https://www.opentrain.ai/papers/distilling-feedback-into-memory-as-a-tool--arxiv-2601.05960/2026-06-17T15:01:32.446Z https://www.opentrain.ai/papers/factum-mechanistic-detection-of-citation-hallucination-in-long-form-rag--arxiv-2601.05866/2026-06-12T09:37:54.178Z https://www.opentrain.ai/papers/hag-hierarchical-demographic-tree-based-agent-generation-for-topic-adaptive-simu--arxiv-2601.05656/2026-06-17T22:38:12.889Z https://www.opentrain.ai/papers/double-breaking-the-acceleration-limit-via-double-retrieval-speculative-parallel--arxiv-2601.05524/2026-06-18T22:26:32.040Z https://www.opentrain.ai/papers/miner-mining-intrinsic-mastery-for-data-efficient-rl-in-large-reasoning-models--arxiv-2601.04731/2026-06-18T18:48:50.479Z https://www.opentrain.ai/papers/neurosymbolic-retrievers-for-retrieval-augmented-generation--arxiv-2601.04568/2026-06-07T19:30:43.846Z https://www.opentrain.ai/papers/what-matters-for-safety-alignment--arxiv-2601.03868/2026-06-18T00:38:50.934Z https://www.opentrain.ai/papers/from-intuition-to-calibrated-judgment-a-rubric-based-expert-panel-study-of-human--arxiv-2601.19913/2026-06-15T19:50:44.007Z https://www.opentrain.ai/papers/understanding-pure-textual-reasoning-for-blind-image-quality-assessment--arxiv-2601.02441/2026-06-17T15:33:49.247Z https://www.opentrain.ai/papers/supracompetitive-pricing-under-ai-monoculture--arxiv-2601.01279/2026-06-17T15:00:54.505Z https://www.opentrain.ai/papers/emoloom-2b-fast-base-model-screening-for-emotion-classification-and-vad-with-lex--arxiv-2601.01112/2026-06-17T15:25:50.224Z https://www.opentrain.ai/papers/a-language-agnostic-hierarchical-lora-moe-architecture-for-ctc-based-multilingua--arxiv-2601.00557/2026-06-17T14:45:33.034Z https://www.opentrain.ai/papers/from-evidence-based-medicine-to-knowledge-graph-retrieval-augmented-generation-f--arxiv-2601.00216/2026-06-19T08:19:34.905Z https://www.opentrain.ai/papers/let-it-flow-agentic-crafting-on-rock-and-roll-building-the-rome-model-within-an--arxiv-2512.24873/2026-06-18T02:33:13.735Z https://www.opentrain.ai/papers/vl-routerbench-a-benchmark-for-vision-language-model-routing--arxiv-2512.23562/2026-06-20T03:05:24.195Z https://www.opentrain.ai/papers/coupling-experts-and-routers-in-mixture-of-experts-via-an-auxiliary-loss--arxiv-2512.23447/2026-06-20T00:58:29.296Z https://www.opentrain.ai/papers/schrodinger-s-navigator-imagining-an-ensemble-of-futures-for-zero-shot-object-na--arxiv-2512.21201/2026-06-17T14:45:18.827Z https://www.opentrain.ai/papers/dial-direct-iterative-adversarial-learning-for-realistic-multi-turn-dialogue-sim--arxiv-2512.20773/2026-06-18T07:12:24.576Z https://www.opentrain.ai/papers/machine-unlearning-in-the-era-of-quantum-machine-learning-an-empirical-study--arxiv-2512.19253/2026-05-22T07:23:36.713Z https://www.opentrain.ai/papers/cyclechart-a-unified-consistency-based-learning-framework-for-bidirectional-char--arxiv-2512.19173/2026-05-28T00:09:13.981Z https://www.opentrain.ai/papers/adaptive-accountability-in-networked-mas-tracing-and-mitigating-emergent-norms-a--arxiv-2512.18561/2026-06-17T14:50:19.425Z https://www.opentrain.ai/papers/value-under-ignorance-in-universal-artificial-intelligence--arxiv-2512.17086/2026-06-18T19:16:42.060Z https://www.opentrain.ai/papers/in-context-algebra--arxiv-2512.16902/2026-06-20T01:11:25.410Z https://www.opentrain.ai/papers/social-story-frames-contextual-reasoning-about-narrative-intent-and-reception--arxiv-2512.15925/2026-06-17T19:24:20.005Z https://www.opentrain.ai/papers/imitation-game-reproducing-deep-learning-bugs-leveraging-an-intelligent-agent--arxiv-2512.14990/2026-06-18T13:18:14.013Z