https://www.opentrain.ai/papers/eyes-on-target-gaze-aware-object-detection-in-egocentric-video--arxiv-2511.01237/2026-06-18T07:22:14.896Z https://www.opentrain.ai/papers/belief-dynamics-reveal-the-dual-nature-of-in-context-learning-and-activation-ste--arxiv-2511.00617/2026-04-15T16:38:39.147Z https://www.opentrain.ai/papers/when-distributions-shifts-causal-generalization-for-low-resource-languages--arxiv-2510.27512/2026-06-09T03:58:35.520Z https://www.opentrain.ai/papers/analysing-environmental-efficiency-in-ai-for-x-ray-diagnosis--arxiv-2511.07436/2026-06-18T05:15:24.326Z https://www.opentrain.ai/papers/probability-distributions-computed-by-autoregressive-transformers--arxiv-2510.27118/2026-06-08T10:29:12.004Z https://www.opentrain.ai/papers/vista-verification-in-sequential-turn-based-assessment--arxiv-2510.27052/2026-06-13T09:49:49.900Z https://www.opentrain.ai/papers/frame-semantic-patterns-for-identifying-underreporting-of-notifiable-events-in-h--arxiv-2510.26969/2026-06-16T15:14:13.536Z https://www.opentrain.ai/papers/evontree-ontology-rule-guided-self-evolution-of-large-language-models--arxiv-2510.26683/2026-06-15T03:56:42.004Z https://www.opentrain.ai/papers/synbullying-a-multi-llm-synthetic-conversational-dataset-for-cyberbullying-detec--arxiv-2511.11599/2026-06-18T05:37:22.941Z https://www.opentrain.ai/papers/open-korean-historical-corpus-a-millennia-scale-diachronic-collection-of-public--arxiv-2510.24541/2026-05-16T02:45:12.298Z https://www.opentrain.ai/papers/luxit-a-luxembourgish-instruction-tuning-dataset-from-monolingual-seed-data--arxiv-2510.24434/2026-06-18T03:23:57.952Z https://www.opentrain.ai/papers/quantifying-systemic-vulnerability-in-the-foundation-model-industry--arxiv-2510.23421/2026-06-10T08:45:21.228Z https://www.opentrain.ai/papers/swiftembed-ultra-fast-text-embeddings-via-static-token-lookup-for-real-time-appl--arxiv-2510.24793/2026-06-11T08:25:07.549Z https://www.opentrain.ai/papers/understanding-in-context-learning-beyond-transformers-an-investigation-of-state--arxiv-2510.23006/2026-05-15T23:51:21.235Z https://www.opentrain.ai/papers/rule-based-explanations-for-retrieval-augmented-llm-systems--arxiv-2510.22689/2026-06-16T16:02:31.652Z https://www.opentrain.ai/papers/from-slides-to-chatbots-enhancing-large-language-models-with-university-course-m--arxiv-2510.22272/2026-06-18T02:49:41.653Z https://www.opentrain.ai/papers/penalizing-length-uncovering-systematic-bias-in-quality-estimation-metrics--arxiv-2510.22028/2026-06-18T04:22:51.239Z https://www.opentrain.ai/papers/steering-evaluation-aware-language-models-to-act-like-they-are-deployed--arxiv-2510.20487/2026-05-22T08:39:35.357Z https://www.opentrain.ai/papers/evaluating-latent-knowledge-of-public-tabular-datasets-in-large-language-models--arxiv-2510.20351/2026-05-22T07:38:53.163Z https://www.opentrain.ai/papers/citation-failure-definition-analysis-and-efficient-mitigation--arxiv-2510.20303/2026-05-22T06:35:36.925Z https://www.opentrain.ai/papers/difficulty-controllable-multiple-choice-question-generation-using-large-language--arxiv-2510.19265/2026-06-08T13:33:21.792Z https://www.opentrain.ai/papers/oren-octree-residual-network-for-real-time-euclidean-signed-distance-mapping--arxiv-2510.18999/2026-06-18T07:22:02.436Z https://www.opentrain.ai/papers/lightmem-lightweight-and-efficient-memory-augmented-generation--arxiv-2510.18866/2026-06-16T20:18:38.611Z https://www.opentrain.ai/papers/cefr-annotated-wordnet-llm-based-proficiency-guided-semantic-database-for-langua--arxiv-2510.18466/2026-06-18T05:34:40.618Z https://www.opentrain.ai/papers/cogate-lstm-prototype-guided-feature-space-gating-for-mitigating-gradient-diluti--arxiv-2510.17018/2026-06-17T09:06:34.189Z https://www.opentrain.ai/papers/in-generative-ai-we-dis-trust-computational-analysis-of-trust-and-distrust-in-re--arxiv-2510.16173/2026-06-16T05:58:15.099Z https://www.opentrain.ai/papers/language-models-are-injective-and-hence-invertible--arxiv-2510.15511/2026-06-17T19:40:10.631Z https://www.opentrain.ai/papers/from-binary-to-bilingual-how-the-national-weather-service-is-using-artificial-in--arxiv-2510.14369/2026-05-22T08:38:06.452Z https://www.opentrain.ai/papers/understanding-the-ability-of-llms-to-handle-character-level-perturbation--arxiv-2510.14365/2026-05-22T07:22:12.138Z https://www.opentrain.ai/papers/assessing-web-search-credibility-and-response-groundedness-in-chat-assistants--arxiv-2510.13749/2026-05-22T06:12:10.860Z https://www.opentrain.ai/papers/embedding-based-context-aware-reranker--arxiv-2510.13329/2026-06-18T05:30:55.997Z https://www.opentrain.ai/papers/llm-prompt-duel-optimizer-efficient-label-free-prompt-optimization--arxiv-2510.13907/2026-06-18T01:40:32.650Z https://www.opentrain.ai/papers/community-size-rather-than-grammatical-complexity-better-predicts-large-language--arxiv-2510.12463/2026-06-17T23:56:38.600Z https://www.opentrain.ai/papers/beyond-the-crowd-llm-augmented-community-notes-for-governing-health-misinformati--arxiv-2510.11423/2026-06-16T22:47:29.212Z https://www.opentrain.ai/papers/cnsocialdepress-a-chinese-social-media-dataset-for-depression-risk-detection-and--arxiv-2510.11233/2026-06-17T03:03:13.113Z https://www.opentrain.ai/papers/detecting-hallucinations-in-authentic-llm-human-interactions--arxiv-2510.10539/2026-06-17T18:28:35.406Z https://www.opentrain.ai/papers/spg-sandwiched-policy-gradient-for-masked-diffusion-language-models--arxiv-2510.09541/2026-06-16T10:07:40.025Z https://www.opentrain.ai/papers/inflated-excellence-or-true-performance-rethinking-medical-diagnostic-benchmarks--arxiv-2510.09275/2026-06-17T20:20:41.066Z