https://chiosa.app/papers/youtu-parsing-omni-one-encoder-one-schema-all-modalities-2610-39301Chiosaen2026-10-30T19:24:09ZOne parser brings grounded records to images, audio, and videohttps://chiosa.app/papers/a-broader-look-into-mllm-s-retrieval-heads-2610-32411Chiosaen2026-10-30T14:48:53ZA small set of heads helps multimodal models find evidencehttps://chiosa.app/papers/a-rsi-adaptive-task-refresh-for-zero-data-multimodal-self-improvement-2610-38568Chiosaen2026-10-30T14:48:53ZTraining logs guide when multimodal tasks are replacedhttps://chiosa.app/papers/advancing-clinical-genomic-analysis-with-a-skill-centred-agent-2610-40556Chiosaen2026-10-30T14:48:53ZClinGeX builds genomic workflows from expert-curated resourceshttps://chiosa.app/papers/agent-wise-test-time-normalization-for-camera-based-cooperative-perception-with-corrupted-collaborators-2610-39505Chiosaen2026-10-30T14:48:53ZSeparate camera statistics help cooperative detection under uneven corruptionhttps://chiosa.app/papers/agentic-llm-reasoning-in-pediatric-diabetes-outcome-prediction-from-multimodal-medical-records-2610-40379Chiosaen2026-10-30T14:48:53ZA clinical reasoning pipeline predicts pediatric diabetes outcomeshttps://chiosa.app/papers/appreciation-teaches-unauthorized-execution-self-evolution-degrades-the-robustness-of-personal-agents-to-indi-2610-39122Chiosaen2026-10-30T14:48:53ZFeedback learning can weaken agents’ authorization checkshttps://chiosa.app/papers/beyond-atol-and-rtol-sound-test-oracles-for-low-precision-gpu-kernels-2610-38983Chiosaen2026-10-30T14:48:53ZA GPU kernel checker adapts its error limits to each inputhttps://chiosa.app/papers/beyond-ips-reliable-counterfactual-evaluation-in-multi-stage-ad-systems-without-logged-propensities-2610-40112Chiosaen2026-10-30T14:48:53ZA reward model helps rank ads from incomplete logshttps://chiosa.app/papers/dwise-denoising-workload-informed-scheduling-engine-2610-39852Chiosaen2026-10-30T14:48:53ZA scheduler cuts delays for block-diffusion requestshttps://chiosa.app/papers/efficient-scalable-oversight-via-rewinding-2610-40535Chiosaen2026-10-30T14:48:53ZRewinding lets verifiers check robust computations efficientlyhttps://chiosa.app/papers/fast-and-accurate-neural-triage-decoding-of-ultra-high-rate-quantum-ldpc-codes-2610-40490Chiosaen2026-10-30T14:48:53ZNeural triage decoding speeds correction for large qLDPC codeshttps://chiosa.app/papers/gpu-resident-speculative-decoding-for-in-browser-llm-inference-with-webgpu-2610-39761Chiosaen2026-10-30T14:48:53ZA browser runtime adapts language model decoding to each GPUhttps://chiosa.app/papers/hairdeck-animation-ready-stylized-hair-cards-from-a-single-image-2610-40599Chiosaen2026-10-30T14:48:53ZHairDeck creates animated stylized hair cards from imageshttps://chiosa.app/papers/how-much-should-a-vla-trust-its-reasoning-step-level-guidance-as-a-measured-action-value-function-2610-40002Chiosaen2026-10-30T14:48:53ZA driving system learns how strongly reasoning should steer its planshttps://chiosa.app/papers/intera11y-interactive-web-accessibility-error-detection-with-llm-agents-2610-39488Chiosaen2026-10-30T14:48:53ZInteractive tools help agents check web accessibility more reliablyhttps://chiosa.app/papers/intrinsic-distribution-matching-2610-39633Chiosaen2026-10-30T14:48:53ZFeature matching helps fast image models render long texthttps://chiosa.app/papers/judged-in-company-in-context-batching-makes-llm-verdicts-depend-on-other-items-2610-40241Chiosaen2026-10-30T14:48:53ZBatching changes many language-model grading decisionshttps://chiosa.app/papers/l3g-world-real-time-infinite-world-generation-with-latent-3d-gaussian-memory-2610-40614Chiosaen2026-10-30T14:48:53ZA 3D scene memory helps video worlds stay consistent on returnhttps://chiosa.app/papers/look-only-when-needed-certificate-guided-visual-routing-for-efficient-diffusion-vlms-2610-36671Chiosaen2026-10-30T14:48:53ZA decoding method skips image processing when predictions agreehttps://chiosa.app/papers/mccl-training-pytorch-models-across-a-fleet-of-macs-at-skywalker-sound-2610-39029Chiosaen2026-10-30T14:48:53ZA PyTorch backend lets Mac GPUs train together over Ethernethttps://chiosa.app/papers/measuring-organizational-influence-on-digital-news-an-information-theoretic-framework-for-media-pluralism-and-2610-40172Chiosaen2026-10-30T14:48:53ZA framework measures ownership patterns in