https://www.opentrain.ai/papers/companioncast-toward-social-collaboration-with-multi-agent-systems-in-shared-exp--arxiv-2512.10918/2026-06-17T20:12:50.184Z https://www.opentrain.ai/papers/kd-oct-efficient-knowledge-distillation-for-clinical-grade-retinal-oct-classific--arxiv-2512.09069/2026-06-17T08:22:21.233Z https://www.opentrain.ai/papers/group-representational-position-encoding--arxiv-2512.07805/2026-06-17T20:42:33.872Z https://www.opentrain.ai/papers/echo-copilot-a-multiple-perspective-agentic-framework-for-reliable-echocardiogra--arxiv-2512.09944/2026-06-18T18:20:01.168Z https://www.opentrain.ai/papers/boom-beyond-only-one-modality-kit-s-multimodal-multilingual-lecture-companion--arxiv-2512.02817/2026-06-11T12:18:27.348Z https://www.opentrain.ai/papers/innogym-benchmarking-the-innovation-potential-of-ai-agents--arxiv-2512.01822/2026-06-17T07:57:36.108Z https://www.opentrain.ai/papers/stellar-structure-guided-llm-assertion-retrieval-and-generation-for-formal-verif--arxiv-2601.19903/2026-04-13T01:41:33.265Z https://www.opentrain.ai/papers/costnav-a-navigation-benchmark-for-real-world-economic-cost-evaluation-of-physic--arxiv-2511.20216/2026-06-17T16:05:42.795Z https://www.opentrain.ai/papers/the-metaphysics-we-train-a-heideggerian-reading-of-machine-learning--arxiv-2602.19028/2026-06-17T15:21:14.238Z https://www.opentrain.ai/papers/foundry-distilling-3d-foundation-models-for-the-edge--arxiv-2511.20721/2026-06-06T03:37:28.977Z https://www.opentrain.ai/papers/pedestrian-crossing-intention-prediction-using-multimodal-fusion-network--arxiv-2511.20008/2026-06-17T13:38:54.781Z https://www.opentrain.ai/papers/sage-shape-adapting-gated-experts-for-adaptive-histopathology-image-segmentation--arxiv-2511.18493/2026-06-19T20:12:36.625Z https://www.opentrain.ai/papers/uni-dad-unified-distillation-and-adaptation-of-diffusion-models-for-few-step-few--arxiv-2511.18281/2026-06-17T15:00:57.289Z https://www.opentrain.ai/papers/bias-is-a-subspace-not-a-coordinate-a-geometric-rethinking-of-post-hoc-debiasing--arxiv-2511.18123/2026-06-12T06:03:12.908Z https://www.opentrain.ai/papers/head-qa-v2-expanding-a-healthcare-benchmark-for-reasoning--arxiv-2511.15355/2026-06-17T16:09:09.726Z https://www.opentrain.ai/papers/stealth-fine-tuning-efficiently-breaking-alignment-in-rvlms-using-self-generated--arxiv-2511.14106/2026-06-17T14:49:40.660Z https://www.opentrain.ai/papers/aisac-an-integrated-multi-agent-system-for-transparent-retrieval-grounded-scient--arxiv-2511.14043/2026-06-17T03:00:55.160Z https://www.opentrain.ai/papers/auditing-google-s-ai-overviews-and-featured-snippets-a-case-study-on-baby-care-a--arxiv-2511.12920/2026-06-18T11:41:59.803Z https://www.opentrain.ai/papers/prism-of-opinions-a-persona-reasoned-multimodal-framework-for-user-centric-conve--arxiv-2511.12130/2026-06-17T14:27:32.434Z https://www.opentrain.ai/papers/mediround-multi-round-entity-level-reasoning-segmentation-in-medical-images--arxiv-2511.12110/2026-06-17T15:02:25.348Z https://www.opentrain.ai/papers/from-synthetic-scenes-to-real-performance-enhancing-spatial-reasoning-in-vlms--arxiv-2511.11440/2026-06-17T15:47:17.981Z https://www.opentrain.ai/papers/mastering-olympiad-level-physics-with-artificial-intelligence--arxiv-2511.10515/2026-06-17T14:06:26.261Z https://www.opentrain.ai/papers/vipra-video-prediction-for-robot-actions--arxiv-2511.07732/2026-06-18T12:03:43.696Z https://www.opentrain.ai/papers/more-agents-improve-math-problem-solving-but-adversarial-robustness-gap-persists--arxiv-2511.07112/2026-06-19T17:34:30.335Z https://www.opentrain.ai/papers/rpts-tree-structured-reasoning-process-scoring-for-faithful-multimodal-evaluatio--arxiv-2511.06899/2026-05-19T11:43:22.244Z