https://www.opentrain.ai/papers/a-linguistics-aware-llm-watermarking-via-syntactic-predictability--arxiv-2510.13829/2026-06-17T18:19:52.349Z https://www.opentrain.ai/papers/augmenting-rating-scale-measures-with-text-derived-items-using-the-information-d--arxiv-2510.08663/2026-05-28T16:28:22.810Z https://www.opentrain.ai/papers/emotionally-charged-logically-blurred-ai-driven-emotional-framing-impairs-human--arxiv-2510.09695/2026-05-30T12:43:34.691Z https://www.opentrain.ai/papers/neuron-level-analysis-of-cultural-understanding-in-large-language-models--arxiv-2510.08284/2026-06-16T15:26:34.557Z https://www.opentrain.ai/papers/understanding-temporal-logic-consistency-in-video-language-models-through-cross--arxiv-2510.08138/2026-04-13T15:07:10.149Z https://www.opentrain.ai/papers/fewer-weights-more-problems-a-practical-attack-on-llm-pruning--arxiv-2510.07985/2026-06-17T22:37:13.607Z https://www.opentrain.ai/papers/rcpu-rotation-constrained-error-compensation-for-structured-pruning-of-large-lan--arxiv-2510.07782/2026-05-22T06:38:44.399Z https://www.opentrain.ai/papers/biasless-language-models-learn-unnaturally-how-llms-fail-to-distinguish-the-poss--arxiv-2510.07178/2026-06-16T20:16:24.823Z https://www.opentrain.ai/papers/improving-discrete-diffusion-unmasking-policies-beyond-explicit-reference-polici--arxiv-2510.05725/2026-06-02T02:17:44.278Z https://www.opentrain.ai/papers/seca-semantically-equivalent-and-coherent-attacks-for-eliciting-llm-hallucinatio--arxiv-2510.04398/2026-06-16T15:37:49.812Z https://www.opentrain.ai/papers/large-language-models-hallucination-a-comprehensive-survey--arxiv-2510.06265/2026-05-22T06:35:20.047Z https://www.opentrain.ai/papers/cache-to-cache-direct-semantic-communication-between-large-language-models--arxiv-2510.03215/2026-06-15T09:32:27.096Z https://www.opentrain.ai/papers/tree-based-dialogue-reinforced-policy-optimization-for-red-teaming-attacks--arxiv-2510.02286/2026-06-16T20:35:12.572Z https://www.opentrain.ai/papers/accuraterag-a-framework-for-building-accurate-retrieval-augmented-question-answe--arxiv-2510.02243/2026-05-22T07:24:24.276Z https://www.opentrain.ai/papers/energy-regularized-sequential-model-editing-on-hyperspheres--arxiv-2510.01172/2026-05-22T07:25:41.761Z https://www.opentrain.ai/papers/knowledgesmith-uncovering-knowledge-updating-in-llms-with-model-editing-and-unle--arxiv-2510.02392/2026-05-27T14:40:39.430Z https://www.opentrain.ai/papers/biasfreebench-a-benchmark-for-mitigating-bias-in-large-language-model-responses--arxiv-2510.00232/2026-06-13T15:44:59.222Z https://www.opentrain.ai/papers/bringing-emerging-architectures-to-sequence-labeling-in-nlp--arxiv-2509.25918/2026-05-28T18:57:13.475Z https://www.opentrain.ai/papers/calibrating-verbalized-confidence-with-self-generated-distractors--arxiv-2509.25532/2026-06-16T15:11:37.946Z https://www.opentrain.ai/papers/the-rise-of-africanlp-a-survey-of-contributions-contributors-community-impact-an--arxiv-2509.25477/2026-05-22T07:42:25.538Z https://www.opentrain.ai/papers/incentive-aligned-multi-source-llm-summaries--arxiv-2509.25184/2026-05-22T07:36:34.759Z https://www.opentrain.ai/papers/easysteer-a-unified-framework-for-high-performance-and-extensible-llm-steering--arxiv-2509.25175/2026-06-18T05:19:08.570Z https://www.opentrain.ai/papers/pretraining-large-language-models-with-nvfp4--arxiv-2509.25149/2026-06-07T08:43:56.981Z https://www.opentrain.ai/papers/vssflow-unifying-video-conditioned-sound-and-speech-generation-via-joint-learnin--arxiv-2509.24773/2026-05-22T06:39:15.191Z https://www.opentrain.ai/papers/proxyattn-guided-sparse-attention-via-representative-heads--arxiv-2509.24745/2026-06-17T18:10:37.881Z https://www.opentrain.ai/papers/building-benchmarks-from-the-ground-up-community-centered-evaluation-of-llms-in--arxiv-2509.24506/2026-06-13T15:20:56.057Z https://www.opentrain.ai/papers/harmmetric-eval-benchmarking-metrics-and-judges-for-llm-harmfulness-assessment--arxiv-2509.24384/2026-06-18T05:51:37.472Z https://www.opentrain.ai/papers/model-merging-scaling-laws-in-large-language-models--arxiv-2509.24244/2026-05-12T04:10:30.521Z https://www.opentrain.ai/papers/m3dlayout-a-multi-source-dataset-of-3d-indoor-layouts-and-structured-description--arxiv-2509.23728/2026-06-16T19:57:12.492Z https://www.opentrain.ai/papers/internal-planning-in-language-models-characterizing-horizon-and-branch-awareness--arxiv-2509.25260/2026-06-17T02:43:15.997Z https://www.opentrain.ai/papers/dual-space-smoothness-for-robust-and-balanced-llm-unlearning--arxiv-2509.23362/2026-06-12T04:13:11.630Z https://www.opentrain.ai/papers/ponderlm-2-pretraining-llm-with-latent-thoughts-in-continuous-space--arxiv-2509.23184/2026-06-14T21:16:29.758Z https://www.opentrain.ai/papers/test-time-policy-adaptation-for-enhanced-multi-turn-interactions-with-llms--arxiv-2509.23166/2026-05-22T07:36:51.653Z https://www.opentrain.ai/papers/semantic-voting-a-self-evaluation-free-approach-for-efficient-llm-self-improveme--arxiv-2509.23067/2026-06-18T07:21:55.696Z https://www.opentrain.ai/papers/autopk-leveraging-llms-and-a-hybrid-similarity-metric-for-advanced-retrieval-of--arxiv-2510.00039/2026-06-17T08:27:53.469Z https://www.opentrain.ai/papers/death-of-the-novel-ty-beyond-n-gram-novelty-as-a-metric-for-textual-creativity--arxiv-2509.22641/2026-06-18T05:49:10.254Z https://www.opentrain.ai/papers/benefits-and-pitfalls-of-reinforcement-learning-for-language-model-planning-a-th--arxiv-2509.22613/2026-06-18T05:51:28.897Z