https://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 backdoorhttps://chiosa.app/papers/agent-world-model-in-the-wild-computer-use-agent-environment-synthesis-2610-26828Chiosaen2026-10-20T18:07:34ZWildAWM creates computer worlds for cross-interface agent traininghttps://chiosa.app/papers/agr-agentic-generative-retrieval-with-tool-augmented-search-2610-26831Chiosaen2026-10-20T18:07:34ZSearch retrieval can request useful features as it generates resultshttps://chiosa.app/papers/agr-agentic-generative-retrieval-with-tool-augmented-search-2610-26831?lang=itChiosait2026-10-20T18:07:34ZLa ricerca può richiedere caratteristiche utili mentre genera risultatihttps://chiosa.app/papers/brushoff-stroke-based-re-rendering-as-a-watermark-removal-attack-on-painting-2610-26682Chiosaen2026-10-20T18:07:34ZBrush strokes remove marks that common edits leave behindhttps://chiosa.app/papers/cartender-verifiable-language-conditioned-driving-by-learning-the-drives-not-taken-2610-26390Chiosaen2026-10-20T18:07:34ZA driving model responds better when it learns alternate pathshttps://chiosa.app/papers/harnesspro-recursive-harness-self-improvement-with-pareto-optimization-for-performance-cost-trade-offs-2610-26770Chiosaen2026-10-20T18:07:34ZHarnessPro improves agent success at lower costhttps://chiosa.app/papers/harnesspro-recursive-harness-self-improvement-with-pareto-optimization-for-performance-cost-trade-offs-2610-26770?lang=itChiosait2026-10-20T18:07:34ZHarnessPro aumenta il successo degli agenti a costo inferiorehttps://chiosa.app/papers/monsoon-scalable-spontaneous-speech-collection-for-low-resource-asr-in-50-languages-2610-26776Chiosaen2026-10-20T18:07:34ZMonsoon builds speech data that improves conversational recognitionhttps://chiosa.app/papers/monsoon-scalable-spontaneous-speech-collection-for-low-resource-asr-in-50-languages-2610-26776?lang=esChiosaes2026-10-20T18:07:34ZMonsoon crea datos de habla que mejoran el reconocimiento conversacionalhttps://chiosa.app/papers/scaling-parameter-efficient-fine-tuning-for-brain-encoding-2610-26802Chiosaen2026-10-20T18:07:34ZSmall adapters improve brain-response predictions across tested modelshttps://chiosa.app/papers/scaling-parameter-efficient-fine-tuning-for-brain-encoding-2610-26802?lang=frChiosafr2026-10-20T18:07:34ZDe petits adaptateurs améliorent les prédictions cérébrales des modèles testéshttps://chiosa.app/papers/state-world-models-execute-the-rules-generate-the-pixels-2610-26811Chiosaen2026-10-20T18:07:34ZA video framework applies world rules before rendering actionshttps://chiosa.app/papers/state-world-models-execute-the-rules-generate-the-pixels-2610-26811?lang=itChiosait2026-10-20T18:07:34ZUn framework video applica le regole del mondo prima di renderizzare le azionihttps://chiosa.app/papers/state-world-models-execute-the-rules-generate-the-pixels-2610-26811?lang=frChiosafr2026-10-20T18:07:34ZUn cadre applique les règles du monde avant de générer les actionshttps://chiosa.app/papers/tandem-serving-hybrid-linear-attention-gui-agents-on-mobile-npus-2610-26660Chiosaen2026-10-20T18:07:34ZTandem speeds hybrid phone-agent model servinghttps://chiosa.app/papers/text-to-image-generative-modeling-without-language-pretraining-2610-26863Chiosaen2026-10-20T18:07:34ZText-to-image models can learn without text-only pretraininghttps://chiosa.app/papers/tokengate-adapting-llms-for-fast-and-memory-efficient-prefill-with-learned-token-pruning-2610-26754Chiosaen2026-10-20T18:07:34ZTokenGate cuts long-prompt processing while preserving accuracyhttps://chiosa.app/papers/a-cue-s-hidden-price-auditing-seller-influence-on-ai-shoppers-2610-25843Chiosaen2026-10-20T08:16:02ZA price sweep reveals how seller cues sway AI shoppinghttps://chiosa.app/papers/beyond-the-record-evaluating-probabilistic-ai-weather-forecasts-deep-in-the-tail-2610-25545Chiosaen2026-10-20T08:16:02ZAI weather forecasts retain skill beyond local heat recordshttps://chiosa.app/papers/claim-laundering-when-agent-decision-models-trust-records-over-reality-2610-25947Chiosaen2026-10-20T08:16:02ZA model can see a failed step yet trust the agent’s recordhttps://chiosa.app/papers/claim-laundering-when-agent-decision-models-trust-records-over-reality-2610-25947?lang=itChiosait2026-10-20T08:16:02ZUn modello può rilevare un passaggio fallito e fidarsi comunque del registro