https://www.opentrain.ai/papers/vlad-grasp-zero-shot-grasp-detection-via-vision-language-models--arxiv-2511.05791/2026-05-06T14:50:25.859Z https://www.opentrain.ai/papers/jr-ai-scientist-and-its-risk-report-autonomous-scientific-exploration-from-a-bas--arxiv-2511.04583/2026-06-17T14:45:25.512Z https://www.opentrain.ai/papers/seeing-straight-document-orientation-detection-for-efficient-ocr--arxiv-2511.04161/2026-05-06T14:50:46.332Z https://www.opentrain.ai/papers/batch-prompting-suppresses-overthinking-reasoning-under-constraint-how-batch-pro--arxiv-2511.04108/2026-06-16T06:49:57.912Z https://www.opentrain.ai/papers/t-fix-text-based-explanations-with-features-interpretable-to-experts--arxiv-2511.04070/2026-06-19T15:12:19.257Z https://www.opentrain.ai/papers/error-aware-knowledge-distillation-via-targeted-revision-for-customer-service-su--arxiv-2511.03005/2026-06-19T15:52:04.632Z https://www.opentrain.ai/papers/parlaspeech-3-0-richly-annotated-spoken-parliamentary-corpora-of-croatian-czech--arxiv-2511.01619/2026-06-19T11:29:48.030Z https://www.opentrain.ai/papers/self-harmony-learning-to-harmonize-self-supervision-and-self-play-in-test-time-r--arxiv-2511.01191/2026-05-06T14:49:47.344Z https://www.opentrain.ai/papers/beat-visual-backdoor-attacks-on-vlm-based-embodied-agents-via-contrastive-trigge--arxiv-2510.27623/2026-06-19T02:14:28.663Z https://www.opentrain.ai/papers/atlas-alignment-making-interpretability-transferable-across-language-models--arxiv-2510.27413/2026-06-18T08:26:33.459Z https://www.opentrain.ai/papers/simple-additions-substantial-gains-expanding-scripts-languages-and-lineage-cover--arxiv-2510.27183/2026-04-12T00:37:17.954Z https://www.opentrain.ai/papers/the-tool-decathlon-benchmarking-language-agents-for-diverse-realistic-and-long-h--arxiv-2510.25726/2026-06-19T12:31:22.127Z https://www.opentrain.ai/papers/from-medical-records-to-diagnostic-dialogues-a-clinical-grounded-approach-and-da--arxiv-2510.25232/2026-06-17T20:11:24.779Z https://www.opentrain.ai/papers/repurposing-synthetic-data-for-fine-grained-search-agent-supervision--arxiv-2510.24694/2026-05-15T22:36:56.278Z https://www.opentrain.ai/papers/synthworlds-controlled-parallel-worlds-for-disentangling-reasoning-and-knowledge--arxiv-2510.24427/2026-05-24T22:06:12.206Z https://www.opentrain.ai/papers/automatically-benchmarking-llm-code-agents-through-agent-driven-annotation-and-e--arxiv-2510.24358/2026-06-19T09:10:19.524Z https://www.opentrain.ai/papers/batch-speculative-decoding-done-right--arxiv-2510.22876/2026-06-19T12:36:58.210Z https://www.opentrain.ai/papers/revision-reflective-intent-mining-and-online-reasoning-auxiliary-for-e-commerce--arxiv-2510.22739/2026-06-17T15:35:03.159Z https://www.opentrain.ai/papers/waon-large-scale-japanese-image-text-pair-dataset-for-improving-model-performanc--arxiv-2510.22276/2026-05-23T20:05:41.149Z https://www.opentrain.ai/papers/atlas-adaptive-transfer-scaling-laws-for-multilingual-pretraining-finetuning-and--arxiv-2510.22037/2026-06-16T03:03:31.695Z https://www.opentrain.ai/papers/when-models-outthink-their-safety-unveiling-and-mitigating-self-jailbreak-in-lar--arxiv-2510.21285/2026-06-14T05:56:11.860Z https://www.opentrain.ai/papers/shoot-first-ask-questions-later-building-rational-agents-that-explore-and-act-li--arxiv-2510.20886/2026-06-17T14:46:55.542Z https://www.opentrain.ai/papers/co-designing-quantum-codes-with-transversal-diagonal-gates-via-multi-agent-syste--arxiv-2510.20728/2026-06-19T17:19:33.666Z https://www.opentrain.ai/papers/globalrag-enhancing-global-reasoning-in-multi-hop-question-answering-via-reinfor--arxiv-2510.20548/2026-06-18T12:07:33.617Z