https://www.opentrain.ai/papers/islamicmmlu-a-benchmark-for-evaluating-llms-on-islamic-knowledge--arxiv-2603.23750/2026-06-17T08:32:22.333Z https://www.opentrain.ai/papers/llms-do-not-grade-essays-like-humans--arxiv-2603.23714/2026-06-15T20:36:13.984Z https://www.opentrain.ai/papers/the-diminishing-returns-of-early-exit-decoding-in-modern-llms--arxiv-2603.23701/2026-04-10T10:26:01.137Z https://www.opentrain.ai/papers/swiss-bench-sbp-002-a-frontier-model-comparison-on-swiss-legal-and-regulatory-ta--arxiv-2603.23646/2026-06-15T07:13:21.661Z https://www.opentrain.ai/papers/evaluating-a-multi-agent-voice-enabled-smart-speaker-for-care-homes-a-safety-foc--arxiv-2603.23625/2026-06-01T02:35:58.682Z https://www.opentrain.ai/papers/vision-on-request-enhanced-vllm-efficiency-with-sparse-dynamically-selected-visi--arxiv-2603.23495/2026-06-16T05:40:59.865Z https://www.opentrain.ai/papers/speceyes-accelerating-agentic-multimodal-llms-via-speculative-perception-and-pla--arxiv-2603.23483/2026-05-30T03:12:01.496Z https://www.opentrain.ai/papers/sortedrl-accelerating-rl-training-for-llms-through-online-length-aware-schedulin--arxiv-2603.23414/2026-05-23T04:30:10.851Z https://www.opentrain.ai/papers/off-policy-value-based-reinforcement-learning-for-large-language-models--arxiv-2603.23355/2026-06-17T11:47:32.032Z https://www.opentrain.ai/papers/safeseek-universal-attribution-of-safety-circuits-in-language-models--arxiv-2603.23268/2026-06-17T16:39:18.017Z https://www.opentrain.ai/papers/is-ai-catching-up-to-human-expression-exploring-emotion-personality-authorship-a--arxiv-2603.23251/2026-06-17T21:33:27.785Z https://www.opentrain.ai/papers/decoding-ai-authorship-can-llms-truly-mimic-human-style-across-literature-and-po--arxiv-2603.23219/2026-06-11T06:38:53.933Z https://www.opentrain.ai/papers/the-illusion-of-reasoning-step-level-evaluation-reveals-decorative-chain-of-thou--arxiv-2603.22816/2026-06-18T05:38:52.164Z https://www.opentrain.ai/papers/language-models-can-explain-visual-features-via-steering--arxiv-2603.22593/2026-06-01T14:17:04.599Z https://www.opentrain.ai/papers/lie-to-me-how-faithful-is-chain-of-thought-reasoning-in-reasoning-models--arxiv-2603.22582/2026-06-18T02:47:36.250Z https://www.opentrain.ai/papers/capitu-a-benchmark-for-evaluating-instruction-following-in-brazilian-portuguese--arxiv-2603.22576/2026-06-15T21:13:16.898Z https://www.opentrain.ai/papers/ego2web-a-web-agent-benchmark-grounded-in-egocentric-videos--arxiv-2603.22529/2026-06-12T17:32:32.006Z https://www.opentrain.ai/papers/tiny-inference-time-scaling-with-latent-verifiers--arxiv-2603.22492/2026-06-02T03:32:09.987Z https://www.opentrain.ai/papers/llm-guided-headline-rewriting-for-clickability-enhancement-without-clickbait--arxiv-2603.22459/2026-06-17T02:41:14.792Z https://www.opentrain.ai/papers/sparse-but-critical-a-token-level-analysis-of-distributional-shifts-in-rlvr-fine--arxiv-2603.22446/2026-05-22T07:51:43.915Z https://www.opentrain.ai/papers/worldcache-content-aware-caching-for-accelerated-video-world-models--arxiv-2603.22286/2026-05-22T06:36:05.617Z https://www.opentrain.ai/papers/tico-time-controllable-training-for-spoken-dialogue-models--arxiv-2603.22267/2026-06-17T19:26:44.175Z https://www.opentrain.ai/papers/from-static-templates-to-dynamic-runtime-graphs-a-survey-of-workflow-optimizatio--arxiv-2603.22386/2026-04-13T15:29:07.744Z https://www.opentrain.ai/papers/memdlm-memory-enhanced-dlm-training--arxiv-2603.22241/2026-06-17T03:51:45.268Z https://www.opentrain.ai/papers/gumbel-distillation-for-parallel-text-generation--arxiv-2603.22216/2026-06-07T07:54:28.612Z https://www.opentrain.ai/papers/dual-space-knowledge-distillation-with-key-query-matching-for-large-language-mod--arxiv-2603.22056/2026-05-22T08:11:33.884Z https://www.opentrain.ai/papers/rom-real-time-overthinking-mitigation-via-streaming-detection-and-intervention--arxiv-2603.22016/2026-06-12T03:13:44.224Z https://www.opentrain.ai/papers/securebreak-a-dataset-towards-safe-and-secure-models--arxiv-2603.21975/2026-06-16T09:08:57.482Z https://www.opentrain.ai/papers/demystifying-reinforcement-learning-for-long-horizon-tool-using-agents-a-compreh--arxiv-2603.21972/2026-06-16T02:32:16.688Z https://www.opentrain.ai/papers/parameter-efficient-fine-tuning-for-medical-text-summarization-a-comparative-stu--arxiv-2603.21970/2026-05-25T08:15:54.498Z https://www.opentrain.ai/papers/p-2o-joint-policy-and-prompt-optimization--arxiv-2603.21877/2026-06-17T03:51:06.185Z https://www.opentrain.ai/papers/manifold-aware-exploration-for-reinforcement-learning-in-video-generation--arxiv-2603.21872/2026-06-17T09:36:24.117Z https://www.opentrain.ai/papers/agentic-personas-for-adaptive-scientific-explanations-with-knowledge-graphs--arxiv-2603.21846/2026-06-16T20:56:26.409Z https://www.opentrain.ai/papers/semeval-2026-task-12-abductive-event-reasoning-towards-real-world-event-causal-i--arxiv-2603.21720/2026-06-14T08:45:27.901Z https://www.opentrain.ai/papers/rethinking-token-reduction-for-large-vision-language-models--arxiv-2603.21701/2026-04-11T13:56:18.963Z https://www.opentrain.ai/papers/optimizing-multi-agent-weather-captioning-via-text-gradient-descent-a-training-f--arxiv-2603.21673/2026-05-20T11:08:06.958Z https://www.opentrain.ai/papers/agenticrec-end-to-end-tool-integrated-policy-optimization-for-ranking-oriented-r--arxiv-2603.21613/2026-06-14T04:55:37.011Z https://www.opentrain.ai/papers/cerebra-a-multidisciplinary-ai-board-for-multimodal-dementia-characterization-an--arxiv-2603.21597/2026-06-17T03:01:13.523Z