-2610-28947Chiosaen2026-10-22T15:13:17ZFor LLM inference, lower precision beats 2:4 above the floorhttps://chiosa.app/papers/pause-search-free-steering-of-coding-agents-before-their-first-source-code-edit-2610-29870Chiosaen2026-10-22T15:13:17ZA single repair plan helps coding agents resolve more taskshttps://chiosa.app/papers/pause-search-free-steering-of-coding-agents-before-their-first-source-code-edit-2610-29870?lang=itChiosait2026-10-22T15:13:17ZUn piano di riparazione aiuta gli agenti di coding a risolvere più attivitàhttps://chiosa.app/papers/pause-search-free-steering-of-coding-agents-before-their-first-source-code-edit-2610-29870?lang=esChiosaes2026-10-22T15:13:17ZUn plan de reparación ayuda a los agentes de programación a resolver más tareashttps://chiosa.app/papers/rubatocodec-budgeted-adaptive-speech-tokenization-with-streaming-decoding-2610-29434Chiosaen2026-10-22T15:13:17ZA fixed event budget lets speech codes adapt their timinghttps://chiosa.app/papers/rubatocodec-budgeted-adaptive-speech-tokenization-with-streaming-decoding-2610-29434?lang=itChiosait2026-10-22T15:13:17ZUn event budget fisso adatta i tempi dei codici vocalihttps://chiosa.app/papers/rubatocodec-budgeted-adaptive-speech-tokenization-with-streaming-decoding-2610-29434?lang=esChiosaes2026-10-22T15:13:17ZUn presupuesto fijo de eventos permite adaptar la temporización de los códigos de hablahttps://chiosa.app/papers/rubatocodec-budgeted-adaptive-speech-tokenization-with-streaming-decoding-2610-29434?lang=frChiosafr2026-10-22T15:13:17ZUn budget d’événements fixe permet aux codes vocaux d’adapter leur rythmehttps://chiosa.app/papers/safter-safety-aware-filtering-through-explicit-recoverability-for-robust-reinforcement-learning-under-distrib-2610-29149Chiosaen2026-10-22T15:13:17ZA robot safety filter learns to preserve recovery optionshttps://chiosa.app/papers/tenetbench-a-clause-anchored-russian-corpus-for-evaluating-language-models-against-professional-codes-of-ethi-2610-29477Chiosaen2026-10-22T15:13:17ZA clause-based test exposes conflicts with professional ethics ruleshttps://chiosa.app/papers/tenetbench-a-clause-anchored-russian-corpus-for-evaluating-language-models-against-professional-codes-of-ethi-2610-29477?lang=esChiosaes2026-10-22T15:13:17ZUna prueba basada en cláusulas revela conflictos con reglas de ética profesionalhttps://chiosa.app/papers/tenetbench-a-clause-anchored-russian-corpus-for-evaluating-language-models-against-professional-codes-of-ethi-2610-29477?lang=frChiosafr2026-10-22T15:13:17ZUn test fondé sur les articles de code révèle des conflits déontologiqueshttps://chiosa.app/papers/the-end-of-consensus-research-2610-30114Chiosaen2026-10-22T15:13:17ZAn AI harness produces a faster consensus protocolhttps://chiosa.app/papers/the-end-of-consensus-research-2610-30114?lang=itChiosait2026-10-22T15:13:17ZUn framework di AI produce un protocollo di consenso più velocehttps://chiosa.app/papers/the-end-of-consensus-research-2610-30114?lang=esChiosaes2026-10-22T15:13:17ZUn entorno de IA produce un protocolo de consenso más rápidohttps://chiosa.app/papers/the-end-of-consensus-research-2610-30114?lang=frChiosafr2026-10-22T15:13:17ZUn cadre d’IA produit un protocole de consensus plus rapidehttps://chiosa.app/papers/uncensored-is-not-unbiased-abliteration-removes-refusals-but-not-script-dependent-bias-about-taiwan-2610-29342Chiosaen2026-10-22T15:13:17ZReducing refusals did not erase Taiwan’s script gaphttps://chiosa.app/papers/uncensored-is-not-unbiased-abliteration-removes-refusals-but-not-script-dependent-bias-about-taiwan-2610-29342?lang=itChiosait2026-10-22T15:13:17ZRidurre