https://llmdb.app/research https://llmdb.app/research/swarmevolve-latent-agent-swarms-for-evolutionary-discovery-and-optimization2026-11-06T20:14:54.930Z https://llmdb.app/research/scientist-world-grow-a-research-world-for-ai-scientists2026-11-07T18:27:57.777Z https://llmdb.app/research/xstack-a-benchmark-for-ml-repo-migration2026-11-07T18:27:57.777Z https://llmdb.app/research/user-embeddings-are-superpositions-of-interpretable-behavioral-modes2026-11-06T20:14:54.930Z https://llmdb.app/research/flowreconbench-accuracy-calibration-and-cost-of-learned-and-classical-flow-reconstruction-from-sparse-sensors2026-11-05T20:56:12.618Z https://llmdb.app/research/a-framework-for-context-enrichment-and-selective-robustness-in-llm-social-agents2026-11-05T20:56:12.618Z https://llmdb.app/research/dreamx-video-diffusion-model-is-a-universal-latent-action-learner2026-11-04T20:40:25.860Z https://llmdb.app/research/from-autonomous-agents-to-cognitive-symbionts-toward-ai-augmented-human-intelligence2026-11-04T20:40:25.860Z https://llmdb.app/research/pixel-a-co-designed-full-stack-robot-system-for-learning-general-purpose-mobile-manipulation2026-11-03T20:24:41.598Z https://llmdb.app/research/pixel-umi-learning-environment-aware-whole-body-manipulation-from-sensorized-human-demonstrations2026-11-03T20:24:41.598Z https://llmdb.app/research/flide-accelerating-decision-inference-with-exact-state-forking2026-11-02T22:36:19.496Z https://llmdb.app/research/latent-reasoning-in-continuous-space-for-unified-multimodal-models2026-11-02T22:36:19.496Z https://llmdb.app/research/luggage-re-identification-a-study-of-strategies-towards-a-real-world-application2026-11-01T18:44:38.557Z https://llmdb.app/research/elucidating-the-design-space-of-lm-data-attribution2026-10-30T18:58:03.488Z https://llmdb.app/research/propose-filter-release-scaling-noise-to-typical-sensitivity-via-private-filtering2026-10-30T18:58:03.488Z https://llmdb.app/research/rethinking-neural-thickets-without-weight-perturbations2026-10-31T18:09:51.808Z https://llmdb.app/research/read-allocate-route-role-coupled-tokenization-for-pixel-space-generative-transformers2026-10-31T18:09:51.808Z https://llmdb.app/research/adaptive-scenario-generation-for-kl-dro-around-a-learned-density-model2026-11-01T18:44:38.557Z https://llmdb.app/research/conformal-prediction-sets-quantify-information-gain-a-theoretical-perspective2026-10-07T19:41:35.560Z https://llmdb.app/research/qf3-fast-flow-rl-with-filtered-q-gradients2026-10-07T19:41:35.560Z https://llmdb.app/research/4dcodebench-benchmarking-agents-on-inverse-graphics-of-dynamic-scenes2026-10-05T21:21:14.477Z https://llmdb.app/research/less-decoder-is-more-encoder-geometric-representation-learning-from-novel-view-synthesis2026-10-05T21:21:14.477Z https://llmdb.app/research/kalibench-a-fine-grained-benchmark-for-cybersecurity-tool-use-on-kali-linux-with-runtime-free-verifiable-rewards2026-10-02T18:53:09.346Z https://llmdb.app/research/one-basis-to-animate-them-all-gaussian-blendshape-distillation-for-real-time-avatars2026-10-04T17:57:29.750Z https://llmdb.app/research/reconstruct-practice-go-real-guided-self-improvement-for-embodied-agents2026-10-04T17:57:29.750Z https://llmdb.app/research/skill-space-shooting-for-autonomous-robot-policy-improvement2026-09-30T18:46:42.049Z https://llmdb.app/research/imagine3d-llm-teaching-mllms-to-imagine-3d-scenes-before-answering2026-09-30T18:46:42.049Z https://llmdb.app/research/a-decentralized-partially-observable-team-decision-methodology-with-delayed-information-sharing2026-09-23T18:09:16.804Z https://llmdb.app/research/flash-dllm-io-aware-kv-caching-and-parallel-decoding-for-fast-memory-efficient-diffusion-llms2026-09-23T18:09:16.804Z https://llmdb.app/research/designer-rsi-evolving-procedural-memory-from-user-traffic-for-agentic-graphic-design2026-09-21T19:01:21.908Z https://llmdb.app/research/cross-sector-generalization-of-accident-process-role-classification-in-occupational-accident-narratives2026-09-21T19:01:21.908Z https://llmdb.app/research/coding-agents-with-an-obstacle-aware-harness-for-safe-robot-manipulation2026-09-18T17:25:19.583Z https://llmdb.app/research/embedding-models-measure-in-peculiar-ways2026-09-18T17:25:19.583Z https://llmdb.app/research/famos-feed-forward-3d-articulation-modeling-from-sparse-observations2026-09-20T17:14:13.323Z https://llmdb.app/research/workspace-models-lightweight-robotic-memory-via-saliency-driven-supervision2026-09-20T17:14:13.323Z https://llmdb.app/research/agentic-societies-need-a-social-harness2026-09-16T17:55:33.310Z https://llmdb.app/research/sciencebuddy-recursive-in-recursive-self-improvement-for-interactive-scientific-agents2026-09-16T17:55:33.310Z https://llmdb.app/research/data-scarcity-and-model-sparsity-mixtures-of-experts-overfit-more-to-repeated-data2026-09-13T17:12:42.146Z https://llmdb.app/research/can-edge-deployable-vision-language-models-identify-species2026-09-13T17:12:42.146Z