https://www.opentrain.ai/papers/spatio-temporal-attention-enhanced-multi-agent-drl-for-uav-assisted-wireless-net--arxiv-2603.21594/2026-06-06T03:00:39.018Z https://www.opentrain.ai/papers/mind-over-space-can-multimodal-large-language-models-mentally-navigate--arxiv-2603.21577/2026-06-11T16:30:57.108Z https://www.opentrain.ai/papers/prism-breaking-the-o-n-memory-wall-in-long-context-llm-inference-via-o-1-photoni--arxiv-2603.21576/2026-06-18T06:13:26.757Z https://www.opentrain.ai/papers/adaptive-robust-estimator-for-multi-agent-reinforcement-learning--arxiv-2603.21574/2026-06-17T16:23:32.371Z https://www.opentrain.ai/papers/counterfactual-credit-policy-optimization-for-multi-agent-collaboration--arxiv-2603.21563/2026-06-11T03:46:07.422Z https://www.opentrain.ai/papers/what-do-world-models-learn-in-rl-probing-latent-representations-in-learned-envir--arxiv-2603.21546/2026-06-15T14:35:26.068Z https://www.opentrain.ai/papers/safepilot-a-framework-for-assuring-llm-enabled-cyber-physical-systems--arxiv-2603.21523/2026-06-15T13:05:31.433Z https://www.opentrain.ai/papers/efficient-failure-management-for-multi-agent-systems-with-reasoning-trace-repres--arxiv-2603.21522/2026-06-18T04:41:40.546Z https://www.opentrain.ai/papers/unified-mas-universally-generating-domain-specific-nodes-for-empowering-automati--arxiv-2603.21475/2026-06-13T00:54:00.894Z https://www.opentrain.ai/papers/cross-context-verification-hierarchical-detection-of-benchmark-contamination-thr--arxiv-2603.21454/2026-06-15T17:47:24.383Z https://www.opentrain.ai/papers/kg-hopper-empowering-compact-open-llms-with-knowledge-graph-reasoning-via-reinfo--arxiv-2603.21440/2026-06-12T09:39:59.197Z https://www.opentrain.ai/papers/llm-powered-workflow-optimization-for-multidisciplinary-software-development-an--arxiv-2603.21439/2026-06-16T05:10:58.608Z https://www.opentrain.ai/papers/domagent-leveraging-knowledge-graphs-and-case-based-reasoning-for-domain-specifi--arxiv-2603.21430/2026-06-18T02:38:58.502Z https://www.opentrain.ai/papers/pivotrl-high-accuracy-agentic-post-training-at-low-compute-cost--arxiv-2603.21383/2026-06-15T04:38:46.729Z https://www.opentrain.ai/papers/a-transformer-architecture-alteration-to-incentivise-externalised-reasoning--arxiv-2603.21376/2026-06-12T10:13:44.718Z https://www.opentrain.ai/papers/adarubric-task-adaptive-rubrics-for-llm-agent-evaluation--arxiv-2603.21362/2026-06-18T04:35:49.972Z https://www.opentrain.ai/papers/roboalign-learning-test-time-reasoning-for-language-action-alignment-in-vision-l--arxiv-2603.21341/2026-06-17T14:56:26.100Z https://www.opentrain.ai/papers/coinbench-moving-beyond-individual-perspectives-to-collective-intent-understandi--arxiv-2603.21329/2026-06-14T04:24:21.922Z https://www.opentrain.ai/papers/improving-coherence-and-persistence-in-agentic-ai-for-system-optimization--arxiv-2603.21321/2026-06-12T08:53:11.735Z https://www.opentrain.ai/papers/enhancing-reasoning-accuracy-in-large-language-models-during-inference-time--arxiv-2603.21301/2026-06-15T02:33:23.602Z https://www.opentrain.ai/papers/when-models-judge-themselves-unsupervised-self-evolution-for-multimodal-reasonin--arxiv-2603.21289/2026-06-16T19:01:56.814Z https://www.opentrain.ai/papers/warbench-a-comprehensive-benchmark-for-evaluating-llms-in-military-decision-maki--arxiv-2603.21280/2026-06-16T14:44:16.076Z https://www.opentrain.ai/papers/conversation-tree-architecture-a-structured-framework-for-context-aware-multi-br--arxiv-2603.21278/2026-06-16T15:25:59.479Z https://www.opentrain.ai/papers/aggregation-alignment-for-federated-learning-with-mixture-of-experts-under-data--arxiv-2603.21276/2026-06-12T08:53:12.592Z https://www.opentrain.ai/papers/the-library-theorem-how-external-organization-governs-agentic-reasoning-capacity--arxiv-2603.21272/2026-06-16T13:07:42.654Z https://www.opentrain.ai/papers/graph-of-states-solving-abductive-tasks-with-large-language-models--arxiv-2603.21250/2026-06-17T12:47:24.471Z https://www.opentrain.ai/papers/qmop-query-guided-mixture-of-projector-for-efficient-visual-token-compression--arxiv-2603.21232/2026-06-17T21:49:35.159Z https://www.opentrain.ai/papers/when-convenience-becomes-risk-a-semantic-view-of-under-specification-in-host-act--arxiv-2603.21231/2026-06-12T09:40:34.321Z https://www.opentrain.ai/papers/almab-dc-active-learning-multi-armed-bandits-and-distributed-computing-for-seque--arxiv-2603.21180/2026-06-17T14:14:22.556Z https://www.opentrain.ai/papers/reasonscaffold-a-scaffolded-reasoning-based-annotation-protocol-for-human-ai-co--arxiv-2603.21094/2026-06-16T11:25:27.020Z https://www.opentrain.ai/papers/alignment-whack-a-mole-finetuning-activates-verbatim-recall-of-copyrighted-books--arxiv-2603.20957/2026-06-16T10:25:38.163Z https://www.opentrain.ai/papers/clinical-cognition-alignment-for-gastrointestinal-diagnosis-with-multimodal-llms--arxiv-2603.20698/2026-04-11T23:19:50.429Z https://www.opentrain.ai/papers/pave-premise-aware-validation-and-editing-for-retrieval-augmented-llms--arxiv-2603.20673/2026-06-16T00:27:23.624Z https://www.opentrain.ai/papers/towards-intelligent-geospatial-data-discovery-a-knowledge-graph-driven-multi-age--arxiv-2603.20670/2026-06-18T01:22:23.482Z https://www.opentrain.ai/papers/mka-memory-keyed-attention-for-efficient-long-context-reasoning--arxiv-2603.20586/2026-06-17T18:48:53.988Z https://www.opentrain.ai/papers/permutation-consensus-listwise-judging-for-robust-factuality-evaluation--arxiv-2603.20562/2026-06-17T06:11:46.014Z