dell’agentehttps://chiosa.app/papers/clean-forcing-drift-resistant-autoregressive-video-diffusion-with-a-frozen-base-2610-25634Chiosaen2026-10-20T08:16:02ZA small corrector reduces drift in long generated videoshttps://chiosa.app/papers/concerns-in-benchmarking-jailbreaks-an-empirical-study-of-attack-success-rates-2610-26595Chiosaen2026-10-20T08:16:02ZJailbreak rankings shift with evaluators and attempt settingshttps://chiosa.app/papers/concerns-in-benchmarking-jailbreaks-an-empirical-study-of-attack-success-rates-2610-26595?lang=itChiosait2026-10-20T08:16:02ZLe classifiche dei jailbreak cambiano con valutatori e tentativihttps://chiosa.app/papers/concerns-in-benchmarking-jailbreaks-an-empirical-study-of-attack-success-rates-2610-26595?lang=esChiosaes2026-10-20T08:16:02ZLas clasificaciones de jailbreak cambian según el evaluador y los intentoshttps://chiosa.app/papers/concerns-in-benchmarking-jailbreaks-an-empirical-study-of-attack-success-rates-2610-26595?lang=frChiosafr2026-10-20T08:16:02ZLe classement des jailbreaks varie selon l’évaluateur et les tentativeshttps://chiosa.app/papers/connection-escrow-holding-ai-agent-pod-egress-in-the-kernel-until-an-isolated-verifier-rules-2610-26501Chiosaen2026-10-20T08:16:02ZA kernel gate ties agent approvals to each connectionhttps://chiosa.app/papers/consistent-llm-call-handling-across-java-frameworks-a-reference-implementation-and-benchmark-2610-25480Chiosaen2026-10-20T08:16:02ZA shared HTTP guard makes Java model calls more consistenthttps://chiosa.app/papers/learn-the-interface-not-the-implementation-output-representation-dominates-training-regime-in-llm-based-rtl-g-2610-25881Chiosaen2026-10-20T08:16:02ZCompact configurations improve hardware generation in one SECDED taskhttps://chiosa.app/papers/learning-from-fleet-experience-a-collective-learning-paradigm-for-robots-2610-25736Chiosaen2026-10-20T08:16:02ZRobot fleets improve a shared policy from task experiencehttps://chiosa.app/papers/logit-averaging-during-training-sets-a-new-state-of-the-art-for-non-invasive-speech-bci-2610-26347Chiosaen2026-10-20T08:16:02ZTraining-time averaging leads across most MEG taskshttps://chiosa.app/papers/neural-video-coding-under-limited-delay-theoretical-optimality-and-system-design-2610-25729Chiosaen2026-10-20T08:16:02ZFuture-frame clues help neural codecs compress videohttps://chiosa.app/papers/one-fact-many-places-redundant-evidence-in-long-visual-documents-breaks-single-gold-evaluation-of-retrieval-c-2610-26401Chiosaen2026-10-20T08:16:02ZRepeated facts can distort document evidence testshttps://chiosa.app/papers/one-fact-many-places-redundant-evidence-in-long-visual-documents-breaks-single-gold-evaluation-of-retrieval-c-2610-26401?lang=frChiosafr2026-10-20T08:16:02ZLes faits répétés peuvent fausser les tests de preuve documentairehttps://chiosa.app/papers/openvlharness-real-world-visual-agentic-tool-use-with-multimodal-memory-2610-26860Chiosaen2026-10-20T08:16:02ZA system helps visual agents gather and reuse evidencehttps://chiosa.app/papers/openvlharness-real-world-visual-agentic-tool-use-with-multimodal-memory-2610-26860?lang=itChiosait2026-10-20T08:16:02ZUn sistema aiuta gli agenti visivi a raccogliere e riutilizzare evidenzehttps://chiosa.app/papers/parallel-language-models-via-variational-decoding-2610-26693Chiosaen2026-10-20T08:16:02ZParallel language models coordinate several token predictions at oncehttps://chiosa.app/papers/parallel-language-models-via-variational-decoding-2610-26693?lang=itChiosait2026-10-20T08:16:02ZI modelli linguistici paralleli coordinano più previsioni di token insiemehttps://chiosa.app/papers/reasoning-aware-multicalibrated-reliability-predictors-for-language-models-2610-26645Chiosaen2026-10-20T08:16:02ZReasoning traces help reveal hidden calibration errorshttps://chiosa.app/papers/reasoning-aware-multicalibrated-reliability-predictors-for-language-models-2610-26645?lang=esChiosaes2026-10-20T08:16:02ZLas trazas de razonamiento ayudan a revelar errores de calibración ocultoshttps://chiosa.app/papers/same-simulation-different-evidence-where-retrieved-tool-output-costs-llm-agents-accuracy-2610-26836Chiosaen2026-10-20T08:16:02ZHow simulator report delivery changes agents’ answershttps://chiosa.app/papers/same-simulation-different-evidence-where-retrieved-tool-output-costs-llm-agents-accuracy-2610-26836?lang=itChiosait2026-10-20T08:16:02ZCome