https://www.opentrain.ai/papers/communication-to-completion-modeling-collaborative-workflows-with-intelligent-mu--arxiv-2510.19995/2026-06-18T13:15:52.545Z https://www.opentrain.ai/papers/agentic-inequality--arxiv-2510.16853/2026-06-18T17:56:59.165Z https://www.opentrain.ai/papers/prior-knowledge-makes-it-possible-from-sublinear-graph-algorithms-to-llm-test-ti--arxiv-2510.16609/2026-06-19T11:27:46.549Z https://www.opentrain.ai/papers/agree-disagree-explain-decomposing-human-label-variation-in-nli-through-the-lens--arxiv-2510.16458/2026-06-08T16:01:06.596Z https://www.opentrain.ai/papers/webserv-a-full-stack-and-rl-ready-web-environment-for-training-web-agents-at-sca--arxiv-2510.16252/2026-06-18T20:03:51.647Z https://www.opentrain.ai/papers/scholareval-research-idea-evaluation-grounded-in-literature--arxiv-2510.16234/2026-06-18T04:52:22.456Z https://www.opentrain.ai/papers/biogen-evidence-grounded-multi-agent-reasoning-framework-for-transcriptomic-inte--arxiv-2510.16082/2026-06-17T19:43:20.618Z https://www.opentrain.ai/papers/three-dimensional-inversion-of-gravity-data-using-implicit-neural-representation--arxiv-2510.17876/2026-06-18T04:55:38.903Z https://www.opentrain.ai/papers/dialectgen-benchmarking-and-improving-dialect-robustness-in-multimodal-generatio--arxiv-2510.14949/2026-06-18T10:58:21.904Z https://www.opentrain.ai/papers/tri-dep-a-trimodal-comparative-study-for-depression-detection-using-speech-text--arxiv-2510.14922/2026-06-19T03:45:33.684Z https://www.opentrain.ai/papers/telling-speculative-stories-to-help-humans-imagine-the-harms-of-healthcare-ai--arxiv-2510.14718/2026-06-15T17:45:13.019Z https://www.opentrain.ai/papers/reap-the-experts-why-pruning-prevails-for-one-shot-moe-compression--arxiv-2510.13999/2026-06-19T08:44:22.766Z https://www.opentrain.ai/papers/dedelayed-deleting-remote-inference-delay-via-on-device-correction--arxiv-2510.13714/2026-06-17T22:32:27.161Z https://www.opentrain.ai/papers/what-not-to-detect-negation-aware-vlms-via-structured-reasoning-and-token-mergin--arxiv-2510.13232/2026-06-15T16:40:47.006Z https://www.opentrain.ai/papers/omni-captioner-data-pipeline-models-and-benchmark-for-omni-detailed-perception--arxiv-2510.12720/2026-06-17T15:01:00.763Z https://www.opentrain.ai/papers/proh-dynamic-planning-and-reasoning-over-knowledge-hypergraphs-for-retrieval-aug--arxiv-2510.12434/2026-06-16T02:36:28.236Z https://www.opentrain.ai/papers/an-order-sensitive-conflict-measure-for-random-permutation-sets--arxiv-2510.16001/2026-05-22T08:08:21.558Z https://www.opentrain.ai/papers/one-life-to-learn-inferring-symbolic-world-models-for-stochastic-environments-fr--arxiv-2510.12088/2026-06-19T01:39:49.045Z https://www.opentrain.ai/papers/sage-a-top-down-bottom-up-knowledge-grounded-user-simulator-for-multi-turn-agent--arxiv-2510.11997/2026-06-14T21:59:26.923Z https://www.opentrain.ai/papers/catch-your-breath-adaptive-computation-for-self-paced-sequence-production--arxiv-2510.13879/2026-06-18T07:21:59.822Z https://www.opentrain.ai/papers/qubit-centric-transformer-for-surface-code-decoding--arxiv-2510.11593/2026-06-02T02:28:49.545Z https://www.opentrain.ai/papers/clmn-concept-based-language-models-via-neural-symbolic-reasoning--arxiv-2510.10063/2026-06-19T10:13:33.049Z https://www.opentrain.ai/papers/dspo-stable-and-efficient-policy-optimization-for-agentic-search-and-reasoning--arxiv-2510.09255/2026-06-16T22:08:11.050Z https://www.opentrain.ai/papers/reasonembed-enhanced-text-embeddings-for-reasoning-intensive-document-retrieval--arxiv-2510.08252/2026-05-17T19:54:43.902Z https://www.opentrain.ai/papers/adaswitch-balancing-exploration-and-guidance-in-knowledge-distillation-via-adapt--arxiv-2510.07842/2026-06-19T18:55:59.980Z