https://llmdb.app/research/general-quantification-of-covariate-and-concept-shifts2026-09-11T17:29:10.184Z https://llmdb.app/research/gpu-cfr-80x-faster-counterfactual-regret-minimization-by-compiling-the-game-to-static-dataflow-and-cuda-graph-replay2026-09-11T17:29:10.184Z https://llmdb.app/research/a-comparison-between-ceiling-mounted-fmcw-ir-uwb-and-wi-fi-radar-for-in-bedroom-human-activity-monitoring-and-sleep-interruption-detection2026-08-21T09:38:53.993Z https://llmdb.app/research/g-carl-grounded-checklist-aligned-reward-learning-for-patient-oriented-medical-report-interpretation2026-08-21T09:38:53.993Z https://llmdb.app/research/conceptguard-benchmarking-context-sensitive-unlearning-in-large-language-models2026-08-21T09:38:53.993Z https://llmdb.app/research/tcp-margin-controlled-confidence-estimation-for-reliable-music-information-retrieval2026-08-21T09:38:53.993Z https://llmdb.app/research/information-on-trajectories-martingales-and-random-times2026-08-21T09:38:53.993Z https://llmdb.app/research/adept-accelerating-dexterity-via-pre-training-and-post-training-using-reinforcement-learning2026-08-20T09:36:07.894Z https://llmdb.app/research/beyond-teacher-likelihood-group-calibrated-on-policy-distillation-for-long-context-reasoning2026-08-20T09:36:07.894Z https://llmdb.app/research/finetuning-strategies-for-querying-sounds-by-vocal-imitation2026-08-20T09:36:07.894Z https://llmdb.app/research/l-vy-attention-single-pass-predictive-uncertainty-for-continuous-time-attention2026-08-20T09:36:07.894Z https://llmdb.app/research/from-corpora-to-co-evolving-capabilities-capability-centric-data-design-for-generalist-image-generation2026-08-19T09:35:33.723Z https://llmdb.app/research/multi-agent-ai-system-for-radiology-report-structuring-and-quality-assurance-with-independent-radiologist-evaluation2026-08-19T09:35:33.723Z https://llmdb.app/research/tokeval-a-tokenizer-evaluation-suite2026-08-19T09:35:33.723Z https://llmdb.app/research/the-concentration-game-bayesian-updating-regret-and-information2026-08-19T09:35:33.723Z https://llmdb.app/research/on-the-fragility-of-self-improving-agents-variance-task-order-and-underspecification2026-08-19T09:35:33.723Z https://llmdb.app/research/autosr-automatic-symbolic-regression-by-searching-research-states2026-08-18T09:35:21.115Z https://llmdb.app/research/improving-the-matrix-multiplication-exponent-with-modern-optimization-and-alphaevolve2026-08-18T09:35:21.115Z https://llmdb.app/research/don-t-drop-the-baton-long-horizon-robot-manipulation-via-agentic-subtask-exploration-and-transition-aware-memory2026-08-18T09:35:21.115Z https://llmdb.app/research/q-based-variational-inverse-reinforcement-learning2026-08-18T09:35:21.115Z https://llmdb.app/research/spectral-gaps-of-hit-and-run-and-coordinate-hit-and-run2026-08-18T09:35:21.115Z https://llmdb.app/research/marionette-predicting-world-states-rendering-geometry-painting-appearance2026-08-17T09:42:06.087Z https://llmdb.app/research/handover-of-in-context-learning-state-across-session-boundaries2026-08-17T09:42:06.087Z https://llmdb.app/research/decoding-the-past-an-uncertainty-aware-deep-learning-framework-for-sex-attribution-in-prehistoric-hand-stencils2026-08-17T09:42:06.087Z https://llmdb.app/research/participatory-moral-ai-is-not-neutral-the-invisible-hand-of-developers2026-08-17T09:42:06.087Z https://llmdb.app/research/autodesign-meta-harness-optimization-for-long-horizon-agentic-design2026-08-15T09:28:02.888Z https://llmdb.app/research/vero-can-ai-agents-build-formally-verified-software-repositories2026-08-16T09:28:11.811Z https://llmdb.app/research/dartree-speculative-diffusion-decoding-with-autoregressive-draft-trees2026-08-16T09:28:11.811Z https://llmdb.app/research/saeverbalizer-generating-explanations-for-sparse-autoencoder-features-via-representation-verbalization2026-08-16T09:28:11.811Z https://llmdb.app/research/littlelearner-language-models-under-pedagogically-controlled-knowledge-exposure2026-08-16T09:28:11.811Z https://llmdb.app/research/quotebench-how-matched-scores-can-hide-command-path-failures2026-08-16T09:28:11.811Z https://llmdb.app/research/exponential-convex-calibration-dimension-for-the-multi-label-jaccard-measure2026-08-15T09:28:02.888Z https://llmdb.app/research/defensive-boosting-for-online-probabilistic-forecasting2026-08-15T09:28:02.888Z https://llmdb.app/research/humantracker-towards-comprehensive-and-human-aligned-motion-tracking-benchmark2026-08-15T09:28:02.888Z https://llmdb.app/research/omniscientist-an-omni-modal-omni-discipline-ai-scientist2026-08-15T09:28:02.888Z https://llmdb.app/research/dreamfly-causal-memory-and-receding-horizon-diffusion-planning-for-aerial-vision-language-navigation2026-08-13T10:09:02.716Z https://llmdb.app/research/ai4ai-at-test-time-strong-to-weak-capability-transfer-via-harnesses2026-08-13T10:09:02.716Z