https://www.opentrain.ai/papers/personavlm-long-term-personalized-multimodal-llms--arxiv-2604.13074/2026-04-20T21:18:57.568Z https://www.opentrain.ai/papers/revisql-achieving-human-level-text-to-sql--arxiv-2603.20004/2026-06-15T05:51:24.978Z https://www.opentrain.ai/papers/inducing-sustained-creativity-and-diversity-in-large-language-models--arxiv-2603.19519/2026-06-14T14:02:48.024Z https://www.opentrain.ai/papers/fintradebench-a-financial-reasoning-benchmark-for-llms--arxiv-2603.19225/2026-06-09T22:35:24.440Z https://www.opentrain.ai/papers/nemotron-cascade-2-post-training-llms-with-cascade-rl-and-multi-domain-on-policy--arxiv-2603.19220/2026-06-17T04:19:25.408Z https://www.opentrain.ai/papers/box-maze-a-process-control-architecture-for-reliable-llm-reasoning--arxiv-2603.19182/2026-06-14T05:51:38.561Z https://www.opentrain.ai/papers/sol-execbench-speed-of-light-benchmarking-for-real-world-gpu-kernels-against-har--arxiv-2603.19173/2026-06-07T15:54:09.201Z https://www.opentrain.ai/papers/ariadne-a-perception-reasoning-synergy-framework-for-trustworthy-coronary-angiog--arxiv-2603.19169/2026-06-16T08:29:51.862Z https://www.opentrain.ai/papers/evaluating-counterfactual-strategic-reasoning-in-large-language-models--arxiv-2603.19167/2026-06-15T07:47:49.791Z https://www.opentrain.ai/papers/cugenopt-a-gpu-accelerated-general-purpose-metaheuristic-framework-for-combinato--arxiv-2603.19163/2026-06-18T07:32:56.429Z https://www.opentrain.ai/papers/vepo-variable-entropy-policy-optimization-for-low-resource-language-foundation-m--arxiv-2603.19152/2026-06-16T11:56:51.775Z https://www.opentrain.ai/papers/d5p4-partition-determinantal-point-process-for-diversity-in-parallel-discrete-di--arxiv-2603.19146/2026-06-06T12:01:54.368Z https://www.opentrain.ai/papers/ugid-unified-graph-isomorphism-for-debiasing-large-language-models--arxiv-2603.19144/2026-06-14T14:36:23.700Z https://www.opentrain.ai/papers/how-uncertainty-estimation-scales-with-sampling-in-reasoning-models--arxiv-2603.19118/2026-06-11T09:20:39.966Z https://www.opentrain.ai/papers/camo-a-conditional-neural-solver-for-the-multi-objective-multiple-traveling-sale--arxiv-2603.19074/2026-04-18T15:52:07.384Z https://www.opentrain.ai/papers/parallelograms-strike-back-llms-generate-better-analogies-than-people--arxiv-2603.19066/2026-06-15T03:01:52.220Z https://www.opentrain.ai/papers/mori-learning-motivation-grounded-reasoning-for-scientific-ideation-in-large-lan--arxiv-2603.19044/2026-06-17T18:44:21.483Z https://www.opentrain.ai/papers/what-really-controls-temporal-reasoning-in-large-language-models-tokenisation-or--arxiv-2603.19017/2026-06-17T07:26:23.239Z https://www.opentrain.ai/papers/security-awareness-in-llm-agents-the-ndai-zone-case--arxiv-2603.19011/2026-06-15T19:09:04.237Z https://www.opentrain.ai/papers/hypothesis-conditioned-query-rewriting-for-decision-useful-retrieval--arxiv-2603.19008/2026-06-16T23:47:14.697Z https://www.opentrain.ai/papers/agentds-technical-report-benchmarking-the-future-of-human-ai-collaboration-in-do--arxiv-2603.19005/2026-06-18T02:57:59.234Z https://www.opentrain.ai/papers/evaluating-5w3h-structured-prompting-for-intent-alignment-in-human-ai-interactio--arxiv-2603.18976/2026-06-16T21:15:42.918Z https://www.opentrain.ai/papers/entropy-trajectory-shape-predicts-llm-reasoning-reliability-a-diagnostic-study-o--arxiv-2603.18940/2026-06-15T16:51:15.981Z https://www.opentrain.ai/papers/characterizing-linear-alignment-across-language-models--arxiv-2603.18908/2026-06-12T04:36:48.627Z https://www.opentrain.ai/papers/i-can-t-believe-it-s-corrupt-evaluating-corruption-in-multi-agent-governance-sys--arxiv-2603.18894/2026-06-17T13:03:15.579Z https://www.opentrain.ai/papers/bridging-network-fragmentation-a-semantic-augmented-drl-framework-for-uav-aided--arxiv-2603.18871/2026-06-17T19:40:53.150Z https://www.opentrain.ai/papers/motion-o-trajectory-grounded-video-reasoning--arxiv-2603.18856/2026-06-13T23:18:53.185Z https://www.opentrain.ai/papers/mi-dm-k-2-5-pro--arxiv-2603.18788/2026-06-16T15:32:51.900Z https://www.opentrain.ai/papers/memento-skills-let-agents-design-agents--arxiv-2603.18743/2026-06-18T06:12:42.891Z https://www.opentrain.ai/papers/causalrm-causal-theoretic-reward-modeling-for-rlhf-from-observational-user-feedb--arxiv-2603.18736/2026-06-18T02:20:35.547Z https://www.opentrain.ai/papers/hisr-hindsight-information-modulated-segmental-process-rewards-for-multi-turn-ag--arxiv-2603.18683/2026-06-15T05:44:23.055Z https://www.opentrain.ai/papers/mosaic-multi-objective-slice-aware-iterative-curation-for-alignment--arxiv-2603.18637/2026-05-10T15:07:22.250Z https://www.opentrain.ai/papers/learning-to-self-evolve--arxiv-2603.18620/2026-06-17T23:33:11.388Z https://www.opentrain.ai/papers/cross-modal-rationale-transfer-for-explainable-humanitarian-classification-on-so--arxiv-2603.18611/2026-06-16T07:01:24.664Z https://www.opentrain.ai/papers/specforge-a-flexible-and-efficient-open-source-training-framework-for-speculativ--arxiv-2603.18567/2026-05-08T07:38:31.774Z https://www.opentrain.ai/papers/ut-aca-uncertainty-triggered-adaptive-context-allocation-for-long-context-infere--arxiv-2603.18446/2026-04-23T02:42:26.238Z https://www.opentrain.ai/papers/taro-token-level-adaptive-routing-for-llm-test-time-alignment--arxiv-2603.18411/2026-06-17T22:44:48.073Z https://www.opentrain.ai/papers/topochunker-topology-aware-agentic-document-chunking-framework--arxiv-2603.18409/2026-06-17T21:27:09.247Z https://www.opentrain.ai/papers/unified-spatio-temporal-token-scoring-for-efficient-video-vlms--arxiv-2603.18004/2026-06-12T13:41:34.907Z