https://www.opentrain.ai/papers/cospadi-compressing-llms-via-calibration-guided-sparse-dictionary-learning--arxiv-2509.22075/2026-06-02T18:27:57.587Z https://www.opentrain.ai/papers/fine-tuning-done-right-in-model-editing--arxiv-2509.22072/2026-05-22T07:36:05.246Z https://www.opentrain.ai/papers/quokka-accelerating-program-verification-with-llms-via-invariant-synthesis--arxiv-2509.21629/2026-05-22T07:25:47.254Z https://www.opentrain.ai/papers/chasing-the-tail-effective-rubric-based-reward-modeling-for-large-language-model--arxiv-2509.21500/2026-06-15T06:04:31.519Z https://www.opentrain.ai/papers/pmark-towards-robust-and-distortion-free-semantic-level-watermarking-with-channe--arxiv-2509.21057/2026-06-16T09:21:43.428Z https://www.opentrain.ai/papers/olaph-optimal-language-phonemizer--arxiv-2509.20086/2026-06-18T06:11:31.245Z https://www.opentrain.ai/papers/redundancy-as-masking-formalizing-the-artificial-age-score-aas-to-model-memory-a--arxiv-2510.01242/2026-06-18T07:22:03.120Z https://www.opentrain.ai/papers/diversity-boosts-ai-generated-text-detection--arxiv-2509.18880/2026-06-17T16:30:00.241Z https://www.opentrain.ai/papers/orapo-oracle-educated-reinforcement-learning-for-data-efficient-and-factual-radi--arxiv-2509.18600/2026-06-16T10:05:52.111Z https://www.opentrain.ai/papers/prior-based-noisy-text-data-filtering-fast-and-strong-alternative-for-perplexity--arxiv-2509.18577/2026-05-14T03:33:05.866Z https://www.opentrain.ai/papers/similarity-field-theory-a-mathematical-framework-for-intelligence--arxiv-2509.18218/2026-04-11T16:49:23.392Z https://www.opentrain.ai/papers/llama-mimi-exploring-the-limits-of-flattened-speech-language-modeling--arxiv-2509.14882/2026-06-15T18:31:53.044Z https://www.opentrain.ai/papers/neural-quantum-states-impurity-solver-for-quantum-embedding-problems--arxiv-2509.12431/2026-06-16T15:07:17.155Z https://www.opentrain.ai/papers/the-ai-memory-gap-users-misremember-what-they-created-with-ai-or-without--arxiv-2509.11851/2026-05-30T18:39:25.236Z https://www.opentrain.ai/papers/incongruent-positivity-when-miscalibrated-positivity-undermines-online-supportiv--arxiv-2509.10184/2026-04-16T09:23:32.531Z https://www.opentrain.ai/papers/otesgn-optimal-transport-enhanced-syntactic-semantic-graph-networks-for-aspect-b--arxiv-2509.08612/2026-06-07T02:32:23.667Z https://www.opentrain.ai/papers/simpleqa-verified-a-reliable-factuality-benchmark-to-measure-parametric-knowledg--arxiv-2509.07968/2026-04-27T05:00:37.783Z https://www.opentrain.ai/papers/fhir-rag-meds-integrating-hl7-fhir-with-retrieval-augmented-large-language-model--arxiv-2509.07706/2026-05-31T07:43:23.776Z https://www.opentrain.ai/papers/llm-analysis-of-150-years-of-german-parliamentary-debates-on-migration-reveals-s--arxiv-2509.07274/2026-06-18T05:50:11.875Z https://www.opentrain.ai/papers/binaryshield-cross-service-threat-intelligence-in-llm-services-using-privacy-pre--arxiv-2509.05608/2026-05-22T06:39:28.797Z https://www.opentrain.ai/papers/no-text-needed-forecasting-mt-quality-and-inequity-from-fertility-and-metadata--arxiv-2509.05425/2026-05-22T08:11:13.515Z https://www.opentrain.ai/papers/from-editor-to-dense-geometry-estimator--arxiv-2509.04338/2026-06-18T06:15:52.645Z https://www.opentrain.ai/papers/multiwikiqa-a-reading-comprehension-benchmark-in-300-languages--arxiv-2509.04111/2026-05-22T07:47:35.193Z https://www.opentrain.ai/papers/agri-query-a-case-study-on-rag-vs-long-context-llms-for-cross-lingual-technical--arxiv-2508.18093/2026-06-16T03:48:31.964Z https://www.opentrain.ai/papers/hfx-joint-design-of-algorithms-and-systems-for-multi-slo-serving-and-fast-scalin--arxiv-2508.15919/2026-06-16T14:07:35.502Z https://www.opentrain.ai/papers/snap-uq-self-supervised-next-activation-prediction-for-single-pass-uncertainty-i--arxiv-2508.12907/2026-06-16T10:28:36.922Z https://www.opentrain.ai/papers/role-augmented-intent-driven-generative-search-engine-optimization--arxiv-2508.11158/2026-06-15T10:50:23.011Z https://www.opentrain.ai/papers/shadow-in-the-cache-unveiling-and-mitigating-privacy-risks-of-kv-cache-in-llm-in--arxiv-2508.09442/2026-06-17T19:11:14.112Z https://www.opentrain.ai/papers/from-product-hilbert-spaces-to-the-generalized-koopman-operator-and-the-nonlinea--arxiv-2508.07494/2026-04-18T07:58:35.461Z https://www.opentrain.ai/papers/intrinsicweather-controllable-weather-editing-in-intrinsic-space--arxiv-2508.06982/2026-06-13T17:58:14.354Z https://www.opentrain.ai/papers/personalized-feature-translation-for-expression-recognition-an-efficient-source--arxiv-2508.09202/2026-06-16T14:07:29.728Z https://www.opentrain.ai/papers/llmeval-fair-a-large-scale-longitudinal-study-on-robust-and-fair-evaluation-of-l--arxiv-2508.05452/2026-06-18T06:10:54.932Z https://www.opentrain.ai/papers/unsupervised-learning-for-inverse-problems-in-computed-tomography--arxiv-2508.05321/2026-06-18T05:49:44.000Z https://www.opentrain.ai/papers/hidden-dynamics-of-massive-activations-in-transformer-training--arxiv-2508.03616/2026-06-14T17:23:00.504Z https://www.opentrain.ai/papers/cropping-outperforms-dropout-as-an-augmentation-strategy-for-self-supervised-tra--arxiv-2508.03453/2026-06-18T05:25:04.214Z https://www.opentrain.ai/papers/roosebert-a-new-deal-for-political-language-modelling--arxiv-2508.03250/2026-05-30T04:36:21.806Z https://www.opentrain.ai/papers/poetone-a-framework-for-constrained-generation-of-structured-chinese-songci-with--arxiv-2508.02515/2026-06-13T13:29:25.526Z https://www.opentrain.ai/papers/harnessing-temporal-databases-for-systematic-evaluation-of-factual-time-sensitiv--arxiv-2508.02045/2026-06-17T13:43:14.407Z