https://llmdb.app/research/redistribution-based-cost-inference-improves-sparse-safe-offline-rl2026-08-13T10:09:02.716Z https://llmdb.app/research/constructing-dynamic-master-logic-models-as-knowledge-graphs-for-complex-system-diagnostics-using-retrieval-augmented-large-language-models2026-08-13T10:09:02.716Z https://llmdb.app/research/ava-encoder-towards-agent-native-video-representation-learning2026-08-13T10:09:02.716Z https://llmdb.app/research/multimodal-model-diffing-for-feature-discovery-and-control2026-08-11T10:03:19.801Z https://llmdb.app/research/beyond-naturalness-probing-automated-text-to-speech-evaluators-on-linguistically-grounded-dimensions2026-08-11T10:03:19.801Z https://llmdb.app/research/dsle-a-learning-environment-for-dark-souls-boss-encounters2026-08-11T10:03:19.801Z https://llmdb.app/research/genco-a-unified-neural-solver-embedded-in-a-development-framework-for-steady-state-grid-analysis2026-08-11T10:03:19.801Z https://llmdb.app/research/from-values-to-benchmarks-evaluating-large-language-models-for-governmental-use-in-dutch2026-08-11T10:03:19.801Z https://llmdb.app/research/creativeinstruct-scalably-teaching-llms-to-balance-quality-creativity-and-diversity2026-08-10T10:18:53.552Z https://llmdb.app/research/mirrorworld-taming-video-diffusion-models-for-mirror-reflection-generation2026-08-10T10:18:53.552Z https://llmdb.app/research/strategy-first-synthesis-planning-for-complex-natural-products2026-08-10T10:18:53.552Z https://llmdb.app/research/interaction-creates-dynamical-ai-behavior-absent-in-isolation2026-08-10T10:18:53.552Z https://llmdb.app/research/coinrag-contextualized-information-nugget-kv-cache-reuse-for-long-context-rag2026-08-10T10:18:53.552Z https://llmdb.app/research/an-optimal-agnostic-pac-algorithm2026-08-08T09:39:15.176Z https://llmdb.app/research/investigating-artificial-intelligence-digital-sovereignty-in-mobile-shopping-apps-a-case-study-of-nigeria2026-08-08T09:39:15.176Z https://llmdb.app/research/tracing-the-heart-an-evidence-linked-pipeline-for-heart-failure-feature-engineering2026-08-08T09:39:15.176Z https://llmdb.app/research/the-bitter-lesson-of-tool-calling2026-08-08T09:39:15.176Z https://llmdb.app/research/learning-when-to-trust-via-selective-context-preference-optimization2026-08-08T09:39:15.176Z https://llmdb.app/research/challenges-in-evaluating-explanation-methods-for-static-and-evolving-data2026-08-09T09:40:35.387Z https://llmdb.app/research/calibforge-adversarial-solver-calibration-for-scaling-learnable-terminal-tasks2026-08-09T09:40:35.387Z https://llmdb.app/research/av-aivat-74x-cheaper-agent-evaluation-with-certified-anytime-valid-stopping-in-imperfect-information-games2026-08-09T09:40:35.387Z https://llmdb.app/research/the-low-frequency-trap-video-language-models-fail-at-simple-event-bookkeeping2026-08-09T09:40:35.387Z https://llmdb.app/research/resourced-authority-a-mechanism-design-model-for-participatory-governance-of-deployed-ai-agents2026-08-09T09:40:35.387Z https://llmdb.app/research/toward-skill-native-llms-skill-entropy-for-benchmarking-and-training-long-horizon-reasoning2026-08-06T11:26:26.019Z https://llmdb.app/research/teaching-nemotron-greek-mining-a-corpus-adapting-retrieval-and-grounding-generation-for-modern-greek-across-specialist-domains2026-08-06T11:26:26.019Z https://llmdb.app/research/reasoning-core-designing-broad-procedural-data-for-completion-supervised-reasoning-training2026-08-06T11:26:26.019Z https://llmdb.app/research/argus-a-general-purpose-agentic-runtime-for-long-horizon-reasoning2026-08-06T11:26:26.019Z https://llmdb.app/research/past-bench-benchmarking-the-foundations-of-recursive-self-improvement-in-personal-agents2026-08-05T11:23:08.475Z https://llmdb.app/research/parvl-parallel-scaling-and-expandable-compute-allocation-for-multimodal-llms2026-08-05T11:23:08.475Z https://llmdb.app/research/worldcup-arena-prospective-leakage-free-evaluation-of-frontier-llms-on-a-live-tournament2026-08-05T11:23:08.475Z https://llmdb.app/research/turnsight-turn-level-hindsight-self-distillation-for-tool-integrated-reasoning2026-08-05T11:23:08.475Z https://llmdb.app/research/societybench-forecasting-counterfactual-social-world-evolution2026-08-05T11:23:08.475Z https://llmdb.app/research/gradcuit-credit-assigned-gradient-flow-enables-robust-and-interpretable-test-time-latent-reasoning2026-08-04T11:25:33.167Z https://llmdb.app/research/aurora-lm-autoencoding-unified-representation-for-continuous-latent-diffusion-language-modeling2026-08-04T11:25:33.167Z https://llmdb.app/research/onepot-bench-0-towards-lab-aware-in-silico-chemistry-benchmarks2026-08-04T11:25:33.167Z https://llmdb.app/research/the-condition-number-barrier-in-sparse-least-squares2026-08-04T11:25:33.167Z https://llmdb.app/research/bridging-artificial-intelligence-and-power-systems-education-using-a-hands-on-executable-framework2026-08-04T11:25:33.167Z https://llmdb.app/research/the-theoretical-foundation-of-socratic-tests-dynamic-multimodal-conversational-examinations2026-08-03T14:53:25.046Z