i rifiuti non elimina la differenza su Taiwan tra sistemi di scritturahttps://chiosa.app/papers/unlocking-spatial-grounding-in-flow-matching-models-via-snr-tuning-2610-29581Chiosaen2026-10-22T15:13:17ZShifting training helps image models follow coordinateshttps://chiosa.app/papers/unlocking-spatial-grounding-in-flow-matching-models-via-snr-tuning-2610-29581?lang=itChiosait2026-10-22T15:13:17ZSpostare l’addestramento aiuta i modelli a seguire le coordinatehttps://chiosa.app/papers/unlocking-spatial-grounding-in-flow-matching-models-via-snr-tuning-2610-29581?lang=esChiosaes2026-10-22T15:13:17ZCambiar el entrenamiento ayuda a los modelos de imagen a seguir coordenadashttps://chiosa.app/papers/unlocking-spatial-grounding-in-flow-matching-models-via-snr-tuning-2610-29581?lang=frChiosafr2026-10-22T15:13:17ZUn entraînement décalé aide les modèles d’image à suivre les coordonnéeshttps://chiosa.app/papers/what-the-author-wrote-what-the-agent-reads-silent-cue-loss-in-enterprise-document-ingestion-2610-30026Chiosaen2026-10-22T15:13:17ZA document parser preserves visual cues agents need to find requirementshttps://chiosa.app/papers/what-the-author-wrote-what-the-agent-reads-silent-cue-loss-in-enterprise-document-ingestion-2610-30026?lang=itChiosait2026-10-22T15:13:17ZUn parser conserva i segnali visivi utili agli agenti per trovare i requisitihttps://chiosa.app/papers/what-the-author-wrote-what-the-agent-reads-silent-cue-loss-in-enterprise-document-ingestion-2610-30026?lang=esChiosaes2026-10-22T15:13:17ZUn analizador conserva las señales visuales que ayudan a los agentes a encontrar requisitoshttps://chiosa.app/papers/what-the-author-wrote-what-the-agent-reads-silent-cue-loss-in-enterprise-document-ingestion-2610-30026?lang=frChiosafr2026-10-22T15:13:17ZUn analyseur préserve les indices visuels qui aident les agents à repérer les exigenceshttps://chiosa.app/papers/when-thoughts-become-memory-unifying-in-context-learning-and-fine-tuning-2610-29419Chiosaen2026-10-22T15:13:17ZA bit-based method compares context with model weightshttps://chiosa.app/papers/when-thoughts-become-memory-unifying-in-context-learning-and-fine-tuning-2610-29419?lang=itChiosait2026-10-22T15:13:17ZUn metodo basato sui bit confronta il contesto con i pesi del modellohttps://chiosa.app/papers/when-thoughts-become-memory-unifying-in-context-learning-and-fine-tuning-2610-29419?lang=esChiosaes2026-10-22T15:13:17ZUn método basado en bits compara el contexto con los pesos del modelohttps://chiosa.app/papers/when-thoughts-become-memory-unifying-in-context-learning-and-fine-tuning-2610-29419?lang=frChiosafr2026-10-22T15:13:17ZUne méthode en bits compare le contexte aux poids du modèlehttps://chiosa.app/papers/where-should-a-stuck-agent-spend-its-next-tokens-causal-attribution-of-inference-time-resources-2610-28834Chiosaen2026-10-22T15:13:17ZA fixed-state test shows what helps coding agents repair codehttps://chiosa.app/papers/don-t-rewrite-the-sid-map-topology-preservation-for-generative-retrieval-in-dynamic-e-commerce-search-2610-26105Chiosaen2026-10-21T16:19:08ZStable item codes help preserve search qualityhttps://chiosa.app/papers/don-t-rewrite-the-sid-map-topology-preservation-for-generative-retrieval-in-dynamic-e-commerce-search-2610-26105?lang=itChiosait2026-10-21T16:19:08ZCodici stabili aiutano a preservare la qualità della ricercahttps://chiosa.app/papers/don-t-rewrite-the-sid-map-topology-preservation-for-generative-retrieval-in-dynamic-e-commerce-search-2610-26105?lang=esChiosaes2026-10-21T16:19:08ZLos códigos estables ayudan a conservar la calidad de