https://www.opentrain.ai/papers/mlp-memory-a-retriever-pretrained-memory-for-large-language-models--arxiv-2508.01832/2026-06-15T18:06:27.252Z https://www.opentrain.ai/papers/ghtm-a-graph-based-hybrid-topic-modeling-approach-with-a-benchmark-dataset-for-t--arxiv-2508.00605/2026-06-18T07:22:23.711Z https://www.opentrain.ai/papers/acoustic-imaging-for-uav-detection-dense-beamformed-energy-maps-and-u-net-seld--arxiv-2508.00307/2026-04-17T22:32:26.347Z https://www.opentrain.ai/papers/role-aware-language-models-for-secure-and-contextualized-access-control-in-organ--arxiv-2507.23465/2026-06-16T15:22:13.830Z https://www.opentrain.ai/papers/who-s-important-sunset-synergistic-understanding-of-stakeholder-events-and-time--arxiv-2507.21903/2026-06-15T15:11:29.280Z https://www.opentrain.ai/papers/a-survey-of-diversity-quantification-in-natural-language-processing-the-why-what--arxiv-2507.20858/2026-06-17T11:37:22.987Z https://www.opentrain.ai/papers/enhancing-jailbreak-attacks-on-llms-via-persona-prompts--arxiv-2507.22171/2026-06-14T20:29:57.853Z https://www.opentrain.ai/papers/packet-level-ddos-data-augmentation-using-dual-stream-temporal-field-diffusion--arxiv-2507.20115/2026-06-17T17:34:44.843Z https://www.opentrain.ai/papers/feyntune-large-language-models-for-high-energy-theory--arxiv-2508.03716/2026-06-17T13:06:32.057Z https://www.opentrain.ai/papers/efficient-compositional-multi-tasking-for-on-device-large-language-models--arxiv-2507.16083/2026-06-16T14:21:52.514Z https://www.opentrain.ai/papers/anthropomimetic-uncertainty-what-verbalized-uncertainty-in-language-models-is-mi--arxiv-2507.10587/2026-03-12T01:18:03.116Z https://www.opentrain.ai/papers/a-third-paradigm-for-llm-evaluation-dialogue-game-based-evaluation-using-clemben--arxiv-2507.08491/2026-06-17T14:23:30.816Z https://www.opentrain.ai/papers/towards-robust-sensor-fusion-ground-slam-a-comprehensive-benchmark-and-a-resilie--arxiv-2507.08364/2026-06-17T16:41:14.926Z https://www.opentrain.ai/papers/from-ambiguity-to-accuracy-the-transformative-effect-of-coreference-resolution-o--arxiv-2507.07847/2026-06-16T23:53:18.939Z https://www.opentrain.ai/papers/psychometric-item-validation-using-virtual-respondents-with-trait-response-media--arxiv-2507.05890/2026-06-16T01:01:02.101Z https://www.opentrain.ai/papers/mechanistic-indicators-of-understanding-in-large-language-models--arxiv-2507.08017/2026-06-17T17:13:45.449Z https://www.opentrain.ai/papers/k-function-joint-pronunciation-transcription-and-feedback-for-evaluating-kids-la--arxiv-2507.03043/2026-04-17T23:18:46.432Z https://www.opentrain.ai/papers/murating-a-high-quality-data-selecting-approach-to-multilingual-large-language-m--arxiv-2507.01785/2026-06-17T06:41:16.094Z https://www.opentrain.ai/papers/a-comparative-study-of-competency-question-elicitation-methods-from-ontology-req--arxiv-2507.02989/2026-06-16T16:03:07.749Z https://www.opentrain.ai/papers/tap-a-taxonomy-guided-framework-for-automated-and-scalable-preference-data-gener--arxiv-2506.23979/2026-06-16T15:04:50.031Z https://www.opentrain.ai/papers/unveiling-decision-making-in-llms-for-text-classification-extraction-of-influent--arxiv-2506.23951/2026-05-11T06:34:25.089Z https://www.opentrain.ai/papers/programming-by-backprop-an-instruction-is-worth-100-examples-when-finetuning-llm--arxiv-2506.18777/2026-06-17T17:13:36.610Z https://www.opentrain.ai/papers/accelerating-residual-reinforcement-learning-with-uncertainty-estimation--arxiv-2506.17564/2026-06-13T16:01:57.839Z https://www.opentrain.ai/papers/long-context-generalization-with-sparse-attention--arxiv-2506.16640/2026-06-17T16:47:14.516Z https://www.opentrain.ai/papers/measuring-intent-comprehension-in-llms--arxiv-2506.16584/2026-05-22T06:56:59.652Z https://www.opentrain.ai/papers/conlid-supervised-contrastive-learning-for-low-resource-language-identification--arxiv-2506.15304/2026-06-13T15:04:02.700Z https://www.opentrain.ai/papers/sysformer-safeguarding-frozen-large-language-models-with-adaptive-system-prompts--arxiv-2506.15751/2026-06-16T17:50:01.943Z https://www.opentrain.ai/papers/toward-principled-llm-safety-testing-solving-the-jailbreak-oracle-problem--arxiv-2506.17299/2026-06-17T10:15:14.431Z https://www.opentrain.ai/papers/lingoloop-attack-trapping-mllms-via-linguistic-context-and-state-entrapment-into--arxiv-2506.14493/2026-05-22T07:25:17.164Z https://www.opentrain.ai/papers/redtopic-toward-topic-diverse-red-teaming-of-large-language-models--arxiv-2507.00026/2026-06-16T16:04:09.105Z https://www.opentrain.ai/papers/agentsynth-scalable-task-generation-for-generalist-computer-use-agents--arxiv-2506.14205/2026-06-17T05:37:57.737Z https://www.opentrain.ai/papers/instruction-following-by-principled-boosting-attention-of-large-language-models--arxiv-2506.13734/2026-06-14T06:44:39.956Z https://www.opentrain.ai/papers/language-agents-for-hypothesis-driven-clinical-decision-making-with-reinforcemen--arxiv-2506.13474/2026-06-16T15:52:25.224Z https://www.opentrain.ai/papers/dualedit-mitigating-safety-fallback-in-llm-backdoor-editing-via-affirmation-refu--arxiv-2506.13285/2026-06-16T14:43:55.414Z https://www.opentrain.ai/papers/mememind-a-large-scale-multimodal-dataset-with-chain-of-thought-reasoning-for-ha--arxiv-2506.18919/2026-06-17T05:38:42.003Z https://www.opentrain.ai/papers/texttt-specs-faster-test-time-scaling-through-speculative-drafts--arxiv-2506.15733/2026-06-17T06:08:56.975Z https://www.opentrain.ai/papers/spurious-rewards-rethinking-training-signals-in-rlvr--arxiv-2506.10947/2026-06-17T12:07:44.266Z