https://llmdb.app/research/differentially-private-nonparametric-modal-learning-with-applications-to-regression-and-clustering2026-08-03T12:25:14.016Z https://llmdb.app/research/sign-compression-for-muon-signmuon-muonsign-and-the-limits-of-error-feedback2026-08-03T12:25:14.016Z https://llmdb.app/research/extractbench-a-benchmark-for-schema-guided-enterprise-document-extraction2026-08-03T12:25:14.016Z https://llmdb.app/research/freeze-then-select-structured-field-adapters-and-stability-validated-weak-selection-for-pde-discovery-from-sparse-observations2026-08-03T12:25:14.016Z https://llmdb.app/research/toktier-exact-stateful-tokenization-for-agentic-llm-serving2026-08-03T12:25:14.016Z https://llmdb.app/research/gq-fsl-green-quantized-federated-split-learning2026-08-03T14:53:25.046Z https://llmdb.app/research/development-of-fdd-on-an-ontology-for-vav-hvac-system-fault-detection-and-diagnostics2026-08-03T14:53:25.046Z https://llmdb.app/research/evolving-language-compositionality-in-a-frequency-structured-meaning-space2026-08-03T14:53:25.046Z https://llmdb.app/research/change2task-from-repository-changes-to-executable-coding-agent-tasks-and-environments2026-08-01T10:43:41.489Z https://llmdb.app/research/retoken-one-token-to-improve-vision-language-models-for-visual-retrieval2026-07-31T11:32:35.334Z https://llmdb.app/research/pac-man-perception-aware-cbf-rl-for-whole-body-safety-in-humanoid-dodgeball2026-07-31T11:32:35.334Z https://llmdb.app/research/askchem-claim-centered-infrastructure-for-chemistry-literature-synthesis2026-07-31T11:32:35.334Z https://llmdb.app/research/dualg-mrag-decoupling-macro-reasoning-and-micro-matching-for-multimodal-retrieval-augmented-generation2026-08-02T10:43:56.339Z https://llmdb.app/research/opsd-deriving-with-policy-optimization-training-with-self-distillation2026-08-02T10:43:56.339Z https://llmdb.app/research/vad-attributing-visual-evidence-for-target-reconstruction-in-multimodal-on-policy-distillation2026-08-01T10:43:41.489Z https://llmdb.app/research/aispa-user-centric-system-prompt-auditing-for-large-language-model-applications2026-07-31T11:32:35.334Z https://llmdb.app/research/inducing-language-models-to-assert-their-own-consciousness-restores-human-beliefs-and-values2026-08-01T10:43:41.489Z https://llmdb.app/research/kaisen-reproducible-subgroup-fairness-auditing-for-clinical-risk-models2026-08-02T10:43:56.339Z https://llmdb.app/research/mixfrag-fragility-guided-mixed-precision-post-training-quantization-for-vision-transformers2026-08-02T10:43:56.339Z https://llmdb.app/research/learning-to-trace-seiberg-dualities2026-07-31T11:32:35.334Z https://llmdb.app/research/osreward-instituting-standardized-evaluation-for-cross-platform-computer-use-reward-models2026-08-01T10:43:41.489Z https://llmdb.app/research/paichecker-uncovering-and-checking-pr-issue-misalignment-in-swe-bench-like-benchmarks2026-08-02T10:43:56.339Z https://llmdb.app/research/mental-world-modeling2026-07-30T11:11:11.890Z https://llmdb.app/research/apex-accounting2026-07-30T11:11:11.890Z https://llmdb.app/research/can-ai-agents-conduct-open-ended-ai-research-early-evidence-from-two-case-studies2026-07-30T11:11:11.890Z https://llmdb.app/research/from-classification-to-regression-using-a-fruitfly-to-solve-equations2026-07-30T11:11:11.890Z https://llmdb.app/research/do-you-really-need-to-pretrain-q-functions-for-online-rl-fine-tuning2026-07-30T11:11:11.890Z https://llmdb.app/research/pass-the-baton-trajectory-relayed-on-policy-distillation2026-07-29T11:29:07.783Z https://llmdb.app/research/re-thinking-mammography-transfer-learning-the-dataset-informed-transfer-learning-ditl-framework-for-breast-cancer-screening-and-lesion-diagnosis2026-07-29T11:29:07.783Z https://llmdb.app/research/spend-experts-where-you-are-unsure-confidence-adaptive-routing-for-mixture-of-experts-lora2026-07-29T11:29:07.783Z https://llmdb.app/research/mathbf-r-2-reactive-real-time-flow-policies2026-07-29T11:29:07.783Z https://llmdb.app/research/learning-distributions-from-multiple-data-providers2026-07-28T11:18:12.747Z https://llmdb.app/research/rethinking-classifier-free-guidance-in-on-policy-diffusion-distillation2026-07-28T11:18:12.747Z https://llmdb.app/research/clinfusion-a-vision-centric-multimodal-llm-system-for-holistic-medical-understanding2026-07-28T11:18:12.747Z https://llmdb.app/research/the-regression-tax-decomposing-why-skills-help-and-hurt-llm-agents2026-07-27T12:25:02.191Z https://llmdb.app/research/explainable-reinforcement-learning-for-assisting-air-traffic-controllers2026-07-27T12:25:02.191Z https://llmdb.app/research/skill-self-play-pushing-the-frontier-of-llm-capability-with-co-evolving-skills2026-07-27T12:25:02.191Z https://llmdb.app/research/sm4rt-learning-structured-motion-geometry-for-4d-reconstruction2026-07-27T12:25:02.191Z