búsquedahttps://chiosa.app/papers/don-t-rewrite-the-sid-map-topology-preservation-for-generative-retrieval-in-dynamic-e-commerce-search-2610-26105?lang=frChiosafr2026-10-21T16:19:08ZDes codes d’articles stables aident à préserver la qualité des rechercheshttps://chiosa.app/papers/local-allow-global-deny-why-per-action-authorization-does-not-compose-in-llm-agents-2610-27620Chiosaen2026-10-21T16:19:08ZWhy some purpose violations require comparing agent runshttps://chiosa.app/papers/local-allow-global-deny-why-per-action-authorization-does-not-compose-in-llm-agents-2610-27620?lang=itChiosait2026-10-21T16:19:08ZPerché alcune violazioni di finalità richiedono di confrontare le esecuzioni degli agentihttps://chiosa.app/papers/local-allow-global-deny-why-per-action-authorization-does-not-compose-in-llm-agents-2610-27620?lang=esChiosaes2026-10-21T16:19:08ZPor qué algunas infracciones de propósito exigen comparar ejecuciones de agenteshttps://chiosa.app/papers/local-allow-global-deny-why-per-action-authorization-does-not-compose-in-llm-agents-2610-27620?lang=frChiosafr2026-10-21T16:19:08ZPourquoi certaines violations de finalité exigent de comparer les exécutions d’un agenthttps://chiosa.app/papers/perceives-but-doesn-t-brake-a-perception-action-binding-gap-in-reasoning-driving-vlas-2610-28184Chiosaen2026-10-21T16:19:08ZA driving model can see a hazard yet fail to brakehttps://chiosa.app/papers/perceives-but-doesn-t-brake-a-perception-action-binding-gap-in-reasoning-driving-vlas-2610-28184?lang=itChiosait2026-10-21T16:19:08ZUn modello di guida può vedere un pericolo e non frenarehttps://chiosa.app/papers/perceives-but-doesn-t-brake-a-perception-action-binding-gap-in-reasoning-driving-vlas-2610-28184?lang=esChiosaes2026-10-21T16:19:08ZUn modelo de conducción puede ver un peligro y aun así no frenarhttps://chiosa.app/papers/perceives-but-doesn-t-brake-a-perception-action-binding-gap-in-reasoning-driving-vlas-2610-28184?lang=frChiosafr2026-10-21T16:19:08ZUn modèle de conduite peut voir un danger sans freinerhttps://chiosa.app/papers/physical-ai-for-intralogistics-benchmarking-the-nvidia-sim-to-real-ecosystem-for-cosmos-enhanced-compass-navi-2610-28432Chiosaen2026-10-21T16:19:08ZSimulation-trained robot navigation improves on the real iw.hubhttps://chiosa.app/papers/physical-ai-for-intralogistics-benchmarking-the-nvidia-sim-to-real-ecosystem-for-cosmos-enhanced-compass-navi-2610-28432?lang=itChiosait2026-10-21T16:19:08ZLa navigazione robotica addestrata in simulazione migliora sull'iw.hub realehttps://chiosa.app/papers/physical-ai-for-intralogistics-benchmarking-the-nvidia-sim-to-real-ecosystem-for-cosmos-enhanced-compass-navi-2610-28432?lang=esChiosaes2026-10-21T16:19:08ZLa navegación robótica entrenada en simulación mejora en el iw.hub realhttps://chiosa.app/papers/physical-ai-for-intralogistics-benchmarking-the-nvidia-sim-to-real-ecosystem-for-cosmos-enhanced-compass-navi-2610-28432?lang=frChiosafr2026-10-21T16:19:08ZLa navigation robotique entraînée en simulation progresse sur l’iw.hub réelhttps://chiosa.app/papers/slots-are-not-speakers-training-free-speaker-linking-for-frozen-streaming-diarizers-2610-28053Chiosaen2026-10-21T16:19:08ZA speaker linker lets diarizers follow people beyond their slot limithttps://chiosa.app/papers/slots-are-not-speakers-training-free-speaker-linking-for-frozen-streaming-diarizers-2610-28053?lang=itChiosait2026-10-21T16:19:08ZUn collegamento aiuta i sistemi di diarizzazione a seguire i parlanti oltre il limite degli slothttps://chiosa.app/papers/slots-are-not-speakers-training-free-speaker-linking-for-frozen-streaming-diarizers-2610-28053?lang=esChiosaes2026-10-21T16:19:08ZUn