https://www.opentrain.ai/papers/vincie-unlocking-in-context-image-editing-from-video--arxiv-2506.10941/2026-06-12T03:26:15.391Z https://www.opentrain.ai/papers/accelerating-diffusion-large-language-models-with-slowfast-sampling-the-three-go--arxiv-2506.10848/2026-06-10T22:06:29.854Z https://www.opentrain.ai/papers/query-level-uncertainty-in-large-language-models--arxiv-2506.09669/2026-05-11T02:48:31.457Z https://www.opentrain.ai/papers/towards-bridging-the-reward-generation-gap-in-direct-alignment-algorithms--arxiv-2506.09457/2026-06-17T17:04:40.152Z https://www.opentrain.ai/papers/structure-augmented-reasoning-generation--arxiv-2506.08364/2026-06-17T17:04:28.968Z https://www.opentrain.ai/papers/not-all-tokens-matter-towards-efficient-llm-reasoning-via-token-significance-in--arxiv-2506.08125/2026-06-17T07:56:17.746Z https://www.opentrain.ai/papers/abstral-augmenting-llms-reasoning-by-reinforcing-abstract-thinking--arxiv-2506.07751/2026-06-16T15:03:19.346Z https://www.opentrain.ai/papers/learning-what-reinforcement-learning-can-t-interleaved-online-fine-tuning-for-ha--arxiv-2506.07527/2026-06-17T16:47:57.417Z https://www.opentrain.ai/papers/when-style-breaks-safety-defending-llms-against-superficial-style-alignment--arxiv-2506.07452/2026-06-15T00:53:44.083Z https://www.opentrain.ai/papers/exploring-effective-strategies-for-building-a-user-configured-gpt-for-coding-cla--arxiv-2506.07194/2026-05-22T02:34:37.488Z https://www.opentrain.ai/papers/a-dependently-typed-calculus-of-event-telicity-and-culminativity--arxiv-2506.06968/2026-06-17T17:16:36.766Z https://www.opentrain.ai/papers/designbench-a-comprehensive-benchmark-for-mllm-based-front-end-code-generation--arxiv-2506.06251/2026-06-17T10:13:22.914Z https://www.opentrain.ai/papers/can-theoretical-physics-research-benefit-from-language-agents--arxiv-2506.06214/2026-04-11T22:25:58.719Z https://www.opentrain.ai/papers/comparative-analysis-of-modern-machine-learning-models-for-retail-sales-forecast--arxiv-2506.05941/2026-06-17T11:39:26.469Z https://www.opentrain.ai/papers/cross-lingual-collapse-how-language-centric-foundation-models-shape-reasoning-in--arxiv-2506.05850/2026-05-16T03:47:50.163Z https://www.opentrain.ai/papers/when-to-use-graphs-in-rag-a-comprehensive-analysis-for-graph-retrieval-augmented--arxiv-2506.05690/2026-06-17T14:19:44.411Z https://www.opentrain.ai/papers/mmtu-a-massive-multi-task-table-understanding-and-reasoning-benchmark--arxiv-2506.05587/2026-06-13T15:13:10.309Z https://www.opentrain.ai/papers/improving-data-efficiency-for-llm-reinforcement-fine-tuning-through-difficulty-t--arxiv-2506.05316/2026-06-17T18:34:47.370Z https://www.opentrain.ai/papers/resisting-contextual-interference-in-rag-via-parametric-knowledge-reinforcement--arxiv-2506.05154/2026-06-18T06:32:41.826Z https://www.opentrain.ai/papers/toward-automated-robustness-evaluation-of-mathematical-reasoning--arxiv-2506.05038/2026-06-17T09:29:39.163Z https://www.opentrain.ai/papers/sensory-motor-control-with-large-language-models-via-iterative-policy-refinement--arxiv-2506.04867/2026-06-03T17:52:46.680Z https://www.opentrain.ai/papers/don-t-do-that-guiding-embodied-systems-through-large-language-model-based-constr--arxiv-2506.04500/2026-06-17T17:59:52.701Z https://www.opentrain.ai/papers/high-accuracy-less-talk-halt-reliable-llms-through-capability-aligned-finetuning--arxiv-2506.04051/2026-06-14T13:29:31.131Z https://www.opentrain.ai/papers/hssbench-benchmarking-humanities-and-social-sciences-ability-for-multimodal-larg--arxiv-2506.03922/2026-06-18T07:34:23.074Z https://www.opentrain.ai/papers/eurogest-investigating-gender-stereotypes-in-multilingual-language-models--arxiv-2506.03867/2026-06-15T09:54:14.597Z https://www.opentrain.ai/papers/assetopsbench-benchmarking-ai-agents-for-task-automation-in-industrial-asset-ope--arxiv-2506.03828/2026-06-17T12:02:51.748Z https://www.opentrain.ai/papers/go-browse-training-web-agents-with-structured-exploration--arxiv-2506.03533/2026-06-17T19:43:16.597Z https://www.opentrain.ai/papers/beyond-memorization-a-rigorous-evaluation-framework-for-medical-knowledge-editin--arxiv-2506.03490/2026-06-17T02:59:27.647Z https://www.opentrain.ai/papers/critique-grpo-advancing-llm-reasoning-with-natural-language-and-numerical-feedba--arxiv-2506.03106/2026-06-17T09:34:51.204Z https://www.opentrain.ai/papers/diablo-diagonal-blocks-are-sufficient-for-finetuning--arxiv-2506.03230/2026-06-17T14:10:14.892Z https://www.opentrain.ai/papers/bitbypass-a-new-direction-in-jailbreaking-aligned-large-language-models-with-bit--arxiv-2506.02479/2026-06-14T16:35:09.168Z https://www.opentrain.ai/papers/esoteric-language-models-bridging-autoregressive-and-masked-diffusion-llms--arxiv-2506.01928/2026-06-01T14:04:35.672Z https://www.opentrain.ai/papers/iquest-an-iterative-question-guided-framework-for-knowledge-base-question-answer--arxiv-2506.01784/2026-06-10T09:36:50.233Z https://www.opentrain.ai/papers/synthesis-of-discrete-continuous-quantum-circuits-with-multimodal-diffusion-mode--arxiv-2506.01666/2026-06-15T23:56:44.014Z https://www.opentrain.ai/papers/sealqa-raising-the-bar-for-reasoning-in-search-augmented-language-models--arxiv-2506.01062/2026-06-17T16:21:51.961Z https://www.opentrain.ai/papers/drivemind-a-dual-visual-language-model-based-reinforcement-learning-framework-fo--arxiv-2506.00819/2026-06-17T14:38:41.382Z https://www.opentrain.ai/papers/2-bench-evaluating-conversational-agents-in-a-dual-control-environment--arxiv-2506.07982/2026-06-17T14:38:35.868Z