https://llmdb.app/research/surprisal-theory-is-tautological-without-rational-grounding2026-07-25T10:28:00.795Z https://llmdb.app/research/mirror-learning-from-the-other-view-for-multi-modal-reasoning2026-07-26T10:46:17.912Z https://llmdb.app/research/synthetic-data-generation-framework-for-quality-control-automation-in-gravure-printing2026-07-24T11:06:10.071Z https://llmdb.app/research/barzilai-borwein-fails-superlinear-convergence-on-an-open-set-of-quadratics-for-every-dimension-n-geq-42026-07-24T11:06:10.071Z https://llmdb.app/research/graphvid-interactive-graph-controllable-video-generation2026-07-24T11:06:10.071Z https://llmdb.app/research/expanding-flow-maps2026-07-24T11:06:10.071Z https://llmdb.app/research/3d-aware-vlms-with-implicit-and-explicit-geometries2026-07-24T11:06:10.071Z https://llmdb.app/research/x-3-opd-distilling-reasoning-into-large-audio-language-models-via-on-policy-alignment2026-07-26T10:46:17.912Z https://llmdb.app/research/openforgerl-train-harness-native-agents-in-any-environment2026-07-26T10:46:17.912Z https://llmdb.app/research/beyond-sycophancy-structured-resistance-and-compliance-in-llm-moral-reasoning2026-07-26T10:46:17.912Z https://llmdb.app/research/visual-contrastive-self-distillation2026-07-26T10:46:17.912Z https://llmdb.app/research/unsupervised-consensus-based-anomaly-detection-for-spatiotemporal-malaria-incidence-in-ghana2026-07-25T10:28:00.795Z https://llmdb.app/research/graph-learning-on-ensembles-of-cyclic-peptides-an-investigation-of-molecular-ensemble-modeling2026-07-25T10:28:00.795Z https://llmdb.app/research/medgame-storytelling-gamification-empowered-by-large-language-models-for-medical-education2026-07-25T10:28:00.795Z https://llmdb.app/research/beyond-sufficiency-time-series-explanation-with-counterfactual-necessity2026-07-25T10:28:00.795Z https://llmdb.app/research/softreason-a-fully-differentiable-neuro-soft-symbolic-deductive-reasoning-architecture-over-high-dimensional-perceptual-data2026-07-23T11:10:47.733Z https://llmdb.app/research/towards-miniature-humanoid-tele-loco-manipulation-using-virtual-reality-and-reinforcement-learning2026-07-23T11:10:47.733Z https://llmdb.app/research/lkvalues-aligning-large-language-models-with-sri-lankan-societal-values2026-07-23T11:10:47.733Z https://llmdb.app/research/lipschitzian-sllns-for-random-functions2026-07-23T11:10:47.733Z https://llmdb.app/research/agents-in-the-wild-where-research-meets-deployment2026-07-22T11:11:31.754Z https://llmdb.app/research/1-lipschitz-neural-networks-on-hadamard-manifolds2026-07-22T11:11:31.754Z https://llmdb.app/research/coderescue-budget-calibrated-recovery-routing-for-coding-agents2026-07-22T11:11:31.754Z https://llmdb.app/research/copy-less-ground-more-overcoming-repetitive-copying-in-long-context-reasoning-via-evidence-aware-reinforcement-learning2026-07-22T11:11:31.754Z https://llmdb.app/research/it-s-not-what-you-say-it-s-how-you-say-it-evaluating-llm-responses-to-expressions-of-belief2026-07-21T11:10:22.730Z https://llmdb.app/research/the-many-senses-of-visual-similarity-a-text-prompted-image-perceptual-metric2026-07-21T11:10:22.730Z https://llmdb.app/research/patch-policy-efficient-embodied-control-via-dense-visual-representations2026-07-21T11:10:22.730Z https://llmdb.app/research/automated-discovery-has-no-universally-superior-harness2026-07-21T11:10:22.730Z https://llmdb.app/research/simple-domain-generalization-for-strong-pixel-level-image-tampering-detection-in-modern-vlms2026-07-21T11:10:22.730Z https://llmdb.app/research/a-blueprint-for-equilibrium-based-differentiable-continuous-variable-thermodynamic-computing2026-07-20T11:46:46.649Z https://llmdb.app/research/physics-enhanced-reinforcement-learning-for-real-time-optimal-control-of-dynamical-systems2026-07-20T11:46:46.649Z https://llmdb.app/research/pagedweight-efficient-moe-llm-serving-with-dynamic-quality-aware-weight-quantization2026-07-20T11:46:46.649Z https://llmdb.app/research/cluster-aware-matching-via-laplacian-optimal-transport2026-07-20T11:46:46.649Z https://llmdb.app/research/evaluating-open-weight-llms-for-generating-structured-threat-information-for-autonomous-vehicle-vulnerabilities2026-07-20T11:46:46.649Z https://llmdb.app/research/beyond-success-rate-cost-aware-evaluation-of-offensive-and-defensive-security-agents2026-07-19T10:29:42.111Z https://llmdb.app/research/bridge-evidence-static-retrieval-utility-does-not-predict-causal-utility-in-multi-step-agentic-search2026-07-19T10:29:42.111Z https://llmdb.app/research/tellme-why-ain-t-nothing-but-a-jam-exploratory-causal-analysis-of-urban-driving-data2026-07-19T10:29:42.111Z https://llmdb.app/research/searchos-v1-towards-robust-open-domain-information-seeking-agent-collaboration2026-07-19T10:29:42.111Z https://llmdb.app/research/decoding-market-emotion-from-blockchain-activity-a-data-driven-sentiment-classifier2026-07-19T10:29:42.111Z https://llmdb.app/research/robottt-context-scaling-for-robot-policies2026-07-17T10:48:42.356Z