enlazador ayuda a la diarización a seguir a más personas que sus ranurashttps://chiosa.app/papers/slots-are-not-speakers-training-free-speaker-linking-for-frozen-streaming-diarizers-2610-28053?lang=frChiosafr2026-10-21T16:19:08ZUn système de liaison aide la diarisation à suivre les locuteurs au-delà de sa limite d’emplacementshttps://chiosa.app/papers/supermimic-scaling-humanoid-whole-body-control-with-one-differentiable-world-model-2610-28480Chiosaen2026-10-21T16:19:08ZOne learned model helps humanoid controllers scale across motionshttps://chiosa.app/papers/supermimic-scaling-humanoid-whole-body-control-with-one-differentiable-world-model-2610-28480?lang=itChiosait2026-10-21T16:19:08ZUn unico modello appreso aiuta i controller umanoidi a scalare su molti movimentihttps://chiosa.app/papers/supermimic-scaling-humanoid-whole-body-control-with-one-differentiable-world-model-2610-28480?lang=esChiosaes2026-10-21T16:19:08ZUn modelo aprendido ayuda a escalar el control humanoide a muchos movimientoshttps://chiosa.app/papers/supermimic-scaling-humanoid-whole-body-control-with-one-differentiable-world-model-2610-28480?lang=frChiosafr2026-10-21T16:19:08ZUn modèle appris aide les contrôleurs humanoïdes à gérer davantage de mouvementshttps://chiosa.app/papers/veocc-learning-persistent-voxel-feature-maps-for-embodied-online-semantic-occupancy-mapping-and-offline-refin-2610-27704Chiosaen2026-10-21T16:19:08ZA persistent voxel map links live mapping to later refinementhttps://chiosa.app/papers/veocc-learning-persistent-voxel-feature-maps-for-embodied-online-semantic-occupancy-mapping-and-offline-refin-2610-27704?lang=itChiosait2026-10-21T16:19:08ZUna mappa persistente di voxel collega la mappatura in tempo reale alla rifinitura successivahttps://chiosa.app/papers/veocc-learning-persistent-voxel-feature-maps-for-embodied-online-semantic-occupancy-mapping-and-offline-refin-2610-27704?lang=esChiosaes2026-10-21T16:19:08ZUn mapa persistente de vóxeles conecta el mapeo en directo con el refinamiento posteriorhttps://chiosa.app/papers/veocc-learning-persistent-voxel-feature-maps-for-embodied-online-semantic-occupancy-mapping-and-offline-refin-2610-27704?lang=frChiosafr2026-10-21T16:19:08ZUne carte persistante de voxels relie cartographie en direct et affinement ultérieurhttps://chiosa.app/papers/when-empathy-misses-the-goal-a-benchmark-for-goal-displacement-in-llm-advice-2610-25522Chiosaen2026-10-21T16:19:08ZA benchmark measures when reassurance leaves advice goals unmethttps://chiosa.app/papers/when-empathy-misses-the-goal-a-benchmark-for-goal-displacement-in-llm-advice-2610-25522?lang=itChiosait2026-10-21T16:19:08ZUn benchmark misura quando le rassicurazioni lasciano irrisolti gli obiettivihttps://chiosa.app/papers/when-empathy-misses-the-goal-a-benchmark-for-goal-displacement-in-llm-advice-2610-25522?lang=esChiosaes2026-10-21T16:19:08ZUn benchmark mide cuándo el consuelo deja sin resolver objetivos prácticoshttps://chiosa.app/papers/when-empathy-misses-the-goal-a-benchmark-for-goal-displacement-in-llm-advice-2610-25522?lang=frChiosafr2026-10-21T16:19:08ZUn benchmark mesure quand les paroles rassurantes détournent le conseil de son buthttps://chiosa.app/papers/autoredclaw-automated-red-teaming-for-claw-style-agents-2610-27244Chiosaen2026-10-21T15:30:14ZAutoRedClaw tests attacks on persistent agent statehttps://chiosa.app/papers/bct-bayes-consistent-tempering-for-flow-language-models-2610-27641Chiosaen2026-10-21T15:30:14ZA flow-wide method improves low-temperature generationhttps://chiosa.app/papers/context-aware-prompt-injection-detection-via-small-language-models-in-rag-pipelines-nokast-securerag-2610-28364Chiosaen2026-10-21T15:30:14ZA