https://www.opentrain.ai/papers/flashdmoe-fast-distributed-moe-in-a-single-kernel--arxiv-2506.04667/2026-06-17T12:05:25.689Z https://www.opentrain.ai/papers/reasonflux-prm-trajectory-aware-prms-for-long-chain-of-thought-reasoning-in-llms--arxiv-2506.18896/2026-06-16T15:03:15.527Z https://www.opentrain.ai/papers/dataset-distillation-via-vision-language-category-prototype--arxiv-2506.23580/2026-06-15T19:51:05.944Z https://www.opentrain.ai/papers/stream-omni-simultaneous-multimodal-interactions-with-large-language-vision-spee--arxiv-2506.13642/2026-06-15T15:41:20.010Z https://www.opentrain.ai/papers/trident-enhancing-large-language-model-safety-with-tri-dimensional-diversified-r--arxiv-2505.24672/2026-06-17T08:51:44.557Z https://www.opentrain.ai/papers/beyond-exponential-decay-rethinking-error-accumulation-in-large-language-models--arxiv-2505.24187/2026-06-18T06:11:47.070Z https://www.opentrain.ai/papers/swingarena-competitive-programming-arena-for-long-context-github-issue-solving--arxiv-2505.23932/2026-06-18T06:00:29.080Z https://www.opentrain.ai/papers/formula-r1-incentivizing-llm-reasoning-over-complex-tables-with-numerical-comput--arxiv-2505.23667/2026-06-17T17:35:58.048Z https://www.opentrain.ai/papers/ajf-adaptive-jailbreak-framework-based-on-the-comprehension-ability-of-black-box--arxiv-2505.23404/2026-06-14T05:44:13.141Z https://www.opentrain.ai/papers/bayesian-attention-mechanism-a-probabilistic-framework-for-positional-encoding-a--arxiv-2505.22842/2026-06-16T17:26:49.136Z https://www.opentrain.ai/papers/measuring-sycophancy-of-language-models-in-multi-turn-dialogues--arxiv-2505.23840/2026-06-17T17:06:46.539Z https://www.opentrain.ai/papers/flying-pigs-far-and-beyond-evaluating-llm-reasoning-in-counterfactual-worlds--arxiv-2505.22318/2026-06-17T17:29:59.742Z https://www.opentrain.ai/papers/mixture-of-retrieval-experts-for-reasoning-guided-multimodal-knowledge-exploitat--arxiv-2505.22095/2026-06-12T10:24:17.330Z https://www.opentrain.ai/papers/reviewing-scientific-papers-for-critical-problems-with-reasoning-llms-baseline-a--arxiv-2505.23824/2026-06-15T20:21:27.144Z https://www.opentrain.ai/papers/redteamcua-realistic-adversarial-testing-of-computer-use-agents-in-hybrid-web-os--arxiv-2505.21936/2026-06-17T16:15:16.649Z https://www.opentrain.ai/papers/r1-code-interpreter-llms-reason-with-code-via-supervised-and-multi-stage-reinfor--arxiv-2505.21668/2026-06-17T08:04:13.775Z https://www.opentrain.ai/papers/reftool-reference-guided-tool-creation-for-knowledge-intensive-reasoning--arxiv-2505.21413/2026-06-12T08:50:44.316Z https://www.opentrain.ai/papers/rpm-reasoning-level-personalization-for-black-box-large-language-models--arxiv-2505.21082/2026-05-20T13:31:40.018Z https://www.opentrain.ai/papers/chemamp-amplified-chemistry-tools-via-composable-agents--arxiv-2505.21569/2026-06-09T15:30:16.644Z https://www.opentrain.ai/papers/do-llms-understand-collaborative-signals-diagnosis-and-repair--arxiv-2505.20730/2026-05-22T05:46:49.964Z https://www.opentrain.ai/papers/fintagging-benchmarking-llms-for-extracting-and-structuring-financial-informatio--arxiv-2505.20650/2026-06-15T15:53:42.982Z https://www.opentrain.ai/papers/visret-visualization-improves-knowledge-intensive-text-to-image-retrieval--arxiv-2505.20291/2026-06-16T15:25:22.050Z https://www.opentrain.ai/papers/vlm-3r-vision-language-models-augmented-with-instruction-aligned-3d-reconstructi--arxiv-2505.20279/2026-06-16T15:57:54.322Z https://www.opentrain.ai/papers/it-s-high-time-a-survey-of-temporal-question-answering--arxiv-2505.20243/2026-05-06T08:34:38.568Z https://www.opentrain.ai/papers/token-distillation-attention-aware-input-embeddings-for-new-tokens--arxiv-2505.20133/2026-06-17T17:08:24.155Z https://www.opentrain.ai/papers/inference-time-alignment-in-continuous-space--arxiv-2505.20081/2026-06-17T22:12:15.000Z https://www.opentrain.ai/papers/incentivizing-strong-reasoning-from-weak-supervision--arxiv-2505.20072/2026-06-17T17:35:17.611Z https://www.opentrain.ai/papers/rea-rl-reflection-aware-online-reinforcement-learning-for-efficient-reasoning--arxiv-2505.19862/2026-06-17T17:34:16.924Z https://www.opentrain.ai/papers/lllms-a-data-driven-survey-of-evolving-research-on-limitations-of-large-language--arxiv-2505.19240/2026-06-17T08:01:14.869Z https://www.opentrain.ai/papers/reasonmap-towards-fine-grained-visual-reasoning-from-transit-maps--arxiv-2505.18675/2026-06-17T08:30:33.432Z https://www.opentrain.ai/papers/sew-self-evolving-agentic-workflows-for-automated-code-generation--arxiv-2505.18646/2026-06-18T03:13:31.568Z https://www.opentrain.ai/papers/knowledge-fusion-of-large-language-models-via-modular-skillpacks--arxiv-2505.18502/2026-06-12T11:01:27.631Z https://www.opentrain.ai/papers/just-as-humans-need-vaccines-so-do-models-model-immunization-to-combat-falsehood--arxiv-2505.17870/2026-06-14T23:14:08.950Z https://www.opentrain.ai/papers/holollm-multisensory-foundation-model-for-language-grounded-human-sensing-and-re--arxiv-2505.17645/2026-06-17T21:11:29.392Z https://www.opentrain.ai/papers/on-the-design-of-kl-regularized-policy-gradient-algorithms-for-llm-reasoning--arxiv-2505.17508/2026-06-16T04:46:26.643Z https://www.opentrain.ai/papers/bottlenecked-transformers-periodic-kv-cache-consolidation-for-generalised-reason--arxiv-2505.16950/2026-06-12T10:22:53.963Z https://www.opentrain.ai/papers/accidental-vulnerability-factors-in-fine-tuning-that-shift-model-safeguards--arxiv-2505.16789/2026-06-12T08:56:20.158Z https://www.opentrain.ai/papers/verifybench-benchmarking-reference-based-reward-systems-for-large-language-model--arxiv-2505.15801/2026-06-17T12:02:35.839Z