newshttps://chiosa.app/papers/mind-the-gap-mtg-ad-dataset-and-fine-grained-evaluation-for-end-to-end-inline-audio-descriptions-2610-39955Chiosaen2026-10-30T14:48:53ZA full-video dataset reveals audio description trade-offshttps://chiosa.app/papers/on-the-fundamental-limits-of-prefill-based-decoding-length-prediction-2610-40541Chiosaen2026-10-30T14:48:53ZRandomness sets a floor on predicting language model response lengthhttps://chiosa.app/papers/online-dense-reinforcement-learning-with-planning-grounding-agent-for-ui-navigation-on-live-ios-apps-2610-39264Chiosaen2026-10-30T14:48:53ZTraining UI agents on live apps helps them transfer beyond iOShttps://chiosa.app/papers/pcm-a-proof-carrying-message-protocol-for-verifiable-multi-agent-communication-2610-39109Chiosaen2026-10-30T14:48:53ZA protocol lets agents check evidence behind claimshttps://chiosa.app/papers/personacuabench-benchmarking-computer-use-agents-serving-diverse-personas-2610-22990Chiosaen2026-10-30T14:48:53ZA benchmark shows task completion can miss user needshttps://chiosa.app/papers/physvlmm-interaction-conditioned-physical-belief-maps-for-articulated-objects-in-robot-scene-maps-2610-40539Chiosaen2026-10-30T14:48:53ZRobot maps can predict how untouched drawers respond to pullshttps://chiosa.app/papers/radiology-guideline-derived-decision-graph-for-efficient-clinical-decision-support-2610-40327Chiosaen2026-10-30T14:48:53ZDecision paths help models follow radiology guidelineshttps://chiosa.app/papers/raincheck-deferred-multimodal-prefill-for-efficient-multi-turn-mllm-inference-2610-39562Chiosaen2026-10-30T14:48:53ZRaincheck restores context after multimodal pruninghttps://chiosa.app/papers/reaction-precedents-extend-retrosynthetic-prediction-beyond-training-coverage-2610-40249Chiosaen2026-10-30T14:48:53ZRetrieved reactions help retrosynthesis beyond training coveragehttps://chiosa.app/papers/read-allocate-route-role-coupled-tokenization-for-pixel-space-generative-transformers-2610-40647Chiosaen2026-10-30T14:48:53ZSpecSlot separates image detail from global communicationhttps://chiosa.app/papers/rethinking-neural-thickets-without-weight-perturbations-2610-40649Chiosaen2026-10-30T14:48:53ZFrozen-model output shifts match many weight-based gainshttps://chiosa.app/papers/rethinking-pre-pretraining-2610-40051Chiosaen2026-10-30T14:48:53ZSynthetic training fails to beat text on fixed budgetshttps://chiosa.app/papers/retrieving-from-your-own-mistakes-on-policy-training-of-embedding-models-for-multi-hop-retrieval-augmented-ge-2610-40409Chiosaen2026-10-30T14:48:53ZTraining retrievers on their own search historieshttps://chiosa.app/papers/rfw-a-agentic-procedural-generation-of-400k-articulated-assets-over-500-categories-2610-40333Chiosaen2026-10-30T14:48:53ZAgents build reusable generators for articulated objectshttps://chiosa.app/papers/scarl-sequence-confidence-aligned-reinforcement-learning-2610-40407Chiosaen2026-10-30T14:48:53ZTraining updates reflect confidence in verified answershttps://chiosa.app/papers/shallowdefend-harnessing-shallow-safety-alignment-for-multi-turn-defender-2610-40627Chiosaen2026-10-30T14:48:53ZMaking a safety decision explicit helps models resist multi-turn attackshttps://chiosa.app/papers/tabletune-measured-self-correcting-draft-length-tables-for-dynamic-speculative-decoding-2610-38968Chiosaen2026-10-30T14:48:53ZA measured table helps vLLM adjust draft lengthhttps://chiosa.app/papers/tabular-foundation-models-are-not-a-shortcut-to-calibrated-clinical-risk-prediction-a-pre-registered-simulati-2610-39065Chiosaen2026-10-30T14:48:53ZTabular AI models did not reliably calibrate clinical riskshttps://chiosa.app/papers/testimony-from-timelines-evidence-grounded-significance-testing-of-temporal-clinical-hypotheses-2610-40619Chiosaen2026-10-30T14:48:53ZA benchmark checks the reasoning behind clinical timeline verdictshttps://chiosa.app/papers/touchbridge-tactile-conditioned-human-to-robot-transfer-for-dexterous-manipulation-2610-40349Chiosaen2026-10-30T14:48:53ZTouchBridge uses touch to transfer human demonstrationshttps://chiosa.app/papers/training-foundation-models-with-a-single-algorithm-2610-40564Chiosaen2026-10-30T14:48:53ZOne learning rule lets training data change across stageshttps://chiosa.app/papers/training-language-models-in-simulation-for-psychiatric-intake-2610-40476Chiosaen2026-10-30T14:48:53ZSimulation training improved psychiatric intake in controlled testshttps://chiosa.app/papers/ugr-unified-generative-ranking-for-heterogeneous-e-commerce-recommendation-2610-39426Chiosaen2026-10-30T14:48:53ZGenerating