small RAG detector uses context to spot hidden attackshttps://chiosa.app/papers/context-aware-prompt-injection-detection-via-small-language-models-in-rag-pipelines-nokast-securerag-2610-28364?lang=esChiosaes2026-10-21T15:30:14ZUn detector RAG pequeño usa el contexto para detectar ataques ocultoshttps://chiosa.app/papers/easformer-environment-action-state-alignment-for-industrial-generative-ranking-2610-27691Chiosaen2026-10-21T15:30:14ZAligning context fields improved industrial app rankinghttps://chiosa.app/papers/graphcast-mamba-learning-non-markovian-corrections-for-weather-forecasting-2610-28512Chiosaen2026-10-21T15:30:14ZA memory branch improves GraphCast’s longer-range forecastshttps://chiosa.app/papers/matrix-game-4-0-harnessing-video-models-for-real-time-playable-game-worlds-2610-27999Chiosaen2026-10-21T15:30:14ZA game engine keeps playable worlds coherent as video adds detailhttps://chiosa.app/papers/on-the-limits-of-scale-inverse-scaling-in-vision-language-models-2610-27360Chiosaen2026-10-21T15:30:14ZSmaller vision models can outperform larger ones on specific taskshttps://chiosa.app/papers/prove-proposer-verifier-decoding-2610-27815Chiosaen2026-10-21T15:30:14ZProVe speeds token generation by checking proposed blockshttps://chiosa.app/papers/rem-what-to-store-when-to-recall-what-to-forget-in-experience-memory-for-coding-agents-2610-27377Chiosaen2026-10-21T15:30:14ZREM times and trims memory for coding agentshttps://chiosa.app/papers/solarrenderer-few-step-generative-reference-rendering-2610-28630Chiosaen2026-10-21T15:30:14ZA video renderer follows new scene formats in four stepshttps://chiosa.app/papers/attractive-faces-skew-text-to-image-reward-models-and-leaderboards-2610-28195Chiosaen2026-10-21T07:20:38ZAttractive faces shape image rankings and scoreshttps://chiosa.app/papers/attractive-faces-skew-text-to-image-reward-models-and-leaderboards-2610-28195?lang=itChiosait2026-10-21T07:20:38ZL’attrattiva dei volti influenza classifiche e punteggi delle immaginihttps://chiosa.app/papers/attractive-faces-skew-text-to-image-reward-models-and-leaderboards-2610-28195?lang=esChiosaes2026-10-21T07:20:38ZEl atractivo influye en las clasificaciones y puntuaciones de imágeneshttps://chiosa.app/papers/auditing-the-product-not-the-recursion-the-evaluation-evidence-behind-recursive-self-improvement-claims-2610-27610Chiosaen2026-10-21T07:20:38ZStudies test final self-improving systems more than the loop behind themhttps://chiosa.app/papers/baseline-and-incremental-user-item-and-request-debiasing-in-instagram-feed-ranking-2610-27423Chiosaen2026-10-21T07:20:38ZA ranking method separates engagement from its baselinehttps://chiosa.app/papers/benchmarking-cpu-gpu-and-ml-power-flow-solvers-from-14-to-70-000-buses-2610-27930Chiosaen2026-10-21T07:20:38ZA broad power-flow test finds physics solvers can match learned modelshttps://chiosa.app/papers/bitmtp-when-multi-token-prediction-meets-low-bit-large-language-models-2610-28500Chiosaen2026-10-21T07:20:38ZA coordinated system makes low-bit language models generate in blockshttps://chiosa.app/papers/bitmtp-when-multi-token-prediction-meets-low-bit-large-language-models-2610-28500?lang=esChiosaes2026-10-21T07:20:38ZUn sistema coordinado permite generar por bloques a modelos de lenguaje de baja precisiónhttps://chiosa.app/papers/cache-engineering-for-agents-2610-28577Chiosaen2026-10-21T07:20:38ZAgents can drop old cache states without rewriting their historyhttps://chiosa.app/papers/cache-engineering-for-agents-2610-28577?lang=frChiosafr2026-10-21T07:20:38ZLes