https://www.opentrain.ai/papers/reward-is-enough-llms-are-in-context-reinforcement-learners--arxiv-2506.06303/2026-06-16T15:06:32.634Z https://www.opentrain.ai/papers/hdlxgraph-bridging-large-language-models-and-hdl-repositories-via-hdl-graph-data--arxiv-2505.15701/2026-06-16T15:26:40.540Z https://www.opentrain.ai/papers/sake-structured-agentic-knowledge-extrapolation-for-complex-llm-reasoning-via-re--arxiv-2505.15062/2026-06-12T08:54:00.480Z https://www.opentrain.ai/papers/mas-zero-designing-multi-agent-systems-with-zero-supervision--arxiv-2505.14996/2026-06-17T05:04:35.068Z https://www.opentrain.ai/papers/reflex-metacognitive-reasoning-for-reflective-zero-shot-robotic-planning-with-la--arxiv-2505.14899/2026-06-15T04:35:40.342Z https://www.opentrain.ai/papers/towards-reliable-proof-generation-with-llms-a-neuro-symbolic-approach--arxiv-2505.14479/2026-06-17T16:38:17.815Z https://www.opentrain.ai/papers/not-minds-but-signs-reframing-llms-through-semiotics--arxiv-2505.17080/2026-04-10T17:47:23.471Z https://www.opentrain.ai/papers/let-s-verify-math-questions-step-by-step--arxiv-2505.13903/2026-06-16T00:28:26.279Z https://www.opentrain.ai/papers/structured-agent-distillation-for-large-language-model--arxiv-2505.13820/2026-06-18T03:13:49.649Z https://www.opentrain.ai/papers/ice-cream-doesn-t-cause-drowning-benchmarking-llms-against-statistical-pitfalls--arxiv-2505.13770/2026-06-12T16:26:17.373Z https://www.opentrain.ai/papers/advancing-software-quality-a-standards-focused-review-of-llm-based-assurance-tec--arxiv-2505.13766/2026-06-17T07:21:14.133Z https://www.opentrain.ai/papers/a-reality-check-of-language-models-as-formalizers-on-constraint-satisfaction-pro--arxiv-2505.13252/2026-04-09T20:10:13.466Z https://www.opentrain.ai/papers/what-if-deception-cannot-be-detected-a-cross-linguistic-study-on-the-limits-of-d--arxiv-2505.13147/2026-06-18T03:17:13.669Z https://www.opentrain.ai/papers/freekv-boosting-kv-cache-retrieval-for-efficient-llm-inference--arxiv-2505.13109/2026-03-10T13:11:33.155Z https://www.opentrain.ai/papers/lexam-benchmarking-legal-reasoning-on-340-law-exams--arxiv-2505.12864/2026-06-15T23:08:39.472Z https://www.opentrain.ai/papers/barrel-boundary-aware-reasoning-for-factual-and-reliable-lrms--arxiv-2505.13529/2026-06-17T16:35:47.967Z https://www.opentrain.ai/papers/logic-jailbreak-efficiently-unlocking-llm-safety-restrictions-through-formal-log--arxiv-2505.13527/2026-06-17T17:38:58.185Z https://www.opentrain.ai/papers/mitigating-content-effects-on-reasoning-in-language-models-through-fine-grained--arxiv-2505.12189/2026-06-03T19:31:36.748Z https://www.opentrain.ai/papers/evalooop-a-self-consistency-centered-framework-for-assessing-large-language-mode--arxiv-2505.12185/2026-06-17T14:44:13.935Z https://www.opentrain.ai/papers/visionreasoner-unified-reasoning-integrated-visual-perception-via-reinforcement--arxiv-2505.12081/2026-06-17T12:11:40.908Z https://www.opentrain.ai/papers/adabon-adaptive-best-of-n-alignment--arxiv-2505.12050/2026-06-17T17:05:37.771Z https://www.opentrain.ai/papers/eamet-robust-massive-model-editing-via-embedding-alignment-optimization--arxiv-2505.11876/2026-06-17T09:34:51.401Z https://www.opentrain.ai/papers/talk-to-your-slides-high-efficiency-slide-editing-via-language-driven-structured--arxiv-2505.11604/2026-06-16T04:06:36.503Z https://www.opentrain.ai/papers/stepwise-guided-policy-optimization-coloring-your-incorrect-reasoning-in-grpo--arxiv-2505.11595/2026-06-17T15:55:21.596Z https://www.opentrain.ai/papers/visual-planning-let-s-think-only-with-images--arxiv-2505.11409/2026-06-17T09:42:58.018Z https://www.opentrain.ai/papers/selfbudgeter-adaptive-token-allocation-for-efficient-llm-reasoning--arxiv-2505.11274/2026-06-17T14:08:20.015Z https://www.opentrain.ai/papers/maximizing-asynchronicity-in-event-based-neural-networks--arxiv-2505.11165/2026-06-17T04:46:37.617Z https://www.opentrain.ai/papers/rei-bench-can-embodied-agents-understand-vague-human-instructions-in-task-planni--arxiv-2505.10872/2026-05-23T22:19:05.734Z https://www.opentrain.ai/papers/why-1-1-1-in-visual-token-pruning-beyond-naive-integration-via-multi-objective-b--arxiv-2505.10118/2026-03-09T02:07:56.650Z https://www.opentrain.ai/papers/learning-virtual-machine-scheduling-in-cloud-computing-through-language-agents--arxiv-2505.10117/2026-03-12T03:08:28.759Z https://www.opentrain.ai/papers/codepde-an-inference-framework-for-llm-driven-pde-solver-generation--arxiv-2505.08783/2026-06-17T12:35:39.958Z https://www.opentrain.ai/papers/multimodal-integrated-knowledge-transfer-to-large-language-models-through-prefer--arxiv-2505.05736/2026-06-16T07:35:54.447Z https://www.opentrain.ai/papers/scalable-llm-reasoning-acceleration-with-low-rank-distillation--arxiv-2505.07861/2026-06-16T15:29:48.169Z https://www.opentrain.ai/papers/rm-r1-reward-modeling-as-reasoning--arxiv-2505.02387/2026-06-16T19:34:12.370Z https://www.opentrain.ai/papers/adaptive-social-learning-via-mode-policy-optimization-for-language-agents--arxiv-2505.02156/2026-06-12T14:42:32.946Z https://www.opentrain.ai/papers/finescope-sae-guided-data-selection-enables-domain-specific-llm-pruning-and-fine--arxiv-2505.00624/2026-06-16T16:05:41.350Z https://www.opentrain.ai/papers/llm-based-human-agent-collaboration-and-interaction-systems-a-survey--arxiv-2505.00753/2026-06-18T06:08:23.334Z https://www.opentrain.ai/papers/topopoint-enhance-topology-reasoning-via-endpoint-detection-in-autonomous-drivin--arxiv-2505.17771/2026-06-18T01:28:23.774Z