https://www.opentrain.ai/papers/tdad-test-driven-agentic-development-reducing-code-regressions-in-ai-coding-agen--arxiv-2603.17973/2026-06-17T09:14:48.662Z https://www.opentrain.ai/papers/efficient-training-free-multi-token-prediction-via-embedding-space-probing--arxiv-2603.17942/2026-06-16T11:49:25.131Z https://www.opentrain.ai/papers/indicsafe-a-benchmark-for-evaluating-multilingual-llm-safety-in-south-asia--arxiv-2603.17915/2026-06-17T13:35:41.205Z https://www.opentrain.ai/papers/mitigating-llm-hallucinations-through-domain-grounded-tiered-retrieval--arxiv-2603.17872/2026-06-17T13:21:42.768Z https://www.opentrain.ai/papers/text-to-stage-spatial-layouts-from-long-form-narratives--arxiv-2603.17832/2026-06-17T23:37:34.137Z https://www.opentrain.ai/papers/process-supervision-for-chain-of-thought-reasoning-via-monte-carlo-net-informati--arxiv-2603.17815/2026-06-11T06:52:09.278Z https://www.opentrain.ai/papers/governed-memory-a-production-architecture-for-multi-agent-workflows--arxiv-2603.17787/2026-06-15T21:31:51.849Z https://www.opentrain.ai/papers/facts-as-first-class-objects-knowledge-objects-for-persistent-llm-memory--arxiv-2603.17781/2026-05-18T11:52:39.914Z https://www.opentrain.ai/papers/coverrl-breaking-the-consensus-trap-in-label-free-reasoning-via-generator-verifi--arxiv-2603.17775/2026-05-11T00:08:05.674Z https://www.opentrain.ai/papers/post-training-local-llm-agents-for-linux-privilege-escalation-with-verifiable-re--arxiv-2603.17673/2026-06-15T19:19:28.412Z https://www.opentrain.ai/papers/verigrey-greybox-agent-validation--arxiv-2603.17639/2026-06-15T04:26:35.516Z https://www.opentrain.ai/papers/complementary-reinforcement-learning--arxiv-2603.17621/2026-05-19T22:31:51.204Z https://www.opentrain.ai/papers/veriagent-a-tool-integrated-multi-agent-system-with-evolving-memory-for-ppa-awar--arxiv-2603.17613/2026-06-08T17:45:59.308Z https://www.opentrain.ai/papers/inducing-epistemological-humility-in-large-language-models-a-targeted-sft-approa--arxiv-2603.17504/2026-06-18T04:10:08.772Z https://www.opentrain.ai/papers/learning-when-to-attend-conditional-memory-access-for-long-context-llms--arxiv-2603.17484/2026-06-12T09:43:43.658Z https://www.opentrain.ai/papers/virpro-visual-referred-probabilistic-prompt-learning-for-weakly-supervised-monoc--arxiv-2603.17470/2026-06-16T10:13:25.960Z https://www.opentrain.ai/papers/trims-real-time-tracking-of-minimal-sufficient-length-for-efficient-reasoning-vi--arxiv-2603.17449/2026-05-02T10:57:46.806Z https://www.opentrain.ai/papers/infodensity-rewarding-information-dense-traces-for-efficient-reasoning--arxiv-2603.17310/2026-06-16T20:19:25.068Z https://www.opentrain.ai/papers/contrastive-reasoning-alignment-reinforcement-learning-from-hidden-representatio--arxiv-2603.17305/2026-06-17T19:56:13.391Z https://www.opentrain.ai/papers/symdirec-a-neuro-symbolic-divide-retrieve-conquer-framework-for-enhanced-rtl-syn--arxiv-2603.17208/2026-06-16T18:49:05.397Z https://www.opentrain.ai/papers/ensemble-self-training-for-unsupervised-machine-translation--arxiv-2603.17087/2026-05-29T07:58:15.734Z https://www.opentrain.ai/papers/internalizing-agency-from-reflective-experience--arxiv-2603.16843/2026-06-09T21:59:11.803Z https://www.opentrain.ai/papers/probing-cultural-signals-in-large-language-models-through-author-profiling--arxiv-2603.16749/2026-06-18T04:36:34.500Z https://www.opentrain.ai/papers/iquest-coder-v1-technical-report--arxiv-2603.16733/2026-05-13T11:36:19.947Z https://www.opentrain.ai/papers/fast-wam-do-world-action-models-need-test-time-future-imagination--arxiv-2603.16666/2026-06-18T05:08:39.561Z https://www.opentrain.ai/papers/omnilingual-sonar-cross-lingual-and-cross-modal-sentence-embeddings-bridging-mas--arxiv-2603.16606/2026-05-31T13:49:37.072Z https://www.opentrain.ai/papers/adamem-adaptive-user-centric-memory-for-long-horizon-dialogue-agents--arxiv-2603.16496/2026-06-16T09:44:53.997Z https://www.opentrain.ai/papers/enggpt2-sovereign-efficient-and-open-intelligence--arxiv-2603.16430/2026-06-17T00:28:46.594Z https://www.opentrain.ai/papers/indexrag-bridging-facts-for-cross-document-reasoning-at-index-time--arxiv-2603.16415/2026-06-14T10:13:42.081Z https://www.opentrain.ai/papers/recover-robust-entity-correction-via-agentic-orchestration-of-hypothesis-variant--arxiv-2603.16411/2026-06-18T02:47:37.091Z https://www.opentrain.ai/papers/fanar-2-0-arabic-generative-ai-stack--arxiv-2603.16397/2026-06-14T07:28:23.347Z https://www.opentrain.ai/papers/offline-exploration-aware-fine-tuning-for-long-chain-mathematical-reasoning--arxiv-2603.16206/2026-06-16T10:12:15.119Z https://www.opentrain.ai/papers/are-large-language-models-truly-smarter-than-humans--arxiv-2603.16197/2026-06-03T17:57:55.085Z https://www.opentrain.ai/papers/structured-semantic-cloaking-for-jailbreak-attacks-on-large-language-models--arxiv-2603.16192/2026-06-17T15:18:24.768Z https://www.opentrain.ai/papers/parametric-social-identity-injection-and-diversification-in-public-opinion-simul--arxiv-2603.16142/2026-06-08T04:33:17.705Z https://www.opentrain.ai/papers/sia-a-synthesize-inject-align-framework-for-knowledge-grounded-and-secure-e-comm--arxiv-2603.16137/2026-06-14T13:40:15.913Z https://www.opentrain.ai/papers/understanding-moral-reasoning-trajectories-in-large-language-models-toward-probi--arxiv-2603.16017/2026-06-17T13:36:38.922Z https://www.opentrain.ai/papers/banglasocialbench-a-benchmark-for-evaluating-sociopragmatic-and-cultural-alignme--arxiv-2603.15949/2026-04-11T16:17:59.475Z