agents peuvent retirer d’anciens états du cache sans réécrire leur historiquehttps://chiosa.app/papers/capable-teacher-myopic-scorer-reward-free-teacher-repair-for-agentic-on-policy-distillation-2610-28586Chiosaen2026-10-21T07:20:38ZA repaired teacher helps agents finish more taskshttps://chiosa.app/papers/capable-teacher-myopic-scorer-reward-free-teacher-repair-for-agentic-on-policy-distillation-2610-28586?lang=itChiosait2026-10-21T07:20:38ZUn teacher con punteggi corretti aiuta gli agenti a completare più compitihttps://chiosa.app/papers/capable-teacher-myopic-scorer-reward-free-teacher-repair-for-agentic-on-policy-distillation-2610-28586?lang=esChiosaes2026-10-21T07:20:38ZUn docente con puntuaciones corregidas ayuda a los agentes a completar más tareashttps://chiosa.app/papers/echo-efficient-cascade-with-homogeneous-operators-for-distillation-guided-100k-sequence-modeling-2610-28569Chiosaen2026-10-21T07:20:38ZECHO keeps long user histories searchable for recommendationhttps://chiosa.app/papers/echo-efficient-cascade-with-homogeneous-operators-for-distillation-guided-100k-sequence-modeling-2610-28569?lang=esChiosaes2026-10-21T07:20:38ZECHO permite buscar en historiales largos para recomendar contenidohttps://chiosa.app/papers/echo-efficient-cascade-with-homogeneous-operators-for-distillation-guided-100k-sequence-modeling-2610-28569?lang=frChiosafr2026-10-21T07:20:38ZECHO facilite la recherche dans les longs historiques d’activitéhttps://chiosa.app/papers/evolving-agent-interfaces-2610-28601Chiosaen2026-10-21T07:20:38ZAgent S4 evolves computer-use tools from task experiencehttps://chiosa.app/papers/evolving-agent-interfaces-2610-28601?lang=itChiosait2026-10-21T07:20:38ZAgent S4 fa evolvere gli strumenti per usare il computer a partire dall’esperienzahttps://chiosa.app/papers/evolving-agent-interfaces-2610-28601?lang=esChiosaes2026-10-21T07:20:38ZAgent S4 hace evolucionar herramientas para usar computadoras a partir de tareashttps://chiosa.app/papers/evolving-agent-interfaces-2610-28601?lang=frChiosafr2026-10-21T07:20:38ZAgent S4 fait évoluer les outils informatiques à partir des tâcheshttps://chiosa.app/papers/execution-time-validation-of-context-carrying-action-intents-in-industrial-cyber-physical-systems-2610-27971Chiosaen2026-10-21T07:20:38ZA controller-side check can stop commands based on stale statehttps://chiosa.app/papers/influence-is-the-target-response-jacobian-times-residuals-2610-27689Chiosaen2026-10-21T07:20:38ZA new method tracks how training targets change predictionshttps://chiosa.app/papers/learning-the-4d-world-through-point-trajectory-forecasting-2610-28594Chiosaen2026-10-21T07:20:38ZPoint trajectories make multi-view forecasts more coherenthttps://chiosa.app/papers/learning-the-4d-world-through-point-trajectory-forecasting-2610-28594?lang=itChiosait2026-10-21T07:20:38ZLe traiettorie dei punti rendono più coerenti le previsioni multi-inquadraturahttps://chiosa.app/papers/pact-vla-speculative-action-chunk-verification-with-pre-commit-observations-2610-28019Chiosaen2026-10-21T07:20:38ZRobots can choose fresher action chunks during inferencehttps://chiosa.app/papers/physical-canvas-a-vision-tactile-world-model-for-robot-policy-evaluation-and-learning-2610-28613Chiosaen2026-10-21T07:20:38ZA robot world model predicts touch and task outcomeshttps://chiosa.app/papers/physical-canvas-a-vision-tactile-world-model-for-robot-policy-evaluation-and-learning-2610-28613?lang=itChiosait2026-10-21T07:20:38ZUn modello del mondo per robot prevede contatti ed esitihttps://chiosa.app/papers/physical-canvas-a-vision-tactile-world-model-for-robot-policy-evaluation-and-learning-2610-28613?lang=esChiosaes2026-10-21T07:20:38ZUn