la consegna dei report del simulatore cambia le risposte degli agentihttps://chiosa.app/papers/same-simulation-different-evidence-where-retrieved-tool-output-costs-llm-agents-accuracy-2610-26836?lang=esChiosaes2026-10-20T08:16:02ZCómo cambia las respuestas de los agentes la entrega del informe del simuladorhttps://chiosa.app/papers/same-simulation-different-evidence-where-retrieved-tool-output-costs-llm-agents-accuracy-2610-26836?lang=frChiosafr2026-10-20T08:16:02ZComment le mode de transmission du rapport change les réponses des agentshttps://chiosa.app/papers/selling-in-the-wild-benchmark-and-randomized-field-evidence-for-a-sales-agent-trained-on-commercial-conversat-2610-25461Chiosaen2026-10-20T08:16:02ZJavo raises sales outcomes in live website testshttps://chiosa.app/papers/streamahead-real-time-streaming-video-question-answering-via-adaptive-precomputation-2610-25551Chiosaen2026-10-20T08:16:02ZStreamAhead adjusts video processing before questions arrivehttps://chiosa.app/papers/strucchunk-structure-aware-retrieval-for-legal-document-rag-2610-26313Chiosaen2026-10-20T08:16:02ZLegal search improves when chunks preserve section structurehttps://chiosa.app/papers/swe-residual-evaluating-starting-state-robustness-of-coding-agents-2610-25899Chiosaen2026-10-20T08:16:02ZInherited software work exposes a gap in coding agentshttps://chiosa.app/papers/the-scheduler-is-a-hidden-retriever-how-asynchrony-shapes-evidence-acquisition-in-search-agents-2610-26310Chiosaen2026-10-20T08:16:02ZWhen search results arrive in a different order, agents seek different evidencehttps://chiosa.app/papers/token-set-choice-confounds-pope-a-systematic-audit-of-yes-no-extraction-in-vlm-hallucination-evaluation-2610-25964Chiosaen2026-10-20T08:16:02ZToken choice can change measured hallucination scoreshttps://chiosa.app/papers/token-set-choice-confounds-pope-a-systematic-audit-of-yes-no-extraction-in-vlm-hallucination-evaluation-2610-25964?lang=itChiosait2026-10-20T08:16:02ZLa scelta dei token può cambiare i punteggi di allucinazione misuratihttps://chiosa.app/papers/towards-architectural-level-safety-control-relocating-hazardous-knowledge-into-removable-experts-in-mixture-o-2610-25791Chiosaen2026-10-20T08:16:02ZREX moves hazardous knowledge into removable expertshttps://chiosa.app/papers/truncate-or-not-a-scaling-study-of-looped-transformers-with-truncated-backpropagation-2610-26030Chiosaen2026-10-20T08:16:02ZTwo fully trained loops can match large models with fewer parametershttps://chiosa.app/papers/veruseval-evaluating-llm-generated-verus-specifications-beyond-verifier-acceptance-2610-26464Chiosaen2026-10-20T08:16:02ZVerifier acceptance can miss weak generated contractshttps://chiosa.app/papers/when-coding-agents-outpace-review-evaluating-prd-driven-development-in-mature-enterprise-repositories-2610-26394Chiosaen2026-10-20T08:16:02ZPACE-Bench checks whether coding agents deliver full requestshttps://chiosa.app/papers/when-coding-agents-outpace-review-evaluating-prd-driven-development-in-mature-enterprise-repositories-2610-26394?lang=itChiosait2026-10-20T08:16:02ZPACE-Bench verifica se gli agenti di coding soddisfano le richieste completehttps://chiosa.app/papers/when-coding-agents-outpace-review-evaluating-prd-driven-development-in-mature-enterprise-repositories-2610-26394?lang=esChiosaes2026-10-20T08:16:02ZPACE-Bench comprueba si los agentes de programación entregan solicitudes completashttps://chiosa.app/papers/when-guidance-becomes-a-guard-early-interception-of-unsafe-inputs-in-text-to-image-generation-2610-26452Chiosaen2026-10-20T08:16:02ZEarly signals can flag risky image promptshttps://chiosa.app/papers/whose-credential-is-it-how-owner-attribution-in-agent-memoryshapes-cross-user-account-misuse-2610-25707Chiosaen2026-10-20T08:16:02ZHow shared memory can lead agents into the wrong accounthttps://chiosa.app/papers/yutela-a-scalable-edge-cloud-aiot-system-for-multi-site-video-anomaly-detection-with-scene-specific-adaptatio-2610-26468Chiosaen2026-10-20T08:16:02ZA camera system shares edge work and adapts models centrallyhttps://chiosa.app/papers/yutela-a-scalable-edge-cloud-aiot-system-for-multi-site-video-anomaly-detection-with-scene-specific-adaptatio-2610-26468?lang=frChiosafr2026-10-20T08:16:02ZUn système de caméras partage le calcul local et adapte ses modèles à distance