https://www.opentrain.ai/papers/openseeker-democratizing-frontier-search-agents-by-fully-open-sourcing-training--arxiv-2603.15594/2026-06-18T06:17:00.611Z https://www.opentrain.ai/papers/thinking-in-latents-adaptive-anchor-refinement-for-implicit-reasoning-in-llms--arxiv-2603.15051/2026-06-15T06:37:20.640Z https://www.opentrain.ai/papers/rs-worldmodel-a-unified-model-for-remote-sensing-understanding-and-future-sense--arxiv-2603.14941/2026-06-16T15:00:37.006Z https://www.opentrain.ai/papers/llm-as-graph-kernel-rethinking-message-passing-on-text-rich-graphs--arxiv-2603.14937/2026-06-17T07:35:13.166Z https://www.opentrain.ai/papers/exposst-explicit-positioning-with-adaptive-masking-for-llm-based-simultaneous-ma--arxiv-2603.14903/2026-06-17T19:52:13.959Z https://www.opentrain.ai/papers/decision-level-ordinal-modeling-for-multimodal-essay-scoring-with-large-language--arxiv-2603.14891/2026-06-17T11:23:38.907Z https://www.opentrain.ai/papers/shopping-companion-a-memory-augmented-llm-agent-for-real-world-e-commerce-tasks--arxiv-2603.14864/2026-06-13T03:12:25.306Z https://www.opentrain.ai/papers/the-impact-of-ideological-discourses-in-rag-a-case-study-with-covid-19-treatment--arxiv-2603.14838/2026-06-16T15:12:17.993Z https://www.opentrain.ai/papers/razor-ratio-aware-layer-editing-for-targeted-unlearning-in-vision-transformers-a--arxiv-2603.14819/2026-06-16T15:04:16.966Z https://www.opentrain.ai/papers/universe-routing-why-self-evolving-agents-need-epistemic-control--arxiv-2603.14799/2026-06-09T23:31:58.534Z https://www.opentrain.ai/papers/openhospital-a-thing-in-itself-arena-for-evolving-and-benchmarking-llm-based-col--arxiv-2603.14771/2026-06-15T13:12:55.464Z https://www.opentrain.ai/papers/polca-stochastic-generative-optimization-with-llm--arxiv-2603.14769/2026-06-14T03:13:40.343Z https://www.opentrain.ai/papers/brainbench-exposing-the-commonsense-reasoning-gap-in-large-language-models--arxiv-2603.14761/2026-06-13T00:57:26.483Z https://www.opentrain.ai/papers/gameuiagent-an-llm-powered-framework-for-automated-game-ui-design-with-structure--arxiv-2603.14724/2026-06-16T19:22:47.925Z https://www.opentrain.ai/papers/beyond-creed-a-non-identity-safety-condition-a-strong-empirical-alternative-to-i--arxiv-2603.14723/2026-06-17T03:17:22.474Z https://www.opentrain.ai/papers/towards-next-generation-llm-training-from-the-data-centric-perspective--arxiv-2603.14712/2026-06-18T04:36:20.055Z https://www.opentrain.ai/papers/beyond-local-code-optimization-multi-agent-reasoning-for-software-system-optimiz--arxiv-2603.14703/2026-06-17T05:55:51.557Z https://www.opentrain.ai/papers/argumentation-for-explainable-and-globally-contestable-decision-support-with-llm--arxiv-2603.14643/2026-06-16T05:03:33.256Z https://www.opentrain.ai/papers/nudging-hidden-states-training-free-model-steering-for-chain-of-thought-reasonin--arxiv-2603.14636/2026-06-13T10:38:24.735Z https://www.opentrain.ai/papers/pa3-policy-aware-agent-alignment-through-chain-of-thought--arxiv-2603.14602/2026-06-09T04:36:33.465Z https://www.opentrain.ai/papers/parameter-efficient-quality-estimation-via-frozen-recursive-models--arxiv-2603.14593/2026-06-09T20:02:01.951Z https://www.opentrain.ai/papers/causalevolve-towards-open-ended-discovery-with-causal-scratchpad--arxiv-2603.14575/2026-05-31T13:19:22.429Z https://www.opentrain.ai/papers/malicious-intent-dataset-and-inoculating-llms-for-enhanced-disinformation-detect--arxiv-2603.14525/2026-06-14T12:25:40.298Z https://www.opentrain.ai/papers/cangjiebench-benchmarking-llms-on-a-low-resource-general-purpose-programming-lan--arxiv-2603.14501/2026-06-18T02:52:44.226Z https://www.opentrain.ai/papers/fine-tuning-mllms-without-forgetting-is-easier-than-you-think--arxiv-2603.14493/2026-06-17T06:48:34.632Z https://www.opentrain.ai/papers/infinite-problem-generator-verifiably-scaling-physics-reasoning-data-with-agenti--arxiv-2603.14486/2026-06-16T12:09:14.950Z https://www.opentrain.ai/papers/ai-can-learn-scientific-taste--arxiv-2603.14473/2026-06-18T04:34:28.452Z https://www.opentrain.ai/papers/an-industrial-scale-insurance-llm-achieving-verifiable-domain-mastery-and-halluc--arxiv-2603.14463/2026-06-17T18:49:47.984Z https://www.opentrain.ai/papers/distilling-reasoning-without-knowledge-a-framework-for-reliable-llms--arxiv-2603.14458/2026-06-16T14:05:15.710Z https://www.opentrain.ai/papers/parsa-bench-a-comprehensive-persian-audio-language-model-benchmark--arxiv-2603.14456/2026-06-17T11:45:34.316Z https://www.opentrain.ai/papers/questionnaire-responses-do-not-capture-the-safety-of-ai-agents--arxiv-2603.14417/2026-06-17T07:08:05.502Z https://www.opentrain.ai/papers/extending-minimal-pairs-with-ordinal-surprisal-curves-and-entropy-across-applied--arxiv-2603.14400/2026-06-09T02:44:40.995Z https://www.opentrain.ai/papers/ecg-reasoning-benchmark-a-benchmark-for-evaluating-clinical-reasoning-capabiliti--arxiv-2603.14326/2026-06-17T15:56:30.011Z https://www.opentrain.ai/papers/mind-the-shift-decoding-monetary-policy-stance-from-fomc-statements-with-large-l--arxiv-2603.14313/2026-06-09T20:08:07.823Z https://www.opentrain.ai/papers/semanticache-efficient-kv-cache-compression-via-semantic-chunking-and-clustered--arxiv-2603.14303/2026-06-15T06:14:37.128Z https://www.opentrain.ai/papers/seeking-physics-in-diffusion-noise--arxiv-2603.14294/2026-06-15T18:50:51.246Z https://www.opentrain.ai/papers/medpriv-bench-benchmarking-the-privacy-utility-trade-off-of-large-language-model--arxiv-2603.14265/2026-06-17T18:40:50.437Z