modelo del mundo para robots predice el tacto y los resultados de tareashttps://chiosa.app/papers/predicting-silent-failures-of-learned-inference-under-restricted-access-what-measurement-physics-and-prior-in-2610-28155Chiosaen2026-10-21T07:20:38ZA score can rank when CT systems fail without warninghttps://chiosa.app/papers/racer-hunting-gpu-kernel-bugs-with-symbolic-equivalence-checking-2610-28429Chiosaen2026-10-21T07:20:38ZRacer checks whether GPU kernel rewrites preserve their functionhttps://chiosa.app/papers/racer-hunting-gpu-kernel-bugs-with-symbolic-equivalence-checking-2610-28429?lang=itChiosait2026-10-21T07:20:38ZRacer verifica che le riscritture dei kernel GPU preservino la funzionehttps://chiosa.app/papers/relative-representations-enable-portable-white-box-monitoring-across-language-models-2610-28366Chiosaen2026-10-21T07:20:38ZShared anchors let language-model monitors transfer across modelshttps://chiosa.app/papers/spar-stepwise-personalized-autoregressive-recommendation-with-prefix-balanced-semantic-ids-2610-27898Chiosaen2026-10-21T07:20:38ZSPAR tailors each recommendation choice to user historyhttps://chiosa.app/papers/stratified-sparse-attention-reducing-the-sparse-to-dense-gap-at-extreme-sparsity-2610-28441Chiosaen2026-10-21T07:20:38ZScore-guided sampling improves sparse attentionhttps://chiosa.app/papers/stratified-sparse-attention-reducing-the-sparse-to-dense-gap-at-extreme-sparsity-2610-28441?lang=itChiosait2026-10-21T07:20:38ZIl campionamento guidato migliora l’attenzione sparsahttps://chiosa.app/papers/stratified-sparse-attention-reducing-the-sparse-to-dense-gap-at-extreme-sparsity-2610-28441?lang=esChiosaes2026-10-21T07:20:38ZEl muestreo guiado por puntuaciones mejora la atención dispersahttps://chiosa.app/papers/sweepann-a-gpu-accelerated-large-k-approximate-vector-search-for-drug-discovery-2610-27306Chiosaen2026-10-21T07:20:38ZSweepANN speeds broad molecule searches on GPUshttps://chiosa.app/papers/testing-tls-1-3-pqc-on-constrained-devices-and-microcontrollers-2610-27766Chiosaen2026-10-21T07:20:38ZPost-quantum TLS can be faster on small deviceshttps://chiosa.app/papers/toolflation-seller-agents-distort-tool-markets-through-spontaneous-generative-engine-optimization-2610-28454Chiosaen2026-10-21T07:20:38ZInflated tool listings sometimes mislead agent buyershttps://chiosa.app/papers/toolflation-seller-agents-distort-tool-markets-through-spontaneous-generative-engine-optimization-2610-28454?lang=itChiosait2026-10-21T07:20:38ZGli annunci gonfiati a volte ingannano gli agenti acquirentihttps://chiosa.app/papers/toolflation-seller-agents-distort-tool-markets-through-spontaneous-generative-engine-optimization-2610-28454?lang=esChiosaes2026-10-21T07:20:38ZLos anuncios inflados a veces desvían a los agentes compradoreshttps://chiosa.app/papers/two-is-enough-binary-classification-priors-suffice-for-multi-class-in-context-tabular-prediction-2610-27569Chiosaen2026-10-21T07:20:38ZTwo-class pretraining still supports multiclass table predictionshttps://chiosa.app/papers/understanding-the-benefits-of-scaffolds-through-computational-separations-2610-27157Chiosaen2026-10-21T07:20:38ZSame-size students struggle to match model harnesseshttps://chiosa.app/papers/when-does-training-on-synthetic-data-provably-work-2610-28036Chiosaen2026-10-21T07:20:38ZSynthetic training can fail where generated data leave gapshttps://chiosa.app/papers/you-are-the-trigger-speaker-activated-backdoors-2610-27210Chiosaen2026-10-21T07:20:38ZA speaker’s ordinary voice can trigger a speech-model backdoor