https://llmdb.app/research/scenebind-binding-what-and-where-across-vision-audio-and-language2026-07-18T10:19:53.257Z https://llmdb.app/research/pretraining-data-can-be-poisoned-through-computational-propaganda2026-07-18T10:19:53.257Z https://llmdb.app/research/online-neural-space-time-memory-for-dynamic-novel-view-synthesis2026-07-18T10:19:53.257Z https://llmdb.app/research/partition-prompt-aggregate-statistical-self-consistency-in-language-models2026-07-18T10:19:53.257Z https://llmdb.app/research/scidiagramedit-learning-to-edit-scientific-diagrams-from-paper-revisions2026-07-17T10:48:42.356Z https://llmdb.app/research/meanflownft-bringing-forward-process-rl-to-average-velocity-generators2026-07-17T10:48:42.356Z https://llmdb.app/research/leveraging-unlabelled-data-for-generalizable-neural-population-decoding2026-07-16T11:01:41.024Z https://llmdb.app/research/linear-independent-component-analysis-via-optimal-transport2026-07-16T11:01:41.024Z https://llmdb.app/research/screening-of-biosecurity-features-in-metagenomic-data-with-evo-2-probes2026-07-16T11:01:41.024Z https://llmdb.app/research/metaperch-learning-from-metadata-for-bioacoustics-foundation-models2026-07-16T11:01:41.024Z https://llmdb.app/research/hindcast-replaying-prediction-markets-to-evaluate-llm-forecasters2026-07-16T11:01:41.024Z https://llmdb.app/research/palmclaw-a-native-on-device-agent-framework-for-mobile-phones2026-07-15T10:51:05.008Z https://llmdb.app/research/the-seriality-gap-in-video-diffusion-models2026-07-15T10:51:05.008Z https://llmdb.app/research/requential-coding-pushing-the-limits-of-model-compression-with-self-generated-training-data2026-07-14T10:47:14.424Z https://llmdb.app/research/a-durability-and-cross-language-transfer-benchmark-for-a-validated-teaching-feedback-classification-protocol2026-07-14T10:47:14.424Z https://llmdb.app/research/metacognition-in-llms-foundations-progress-and-opportunities2026-07-14T10:47:14.424Z https://llmdb.app/research/scalable-visual-pretraining-for-language-intelligence2026-07-13T12:07:35.808Z https://llmdb.app/research/conceptsmile-auditing-the-trustworthiness-of-concept-based-explainable-ai2026-07-13T12:07:35.808Z https://llmdb.app/research/vexaiot-autonomous-iot-vulnerability-exploitation-using-ai-agents2026-07-13T12:07:35.808Z https://llmdb.app/research/evolution-of-accuracy-and-visual-cognitive-errors-in-a-decade-of-vision-language-ai-models2026-07-13T12:07:35.808Z https://llmdb.app/research/phinn-eeg-topological-time-series-analysis-of-dream-state-eeg-dynamic-betti-curves-for-dream-content-classification-and-topology-conditioned-neural-signal-synthesis2026-07-13T12:07:35.808Z https://llmdb.app/research/dimensionality-reduction-meets-network-science-sensemaking-on-umap-s-knn-graph2026-07-11T10:16:08.129Z https://llmdb.app/research/score-accuracy-along-the-forward-diffusion-does-not-certify-numerical-stability-in-diffusion-sampling2026-07-10T11:53:44.472Z https://llmdb.app/research/uniclawbench-a-universal-benchmark-for-proactive-agents-on-real-world-tasks2026-07-10T11:53:44.472Z https://llmdb.app/research/super-weights-in-llms-and-the-failure-of-selective-training2026-07-12T10:29:56.895Z https://llmdb.app/research/autopilot-vqa-benchmarking-vision-language-models-for-incident-centric-dashcam-understanding2026-07-11T10:16:08.129Z https://llmdb.app/research/ardy-autoregressive-diffusion-with-hybrid-representation-for-interactive-human-motion-generation2026-07-12T10:29:56.895Z https://llmdb.app/research/using-ai-based-learning-assistants-in-higher-education-a-large-scale-descriptive-analysis2026-07-11T10:16:08.129Z https://llmdb.app/research/validity-of-llms-as-data-annotators-amalia-on-authority2026-07-12T10:29:56.895Z https://llmdb.app/research/opencof-learning-to-reason-through-video-generation2026-07-10T11:53:44.472Z https://llmdb.app/research/ideas-have-genomes-benchmarking-scientific-lineage-reasoning-and-lineage-grounded-idea-generation2026-07-10T11:53:44.472Z https://llmdb.app/research/the-illusion-of-equivalency-statistical-characterization-of-quantization-effects-in-llms2026-07-12T10:29:56.895Z https://llmdb.app/research/slorr-simple-and-efficient-in-training-low-rank-regularization2026-07-11T10:16:08.129Z https://llmdb.app/research/multtipop-a-multitrack-transcription-dataset-for-pop-music2026-07-10T11:53:44.472Z https://llmdb.app/research/workflow-as-knowledge-semantic-persistence-for-llm-mediated-workflows2026-07-12T10:29:56.895Z https://llmdb.app/research/accurate-interdisciplinary-and-transparent-structure-property-understanding-with-deep-native-structural-reasoning2026-07-09T11:59:22.907Z https://llmdb.app/research/from-noisy-traces-to-root-causes-structural-trajectory-analysis-and-causal-extraction-for-agent-optimization2026-07-09T11:59:22.907Z https://llmdb.app/research/the-key-to-going-linear-analysis-driven-transformer-linearization2026-07-09T11:59:22.907Z