https://www.opentrain.ai/papers/automatic-inter-document-multi-hop-scientific-qa-generation--arxiv-2603.14257/2026-06-17T23:36:15.690Z https://www.opentrain.ai/papers/why-do-llm-based-web-agents-fail-a-hierarchical-planning-perspective--arxiv-2603.14248/2026-06-17T08:59:41.918Z https://www.opentrain.ai/papers/mmou-a-massive-multi-task-omni-understanding-and-reasoning-benchmark-for-long-an--arxiv-2603.14145/2026-06-17T05:23:47.242Z https://www.opentrain.ai/papers/understanding-the-emergence-of-seemingly-useless-features-in-next-token-predicto--arxiv-2603.14087/2026-06-15T13:10:18.967Z https://www.opentrain.ai/papers/the-reasoning-bottleneck-in-graph-rag-structured-prompting-and-context-compressi--arxiv-2603.14045/2026-06-16T14:47:29.895Z https://www.opentrain.ai/papers/supervised-fine-tuning-versus-reinforcement-learning-a-study-of-post-training-me--arxiv-2603.13985/2026-06-14T12:33:44.501Z https://www.opentrain.ai/papers/flux-data-worth-training-on--arxiv-2603.13972/2026-06-18T05:40:12.367Z https://www.opentrain.ai/papers/toolflood-beyond-selection-hiding-valid-tools-from-llm-agents-via-semantic-cover--arxiv-2603.13950/2026-05-11T05:25:21.360Z https://www.opentrain.ai/papers/omnicompliance-100k-a-multi-domain-rule-grounded-real-world-safety-compliance-da--arxiv-2603.13933/2026-06-09T19:18:11.589Z https://www.opentrain.ai/papers/step-cot-stepwise-visual-chain-of-thought-for-medical-visual-question-answering--arxiv-2603.13878/2026-06-17T05:01:59.527Z https://www.opentrain.ai/papers/gradmem-learning-to-write-context-into-memory-with-test-time-gradient-descent--arxiv-2603.13875/2026-06-16T14:59:39.811Z https://www.opentrain.ai/papers/apex-searcher-augmenting-llms-search-capabilities-through-agentic-planning-and-e--arxiv-2603.13853/2026-05-22T08:07:17.878Z https://www.opentrain.ai/papers/deceptguard-a-constitutional-oversight-framework-for-detecting-deception-in-llm--arxiv-2603.13791/2026-06-15T01:49:46.674Z https://www.opentrain.ai/papers/greedy-information-projection-for-llm-data-selection--arxiv-2603.13790/2026-06-17T09:26:11.658Z https://www.opentrain.ai/papers/knowledge-distillation-for-large-language-models--arxiv-2603.13765/2026-06-16T23:12:18.804Z https://www.opentrain.ai/papers/can-we-trust-llms-on-memristors-diving-into-reasoning-ability-under-non-ideality--arxiv-2603.13725/2026-06-16T14:49:17.801Z https://www.opentrain.ai/papers/saatt-nav-a-socially-aware-autonomous-transparent-transportation-navigation-fram--arxiv-2603.13698/2026-06-15T08:30:00.946Z https://www.opentrain.ai/papers/nccl-ep-towards-a-unified-expert-parallel-communication-api-for-nccl--arxiv-2603.13606/2026-06-16T11:36:48.913Z https://www.opentrain.ai/papers/prefpo-pairwise-preference-prompt-optimization--arxiv-2603.19311/2026-06-14T22:40:55.031Z https://www.opentrain.ai/papers/semantic-invariance-in-agentic-ai--arxiv-2603.13173/2026-06-17T04:01:37.353Z https://www.opentrain.ai/papers/davinci-env-open-swe-environment-synthesis-at-scale--arxiv-2603.13023/2026-06-16T20:39:52.055Z https://www.opentrain.ai/papers/efficient-and-interpretable-multi-agent-llm-routing-via-ant-colony-optimization--arxiv-2603.12933/2026-06-17T15:48:41.580Z https://www.opentrain.ai/papers/i-know-what-i-don-t-know-latent-posterior-factor-models-for-multi-evidence-proba--arxiv-2603.15670/2026-06-16T15:15:24.393Z https://www.opentrain.ai/papers/adaptive-vision-language-model-routing-for-computer-use-agents--arxiv-2603.12823/2026-06-16T22:44:19.854Z https://www.opentrain.ai/papers/altered-thoughts-altered-actions-probing-chain-of-thought-vulnerabilities-in-vla--arxiv-2603.12717/2026-06-18T01:24:15.049Z https://www.opentrain.ai/papers/ai-planning-framework-for-llm-based-web-agents--arxiv-2603.12710/2026-06-16T22:36:38.449Z https://www.opentrain.ai/papers/cost-efficient-multimodal-llm-inference-via-cross-tier-gpu-heterogeneity--arxiv-2603.12707/2026-06-17T09:48:58.398Z https://www.opentrain.ai/papers/fgtr-fine-grained-multi-table-retrieval-via-hierarchical-llm-reasoning--arxiv-2603.12702/2026-06-17T22:56:12.917Z https://www.opentrain.ai/papers/evolvecoder-evolving-test-cases-via-adversarial-verification-for-code-reinforcem--arxiv-2603.12698/2026-06-16T14:51:20.626Z https://www.opentrain.ai/papers/agentdrift-unsafe-recommendation-drift-under-tool-corruption-hidden-by-ranking-m--arxiv-2603.12564/2026-06-17T06:25:54.282Z https://www.opentrain.ai/papers/spatio-semantic-expert-routing-architecture-with-mixture-of-experts-for-referrin--arxiv-2603.12538/2026-06-18T00:39:50.179Z https://www.opentrain.ai/papers/llm-biasscope-a-real-time-bias-analysis-platform-for-comparative-llm-evaluation--arxiv-2603.12522/2026-06-17T07:23:12.713Z https://www.opentrain.ai/papers/red-teaming-vision-language-action-models-via-quality-diversity-prompt-generatio--arxiv-2603.12510/2026-06-18T01:21:30.412Z https://www.opentrain.ai/papers/shattering-the-shortcut-a-topology-regularized-benchmark-for-multi-hop-medical-r--arxiv-2603.12458/2026-06-16T11:22:29.723Z https://www.opentrain.ai/papers/cse-uoi-at-semeval-2026-task-6-a-two-stage-heterogeneous-ensemble-with-deliberat--arxiv-2603.12453/2026-06-16T14:48:17.110Z https://www.opentrain.ai/papers/neurolora-context-aware-neuromodulation-for-parameter-efficient-multi-task-adapt--arxiv-2603.12378/2026-06-15T16:52:14.159Z https://www.opentrain.ai/papers/multi-step-semantic-reasoning-in-generative-retrieval--arxiv-2603.12368/2026-06-17T09:38:28.848Z https://www.opentrain.ai/papers/endocot-scaling-endogenous-chain-of-thought-reasoning-in-diffusion-models--arxiv-2603.12252/2026-06-18T04:32:23.723Z