mixed recommendation lists improved tested outcomeshttps://chiosa.app/papers/utility-wam-correcting-future-induced-action-changes-2610-39367Chiosaen2026-10-30T14:48:53ZA robot controller repairs harmful visual futures and skips needless oneshttps://chiosa.app/papers/vibegame-prompt-to-game-development-with-ai-native-engine-and-self-evolving-adversarial-agent-team-2610-33106Chiosaen2026-10-30T14:48:53ZA framework helps agents build and test complete 2D gameshttps://chiosa.app/papers/videomembench-how-well-do-mllms-remember-in-video-conversations-2610-40131Chiosaen2026-10-30T14:48:53ZVideoMemBench tests memory across video conversationshttps://chiosa.app/papers/weviscut-the-whole-editing-room-in-one-agent-from-narration-to-long-form-video-2610-38352Chiosaen2026-10-30T14:48:53ZOne model coordinates long-form video productionhttps://chiosa.app/papers/what-makes-a-good-audio-prompt-for-zero-shot-tts-learning-prompt-selection-from-synthesis-outcomes-2610-40372Chiosaen2026-10-30T14:48:53ZChoosing a voice prompt by the speech it helps a model producehttps://chiosa.app/papers/when-should-ai-decide-defer-and-deviate-responsible-automation-for-deceased-donor-kidney-allocation-2610-39045Chiosaen2026-10-30T14:48:53ZInterpretable rules guide kidney allocation decisionshttps://chiosa.app/papers/where-do-vision-language-models-fail-at-3d-reasoning-2610-39639Chiosaen2026-10-30T14:48:53ZA 3D test reveals models struggle with complete color countshttps://chiosa.app/papers/who-owns-digital-news-and-who-gets-cited-measuring-media-concentration-across-77-countries-and-seven-ai-syste-2610-40164Chiosaen2026-10-30T14:48:53ZGrouping news sites by owner reveals more concentrated marketshttps://chiosa.app/papers/why-speculative-decoding-works-better-than-predicted-on-sparse-moe-models-2610-38981Chiosaen2026-10-30T14:48:53ZWhy sparse MoE models gain at low batch sizeshttps://chiosa.app/papers/worldprobe-when-video-world-models-fall-apart-under-long-horizon-spatial-exploration-2610-39721Chiosaen2026-10-30T14:48:53ZWorldProbe tests whether video worlds stay coherent as you explorehttps://chiosa.app/papers/your-benchmark-is-an-empirical-measure-over-difficulty-2610-29927Chiosaen2026-10-30T14:48:53ZWhy uneven question difficulty can skew test scoreshttps://chiosa.app/papers/your-lr-schedule-may-not-be-principled-effective-learning-rate-scheduling-in-weight-normalized-training-2610-40362Chiosaen2026-10-30T14:48:53ZA learning-rate schedule built around update sizehttps://chiosa.app/papers/realcli-toward-a-unified-evaluation-of-human-agent-collaboration-for-cli-agents-2610-22507Chiosaen2026-10-29T19:16:34ZCLI agents can finish tasks but miss collaboration checkshttps://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/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/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/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/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/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/card-contact-anchored-retargeting-for-dexterous-manipulation-2610-36539Chiosaen2026-10-29T11:00:41ZContact targets help robot hands reproduce human touchhttps://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/decision-models-as-judges-for-hallucination-detection-2610-37229Chiosaen2026-10-29T11:00:41ZDecision models catch some hallucinations, but confidence can misleadhttps://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/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/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/generative-representation-learning-for-scalable-latent-tokenization-2610-20533Chiosaen2026-10-29T11:00:41ZA new image tokenizer scales while resisting shortcut featureshttps://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/rsigen-reciprocal-self-improvement-for-agentic-visual-generation-2610-18688Chiosaen2026-10-29T11:00:41ZRSIgen links learning between image planners and generatorshttps://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/tulva-practical-asynchronous-threshold-fhe-2610-20521Chiosaen2026-10-29T11:00:41ZTulva lets enough committee members decrypt without being online togetherhttps://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/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-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/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 rules