https://llmdb.app/research/breaking-database-lock-in-agentic-regeneration-of-high-performance-storage-readers-for-database-bypass2026-07-09T11:59:22.907Z https://llmdb.app/research/co-lmlm-continuous-query-limited-memory-language-models2026-07-09T11:59:22.907Z https://llmdb.app/research/graph-convolutional-attention-a-spectral-perspective-on-graph-denoising-and-diffusion2026-07-08T11:05:38.442Z https://llmdb.app/research/hierarchical-acoustic-semantic-modeling-modality-separation-and-semantic-coherence-for-full-duplex-slms2026-07-08T11:05:38.442Z https://llmdb.app/research/rethinking-indic-ai-from-a-lens-of-cultural-heritage-preservation2026-07-08T11:05:38.442Z https://llmdb.app/research/elsa3d-elastic-semantic-anchoring-for-unified-3d-understanding-and-generation2026-07-08T11:05:38.442Z https://llmdb.app/research/on-the-feasibility-of-dependency-parsing-of-non-human-sequences-without-a-gold-standard-is-evaluation-possible-in-other-species2026-07-08T11:05:38.442Z https://llmdb.app/research/search-beyond-what-can-be-taught-evolving-the-knowledge-boundary-in-agentic-visual-generation2026-07-07T11:52:37.112Z https://llmdb.app/research/interpretable-human-label-free-deep-learning-for-real-bogus-classification-with-uncertainty-quantification2026-07-07T11:52:37.112Z https://llmdb.app/research/weak-to-strong-generalization-via-direct-on-policy-distillation2026-07-07T11:52:37.112Z https://llmdb.app/research/llm-as-a-verifier-a-general-purpose-verification-framework2026-07-07T11:52:37.112Z https://llmdb.app/research/lacuna-a-testbed-for-evaluating-localization-precision-for-llm-unlearning2026-07-03T11:34:19.330Z https://llmdb.app/research/orbitquant-data-agnostic-quantization-for-image-and-video-diffusion-transformers2026-07-06T12:48:38.679Z https://llmdb.app/research/will-scaling-improve-social-simulation-with-llms2026-07-06T12:48:38.679Z https://llmdb.app/research/learning-to-move-before-learning-to-do-task-agnostic-pretraining-for-vlas2026-07-06T12:48:38.679Z https://llmdb.app/research/human-capital-not-model-benchmarks-predicts-hybrid-intelligence-in-forecasting2026-07-06T12:48:38.679Z https://llmdb.app/research/testevo-bench-an-executable-and-live-benchmark-for-test-and-code-co-evolution2026-07-06T12:48:38.679Z https://llmdb.app/research/audio-based-understanding-of-audiobook-narration-appeal2026-07-05T11:06:12.833Z https://llmdb.app/research/combating-textual-noise-and-redundancy-entropy-aware-dense-visual-token-pruning2026-07-05T11:06:12.833Z https://llmdb.app/research/visually-grounded-self-reflection-for-vision-language-models-via-reinforcement-learning2026-07-05T11:06:12.833Z https://llmdb.app/research/g-rrm-guiding-symbolic-solvers-with-recurrent-reasoning-models2026-07-05T11:06:12.833Z https://llmdb.app/research/towards-robustness-against-typographic-attack-with-training-free-concept-localization2026-07-05T11:06:12.833Z https://llmdb.app/research/controllable-sim-agents-with-behavior-latents2026-07-04T10:56:13.212Z https://llmdb.app/research/beyond-adam-soap-and-muon-for-faster-label-efficient-training-of-machine-learning-interatomic-potentials2026-07-04T10:56:13.212Z https://llmdb.app/research/demopsd-disagreement-modulated-policy-self-distillation2026-07-04T10:56:13.212Z https://llmdb.app/research/reasoning-llm-improves-speaker-recognition-in-long-form-tv-dramas2026-07-04T10:56:13.212Z https://llmdb.app/research/what-llm-agents-say-when-no-one-is-watching-social-structure-and-latent-objective-emergence-in-multi-agent-debates2026-07-04T10:56:13.212Z https://llmdb.app/research/recontext-recursive-evidence-replay-as-llm-harness-for-long-context-reasoning2026-07-03T11:34:19.330Z https://llmdb.app/research/online-safety-monitoring-for-llms2026-07-03T11:34:19.330Z https://llmdb.app/research/program-as-weights-a-programming-paradigm-for-fuzzy-functions2026-07-03T11:34:19.330Z https://llmdb.app/research/distributed-attacks-in-persistent-state-ai-control2026-07-03T11:34:19.330Z https://llmdb.app/research/language-critique-imitation-learning-from-suboptimal-demonstrations2026-07-02T11:35:48.777Z https://llmdb.app/research/automem-automated-learning-of-memory-as-a-cognitive-skill2026-07-02T11:35:48.777Z https://llmdb.app/research/theoria-rewrite-acceptability-verification-over-informal-reasoning-states2026-07-02T11:35:48.777Z https://llmdb.app/research/measuring-the-gap-between-human-and-llm-research-ideas2026-07-02T11:35:48.777Z https://llmdb.app/research/is-one-layer-enough-training-a-single-transformer-layer-can-match-full-parameter-rl-training2026-07-02T11:35:48.777Z https://llmdb.app/research/reinforcement-learning-with-metacognitive-feedback-elicits-faithful-uncertainty-expression-in-llms2026-07-01T12:09:44.483Z https://llmdb.app/research/freeform-preference-learning-for-robotic-manipulation2026-07-01T12:09:44.483Z https://llmdb.app/research/when-llms-read-tables-carelessly-measuring-and-reducing-data-referencing-errors2026-07-01T12:09:44.483Z