https://www.opentrain.ai/papers/sparking-scientific-creativity-via-llm-driven-interdisciplinary-inspiration--arxiv-2603.12226/2026-06-17T15:18:55.124Z https://www.opentrain.ai/papers/indexcache-accelerating-sparse-attention-via-cross-layer-index-reuse--arxiv-2603.12201/2026-06-17T14:24:56.439Z https://www.opentrain.ai/papers/long-context-encoder-models-for-polish-language-understanding--arxiv-2603.12191/2026-06-10T03:11:57.172Z https://www.opentrain.ai/papers/behaviorvlm-unified-finetuning-free-behavioral-understanding-with-vision-languag--arxiv-2603.12176/2026-06-15T17:28:52.095Z https://www.opentrain.ai/papers/qaq-bidirectional-semantic-coherence-for-selecting-high-quality-synthetic-code-i--arxiv-2603.12165/2026-06-16T15:56:59.118Z https://www.opentrain.ai/papers/glyphbanana-advancing-precise-text-rendering-through-agentic-workflows--arxiv-2603.12155/2026-06-17T10:28:25.567Z https://www.opentrain.ai/papers/automatic-generation-of-high-performance-rl-environments--arxiv-2603.12145/2026-06-16T23:24:16.787Z https://www.opentrain.ai/papers/topobench-benchmarking-llms-on-hard-topological-reasoning--arxiv-2603.12133/2026-06-16T15:56:57.606Z https://www.opentrain.ai/papers/increasing-intelligence-in-ai-agents-can-worsen-collective-outcomes--arxiv-2603.12129/2026-05-30T05:09:27.095Z https://www.opentrain.ai/papers/cross-context-review-improving-llm-output-quality-by-separating-production-and-r--arxiv-2603.12123/2026-06-18T04:15:42.853Z https://www.opentrain.ai/papers/on-information-self-locking-in-reinforcement-learning-for-active-reasoning-of-ll--arxiv-2603.12109/2026-06-18T03:53:07.708Z https://www.opentrain.ai/papers/resource-efficient-iterative-llm-based-nas-with-feedback-memory--arxiv-2603.12091/2026-06-17T08:28:45.249Z https://www.opentrain.ai/papers/labshield-a-multimodal-benchmark-for-safety-critical-reasoning-and-planning-in-s--arxiv-2603.11987/2026-06-17T06:20:36.820Z https://www.opentrain.ai/papers/think-while-watching-online-streaming-segment-level-memory-for-multi-turn-video--arxiv-2603.11896/2026-05-06T08:37:33.205Z https://www.opentrain.ai/papers/bielik-minitron-7b-compressing-large-language-models-via-structured-pruning-and--arxiv-2603.11881/2026-06-16T15:40:59.589Z https://www.opentrain.ai/papers/from-control-to-foresight-simulation-as-a-new-paradigm-for-human-agent-collabora--arxiv-2603.11677/2026-06-12T10:11:13.119Z https://www.opentrain.ai/papers/multi-task-reinforcement-learning-for-enhanced-multimodal-llm-as-a-judge--arxiv-2603.11665/2026-06-17T23:27:59.411Z https://www.opentrain.ai/papers/nuanced-emotion-recognition-based-on-a-segment-based-mllm-framework-leveraging-q--arxiv-2603.13406/2026-06-14T12:32:29.525Z https://www.opentrain.ai/papers/performance-evaluation-of-open-source-large-language-models-for-assisting-pathol--arxiv-2603.11597/2026-06-17T07:26:19.159Z https://www.opentrain.ai/papers/where-matters-more-than-what-decoding-aligned-kv-cache-compression-via-position--arxiv-2603.11564/2026-04-23T02:37:42.729Z https://www.opentrain.ai/papers/try-check-and-retry-a-divide-and-conquer-framework-for-boosting-long-context-too--arxiv-2603.11495/2026-05-18T08:08:38.302Z https://www.opentrain.ai/papers/bloop-zero-shot-abstractive-summarization-using-large-language-models-with-bigra--arxiv-2603.11415/2026-06-06T11:58:00.513Z https://www.opentrain.ai/papers/stop-listening-to-me-how-multi-turn-conversations-can-degrade-diagnostic-reasoni--arxiv-2603.11394/2026-05-31T05:23:30.970Z https://www.opentrain.ai/papers/evaluating-explainable-ai-attribution-methods-in-neural-machine-translation-via--arxiv-2603.11342/2026-06-17T07:29:27.913Z https://www.opentrain.ai/papers/compass-the-explainable-agentic-framework-for-sovereignty-sustainability-complia--arxiv-2603.11277/2026-06-17T15:45:57.287Z https://www.opentrain.ai/papers/llms-can-infer-political-alignment-from-online-conversations--arxiv-2603.11253/2026-06-17T23:51:47.713Z https://www.opentrain.ai/papers/markovian-generation-chains-in-large-language-models--arxiv-2603.11228/2026-06-16T10:56:57.803Z https://www.opentrain.ai/papers/dereason-a-difficulty-aware-curriculum-improves-decoupled-sft-then-rl-training-f--arxiv-2603.11193/2026-06-17T13:09:36.836Z https://www.opentrain.ai/papers/comic-agentic-sketch-comedy-generation--arxiv-2603.11048/2026-06-17T08:13:16.115Z https://www.opentrain.ai/papers/instruction-set-for-the-representation-of-graphs--arxiv-2603.11039/2026-06-15T03:48:53.224Z https://www.opentrain.ai/papers/groundcount-grounding-vision-language-models-with-object-detection-for-mitigatin--arxiv-2603.10978/2026-06-17T14:39:53.721Z https://www.opentrain.ai/papers/webweaver-breaking-topology-confidentiality-in-llm-multi-agent-systems-with-stea--arxiv-2603.11132/2026-06-18T03:27:59.385Z https://www.opentrain.ai/papers/llm2vec-gen-generative-embeddings-from-large-language-models--arxiv-2603.10913/2026-06-17T20:38:44.606Z https://www.opentrain.ai/papers/a-hybrid-knowledge-grounded-framework-for-safety-and-traceability-in-prescriptio--arxiv-2603.10891/2026-06-10T07:55:53.206Z https://www.opentrain.ai/papers/dynamics-predictive-sampling-for-active-rl-finetuning-of-large-reasoning-models--arxiv-2603.10887/2026-06-17T01:31:24.139Z https://www.opentrain.ai/papers/continuous-diffusion-transformers-for-designing-synthetic-regulatory-elements--arxiv-2603.10885/2026-06-16T16:05:37.228Z https://www.opentrain.ai/papers/from-images-to-words-efficient-cross-modal-knowledge-distillation-to-language-mo--arxiv-2603.10877/2026-06-16T20:24:29.865Z