https://www.opentrain.ai/papers/funreason-enhancing-large-language-models-function-calling-via-self-refinement-m--arxiv-2505.20192/2026-06-17T22:30:54.253Z https://www.opentrain.ai/papers/r-d-agent-quant-a-multi-agent-framework-for-data-centric-factors-and-model-joint--arxiv-2505.15155/2026-06-17T21:48:25.278Z https://www.opentrain.ai/papers/efficient-agent-training-for-computer-use--arxiv-2505.13909/2026-06-17T16:47:15.739Z https://www.opentrain.ai/papers/agent-rl-scaling-law-agent-rl-with-spontaneous-code-execution-for-mathematical-p--arxiv-2505.07773/2026-06-17T14:24:39.015Z https://www.opentrain.ai/papers/advancing-multimodal-reasoning-via-reinforcement-learning-with-cold-start--arxiv-2505.22334/2026-06-17T09:38:15.030Z https://www.opentrain.ai/papers/enhancing-visual-grounding-for-gui-agents-via-self-evolutionary-reinforcement-le--arxiv-2505.12370/2026-06-16T21:45:37.725Z https://www.opentrain.ai/papers/clever-a-curated-benchmark-for-formally-verified-code-generation--arxiv-2505.13938/2026-06-16T10:01:38.020Z https://www.opentrain.ai/papers/absolute-zero-reinforced-self-play-reasoning-with-zero-data--arxiv-2505.03335/2026-06-15T21:32:40.019Z https://www.opentrain.ai/papers/unsupervised-post-training-for-multi-modal-llm-reasoning-via-grpo--arxiv-2505.22453/2026-06-15T19:51:54.654Z https://www.opentrain.ai/papers/sophiavl-r1-reinforcing-mllms-reasoning-with-thinking-reward--arxiv-2505.17018/2026-06-15T14:11:14.963Z https://www.opentrain.ai/papers/r1-sharevl-incentivizing-reasoning-capability-of-multimodal-large-language-model--arxiv-2505.16673/2026-06-15T12:47:37.608Z https://www.opentrain.ai/papers/infochartqa-a-benchmark-for-multimodal-question-answering-on-infographic-charts--arxiv-2505.19028/2026-06-15T06:02:27.495Z https://www.opentrain.ai/papers/the-p-3-dataset-pixels-points-and-polygons-for-multimodal-building-vectorization--arxiv-2505.15379/2026-06-15T05:25:37.808Z https://www.opentrain.ai/papers/delving-into-rl-for-image-generation-with-cot-a-study-on-dpo-vs-grpo--arxiv-2505.17017/2026-06-15T01:53:35.561Z https://www.opentrain.ai/papers/efficient-multivariate-time-series-forecasting-via-calibrated-language-models-wi--arxiv-2505.02138/2026-06-14T17:44:31.414Z https://www.opentrain.ai/papers/simpledeepsearcher-deep-information-seeking-via-web-powered-reasoning-trajectory--arxiv-2505.16834/2026-06-14T05:06:56.058Z https://www.opentrain.ai/papers/from-eduvisbench-to-eduvisagent-a-benchmark-and-multi-agent-framework-for-pedago--arxiv-2505.16832/2026-06-14T01:19:28.335Z https://www.opentrain.ai/papers/reason-like-a-radiologist-chain-of-thought-and-reinforcement-learning-for-verifi--arxiv-2504.18453/2026-05-22T07:37:49.384Z https://www.opentrain.ai/papers/comparing-uncertainty-measurement-and-mitigation-methods-for-large-language-mode--arxiv-2504.18346/2026-06-17T08:29:04.812Z https://www.opentrain.ai/papers/aleph-alpha-germanweb-improving-german-language-llm-pre-training-with-model-base--arxiv-2505.00022/2026-06-16T12:29:46.074Z https://www.opentrain.ai/papers/fluke-a-linguistically-driven-and-task-agnostic-framework-for-robustness-evaluat--arxiv-2504.17311/2026-06-17T02:57:25.756Z https://www.opentrain.ai/papers/paper2code-automating-code-generation-from-scientific-papers-in-machine-learning--arxiv-2504.17192/2026-06-16T13:29:47.124Z https://www.opentrain.ai/papers/recellty-domain-specific-knowledge-graph-retrieval-augmented-llms-reasoning-work--arxiv-2505.00017/2026-06-17T17:38:47.917Z https://www.opentrain.ai/papers/genemamba-an-efficient-and-effective-foundation-model-on-single-cell-data--arxiv-2504.16956/2026-06-16T15:23:44.727Z https://www.opentrain.ai/papers/trustgeogen-formal-verified-data-engine-for-trustworthy-multi-modal-geometric-pr--arxiv-2504.15780/2026-06-13T07:43:11.826Z https://www.opentrain.ai/papers/dip-efficient-large-multimodal-model-training-with-dynamic-interleaved-pipeline--arxiv-2504.14145/2026-06-17T05:03:52.572Z https://www.opentrain.ai/papers/cost-of-pass-an-economic-framework-for-evaluating-language-models--arxiv-2504.13359/2026-06-17T08:27:03.323Z https://www.opentrain.ai/papers/diffusion-generative-recommendation-with-continuous-tokens--arxiv-2504.12007/2026-06-17T10:19:55.165Z https://www.opentrain.ai/papers/agenta-b-automated-and-scalable-web-a-btesting-with-interactive-llm-agents--arxiv-2504.09723/2026-06-17T11:44:49.513Z https://www.opentrain.ai/papers/a-survey-of-frontiers-in-llm-reasoning-inference-scaling-learning-to-reason-and--arxiv-2504.09037/2026-06-15T15:19:21.216Z https://www.opentrain.ai/papers/mcp-bridge-a-lightweight-llm-agnostic-restful-proxy-for-model-context-protocol-s--arxiv-2504.08999/2026-06-17T18:08:29.940Z https://www.opentrain.ai/papers/generating-fine-details-of-entity-interactions--arxiv-2504.08714/2026-06-17T13:57:59.304Z https://www.opentrain.ai/papers/automating-quantum-feature-map-design-via-large-language-models--arxiv-2504.07396/2026-06-17T07:36:07.146Z https://www.opentrain.ai/papers/caredio-cultural-alignment-via-representativeness-and-distinctiveness-guided-dat--arxiv-2504.08820/2026-05-22T08:39:55.255Z https://www.opentrain.ai/papers/can-llms-simulate-personas-with-reversed-performance-a-systematic-investigation--arxiv-2504.06460/2026-06-16T15:40:36.500Z https://www.opentrain.ai/papers/don-t-let-it-hallucinate-premise-verification-via-retrieval-augmented-logical-re--arxiv-2504.06438/2026-05-22T07:09:16.475Z https://www.opentrain.ai/papers/biascause-evaluate-socially-biased-causal-reasoning-of-large-language-models--arxiv-2504.07997/2026-05-22T06:11:31.369Z