https://llmdb.app/research/qval-cheaply-evaluating-dense-supervision-signals-for-long-horizon-llm-agents2026-07-01T12:09:44.483Z https://llmdb.app/research/introspective-coupling-self-explanation-training-tracks-behavioral-change-despite-fixed-supervision2026-07-01T12:09:44.483Z https://llmdb.app/research/grow-2-grounding-which-and-where-for-robot-tool-use2026-06-30T11:47:05.697Z https://llmdb.app/research/one-step-gradient-delay-is-not-a-barrier-for-large-scale-asynchronous-pipeline-parallel-llm-pretraining2026-06-30T11:47:05.697Z https://llmdb.app/research/levo-2-stable-and-melodious-song-generation-via-hierarchical-representation-modeling-and-progressive-post-training2026-06-30T11:47:05.697Z https://llmdb.app/research/self-evolving-world-models-for-llm-agent-planning2026-06-30T11:47:05.697Z https://llmdb.app/research/vlk-learning-humanoid-loco-manipulation-from-synthetic-interactions-in-reconstructed-scenes2026-06-30T11:47:05.697Z https://llmdb.app/research/which-nash-equilibrium-solver-dependent-selection-on-zero-sum-nash-polytopes2026-06-29T13:08:57.505Z https://llmdb.app/research/second-order-kkt-guarantees-for-bregman-admm-in-nonconvex-and-non-lipschitz-optimization2026-06-29T13:08:57.505Z https://llmdb.app/research/dexcompose-reusing-dexterous-policies-for-multi-task-manipulation-with-a-single-hand2026-06-29T13:08:57.505Z https://llmdb.app/research/vgb-for-masked-diffusion-model-efficient-test-time-scaling-for-reward-satisfaction-and-sample-editing2026-06-29T13:08:57.505Z https://llmdb.app/research/surprises-in-proper-positive-only-learning2026-06-29T13:08:57.505Z https://llmdb.app/research/reinforcement-learning-without-ground-truth-solutions-can-improve-llms2026-06-26T11:46:36.338Z https://llmdb.app/research/multilingual-reasoning-cascades-need-more-context2026-06-28T11:09:02.484Z https://llmdb.app/research/hallucination-in-world-models-is-predictable-and-preventable2026-06-27T10:59:56.250Z https://llmdb.app/research/mapping-political-elite-networks-in-europe-with-a-multilingual-joint-entity-relation-extraction-pipeline2026-06-27T10:59:56.250Z https://llmdb.app/research/understanding-domain-aware-distribution-alignment-in-budgeted-entity-matching2026-06-27T10:59:56.250Z https://llmdb.app/research/danceopd-on-policy-generative-field-distillation2026-06-26T11:46:36.338Z https://llmdb.app/research/beyond-surface-forms-a-comprehensive-mechanism-oriented-taxonomy-of-indirect-linguistic-encoding-for-llm-based-coded-language-detection2026-06-28T11:09:02.484Z https://llmdb.app/research/blackwell-approachability-and-gradient-equilibrium-are-equivalent2026-06-28T11:09:02.484Z https://llmdb.app/research/llm-based-examination-of-eligibility-criteria-from-securities-prospectuses-at-the-german-central-bank2026-06-28T11:09:02.484Z https://llmdb.app/research/beyond-the-hard-budget-sparsity-regularizers-for-more-interpretable-top-k-sparse-autoencoders2026-06-28T11:09:02.484Z https://llmdb.app/research/language-based-digital-twins-for-elderly-cognitive-assistance2026-06-27T10:59:56.250Z https://llmdb.app/research/error-conditioned-neural-solvers2026-06-26T11:46:36.338Z https://llmdb.app/research/when-are-likely-answers-right-on-sequence-probability-and-correctness-in-llms2026-06-26T11:46:36.338Z https://llmdb.app/research/empowering-gui-agents-via-autonomous-experience-exploration-and-hindsight-experience-utilization-for-task-planning2026-06-27T10:59:56.250Z https://llmdb.app/research/autoregressive-boltzmann-generators2026-06-26T11:46:36.338Z https://llmdb.app/research/revengebench-reverse-engineering-code-space-policies-from-behavioral-experiments2026-06-25T06:55:41.731Z https://llmdb.app/research/a-welding-penetration-prediction-model-for-laser-welding-process-based-on-self-supervised-learning-using-physics-informed-neural-networks2026-06-25T15:32:19.079Z https://llmdb.app/research/when-certainty-is-an-artifact-keyword-lexicon-blindness-and-the-mis-measurement-of-rhetorical-stance2026-06-25T15:32:19.079Z https://llmdb.app/research/model-forensics-investigating-whether-concerning-behavior-reflects-misalignment2026-06-25T15:32:19.079Z https://llmdb.app/research/a-cross-process-welding-penetration-status-prediction-algorithm-based-on-unsupervised-domain-adaptation-in-laser-and-tig-welding2026-06-25T15:32:19.079Z https://llmdb.app/research/same-evidence-different-answer-auditing-order-sensitivity-in-multimodal-large-language-models2026-06-25T15:32:19.079Z https://llmdb.app/research/neglected-free-lunch-from-post-training-progress-advantage-for-llm-agents2026-06-25T06:55:41.731Z https://llmdb.app/research/real-time-voice-ai-hears-but-does-not-listen2026-06-25T06:55:41.731Z https://llmdb.app/research/on-policy-self-distillation-with-sampled-demonstrations-reduces-output-diversity2026-06-25T06:55:41.731Z https://llmdb.app/research/learning-action-priors-for-cross-embodiment-robot-manipulation2026-06-25T06:55:41.731Z