https://www.opentrain.ai/papers/grace-a-unified-2d-multi-robot-path-planning-simulator-benchmark-for-grid-roadma--arxiv-2603.10858/2026-06-16T16:45:41.626Z https://www.opentrain.ai/papers/towards-cold-start-drafting-and-continual-refining-a-value-driven-memory-approac--arxiv-2603.10846/2026-06-17T21:10:56.763Z https://www.opentrain.ai/papers/nurture-first-agent-development-building-domain-expert-ai-agents-through-convers--arxiv-2603.10808/2026-06-16T16:45:35.753Z https://www.opentrain.ai/papers/risk-adjusted-harm-scoring-for-automated-red-teaming-for-llms-in-financial-servi--arxiv-2603.10807/2026-06-17T11:20:29.938Z https://www.opentrain.ai/papers/word-recovery-in-large-language-models-enables-character-level-tokenization-robu--arxiv-2603.10771/2026-06-09T19:34:46.503Z https://www.opentrain.ai/papers/heartagent-an-autonomous-agent-system-for-explainable-differential-diagnosis-in--arxiv-2603.10764/2026-06-09T19:24:58.472Z https://www.opentrain.ai/papers/structured-linked-data-as-a-memory-layer-for-agent-orchestrated-retrieval--arxiv-2603.10700/2026-06-10T21:15:40.197Z https://www.opentrain.ai/papers/emulating-clinician-cognition-via-self-evolving-deep-clinical-research--arxiv-2603.10677/2026-06-18T02:36:31.930Z https://www.opentrain.ai/papers/does-llm-alignment-really-need-diversity-an-empirical-study-of-adapting-rlvr-met--arxiv-2603.10588/2026-06-17T21:43:37.630Z https://www.opentrain.ai/papers/cuaaudit-meta-evaluation-of-vision-language-models-as-auditors-of-autonomous-com--arxiv-2603.10577/2026-05-10T03:18:05.241Z https://www.opentrain.ai/papers/end-to-end-chatbot-evaluation-with-adaptive-reasoning-and-uncertainty-filtering--arxiv-2603.10570/2026-06-14T12:36:22.081Z https://www.opentrain.ai/papers/ih-challenge-a-training-dataset-to-improve-instruction-hierarchy-on-frontier-llm--arxiv-2603.10521/2026-06-17T18:30:22.671Z https://www.opentrain.ai/papers/peem-prompt-engineering-evaluation-metrics-for-interpretable-joint-evaluation-of--arxiv-2603.10477/2026-06-16T22:14:11.905Z https://www.opentrain.ai/papers/learning-to-negotiate-multi-agent-deliberation-for-collective-value-alignment-in--arxiv-2603.10476/2026-06-17T22:18:12.762Z https://www.opentrain.ai/papers/aligning-large-language-models-with-searcher-preferences--arxiv-2603.10473/2026-06-17T21:44:32.645Z https://www.opentrain.ai/papers/mitigating-translationese-bias-in-multilingual-llm-as-a-judge-via-disentangled-i--arxiv-2603.10351/2026-06-16T04:23:23.394Z https://www.opentrain.ai/papers/overcoming-visual-clutter-in-vision-language-action-models-via-concept-gated-vis--arxiv-2603.10340/2026-06-15T18:41:49.017Z https://www.opentrain.ai/papers/large-language-models-can-disambiguate-opioid-slang-on-social-media--arxiv-2603.10313/2026-06-16T15:10:42.210Z https://www.opentrain.ai/papers/is-this-idea-novel-an-automated-benchmark-for-judgment-of-research-ideas--arxiv-2603.10303/2026-06-17T21:44:37.724Z https://www.opentrain.ai/papers/gr-sap-generative-replay-for-safety-alignment-preservation-during-fine-tuning--arxiv-2603.10243/2026-06-17T15:48:54.994Z https://www.opentrain.ai/papers/s-grades-studying-generalization-of-student-response-assessments-in-diverse-eval--arxiv-2603.10233/2026-06-18T05:25:17.782Z https://www.opentrain.ai/papers/adaptive-activation-cancellation-for-hallucination-mitigation-in-large-language--arxiv-2603.10195/2026-06-15T03:11:28.218Z https://www.opentrain.ai/papers/video-based-reward-modeling-for-computer-use-agents--arxiv-2603.10178/2026-06-17T21:43:16.666Z https://www.opentrain.ai/papers/calibration-reasoning-framework-for-descriptive-speech-quality-assessment--arxiv-2603.10175/2026-06-16T11:10:20.887Z https://www.opentrain.ai/papers/openclaw-rl-train-any-agent-simply-by-talking--arxiv-2603.10165/2026-06-18T04:35:29.779Z https://www.opentrain.ai/papers/clipo-contrastive-learning-in-policy-optimization-generalizes-rlvr--arxiv-2603.10101/2026-05-24T10:39:01.444Z https://www.opentrain.ai/papers/think-before-you-lie-how-reasoning-improves-honesty--arxiv-2603.09957/2026-06-18T00:14:03.427Z https://www.opentrain.ai/papers/towards-a-neural-debugger-for-python--arxiv-2603.09951/2026-06-16T14:00:48.909Z https://www.opentrain.ai/papers/pathmem-toward-cognition-aligned-memory-transformation-for-pathology-mllms--arxiv-2603.09943/2026-06-15T22:48:04.890Z https://www.opentrain.ai/papers/model-merging-in-the-era-of-large-language-models-methods-applications-and-futur--arxiv-2603.09938/2026-06-14T13:04:22.078Z https://www.opentrain.ai/papers/mssr-memory-aware-adaptive-replay-for-continual-llm-fine-tuning--arxiv-2603.09892/2026-06-17T21:55:15.672Z https://www.opentrain.ai/papers/influencing-llm-multi-agent-dialogue-via-policy-parameterized-prompts--arxiv-2603.09890/2026-06-17T09:34:44.153Z https://www.opentrain.ai/papers/one-eval-an-agentic-system-for-automated-and-traceable-llm-evaluation--arxiv-2603.09821/2026-06-17T13:22:47.236Z https://www.opentrain.ai/papers/mitra-an-ai-assistant-for-knowledge-retrieval-in-physics-collaborations--arxiv-2603.09800/2026-05-29T15:44:13.168Z https://www.opentrain.ai/papers/quantifying-the-necessity-of-chain-of-thought-through-opaque-serial-depth--arxiv-2603.09786/2026-06-12T15:39:20.323Z https://www.opentrain.ai/papers/epic-europarl-uds-information-theoretic-perspectives-on-translation-and-interpre--arxiv-2603.09785/2026-06-16T15:41:00.560Z https://www.opentrain.ai/papers/ego-embedding-guided-personalization-of-vision-language-models--arxiv-2603.09771/2026-06-16T15:11:43.901Z