https://www.opentrain.ai/papers/lad-rag-layout-aware-dynamic-rag-for-visually-rich-document-understanding--arxiv-2510.07233/2026-06-03T19:28:54.687Z https://www.opentrain.ai/papers/multi-hop-deep-joint-source-channel-coding-with-deep-hash-distillation-for-seman--arxiv-2510.06868/2026-06-16T15:25:17.491Z https://www.opentrain.ai/papers/star-kvqa-structured-reasoning-traces-for-implicit-knowledge-visual-question-ans--arxiv-2510.06638/2026-06-18T05:04:24.781Z https://www.opentrain.ai/papers/mitigating-premature-exploitation-in-particle-based-monte-carlo-for-inference-ti--arxiv-2510.05825/2026-04-08T21:49:36.696Z https://www.opentrain.ai/papers/agentdr-dynamic-recommendation-with-implicit-item-item-relations-via-llm-based-a--arxiv-2510.05598/2026-06-16T04:23:38.731Z https://www.opentrain.ai/papers/multilingual-routing-in-mixture-of-experts--arxiv-2510.04694/2026-04-18T22:00:29.983Z https://www.opentrain.ai/papers/watch-and-learn-learning-to-use-computers-from-online-videos--arxiv-2510.04673/2026-06-10T00:25:12.186Z https://www.opentrain.ai/papers/compressed-convolutional-attention-efficient-attention-in-a-compressed-latent-sp--arxiv-2510.04476/2026-06-18T09:51:46.869Z https://www.opentrain.ai/papers/expressive-power-of-implicit-models-rich-equilibria-and-test-time-scaling--arxiv-2510.03638/2026-06-17T03:26:45.615Z https://www.opentrain.ai/papers/markovian-reeb-graphs-for-simulating-spatiotemporal-patterns-of-life--arxiv-2510.03152/2026-05-22T07:48:58.381Z https://www.opentrain.ai/papers/biox-bridge-model-bridging-for-unsupervised-cross-modal-knowledge-transfer-acros--arxiv-2510.02276/2026-06-18T06:56:36.221Z https://www.opentrain.ai/papers/can-ai-truly-represent-your-voice-in-deliberations-a-comprehensive-study-of-larg--arxiv-2510.05154/2026-06-19T12:30:27.539Z https://www.opentrain.ai/papers/is-it-thinking-or-cheating-detecting-implicit-reward-hacking-by-measuring-reason--arxiv-2510.01367/2026-06-18T06:51:40.962Z https://www.opentrain.ai/papers/where-do-backdoors-live-a-component-level-analysis-of-backdoor-propagation-in-sp--arxiv-2510.01157/2026-06-19T12:32:30.254Z https://www.opentrain.ai/papers/hearing-the-order-investigating-position-bias-in-large-audio-language-models--arxiv-2510.00628/2026-06-19T12:38:39.301Z https://www.opentrain.ai/papers/drbench-a-realistic-benchmark-for-enterprise-deep-research--arxiv-2510.00172/2026-06-18T23:37:18.423Z https://www.opentrain.ai/papers/profvlm-a-lightweight-video-language-model-for-multi-view-proficiency-estimation--arxiv-2509.26278/2026-06-19T19:15:19.156Z https://www.opentrain.ai/papers/reasoningbank-scaling-agent-self-evolving-with-reasoning-memory--arxiv-2509.25140/2026-06-17T16:54:21.254Z https://www.opentrain.ai/papers/towards-personalized-deep-research-benchmarks-and-evaluations--arxiv-2509.25106/2026-06-17T12:52:37.645Z https://www.opentrain.ai/papers/scaling-generalist-data-analytic-agents--arxiv-2509.25084/2026-06-19T12:36:49.130Z https://www.opentrain.ai/papers/stop-before-you-fail-operational-capability-boundaries-for-mitigating-unproducti--arxiv-2509.24711/2026-06-18T16:34:16.533Z https://www.opentrain.ai/papers/towards-safe-reasoning-in-large-reasoning-models-via-corrective-intervention--arxiv-2509.24393/2026-06-18T03:54:38.832Z https://www.opentrain.ai/papers/simuhome-a-temporal-and-environment-aware-benchmark-for-smart-home-llm-agents--arxiv-2509.24282/2026-06-17T16:29:23.187Z https://www.opentrain.ai/papers/reasoning-or-retrieval-a-study-of-answer-attribution-on-large-reasoning-models--arxiv-2509.24156/2026-06-19T12:38:41.659Z https://www.opentrain.ai/papers/voicebridge-general-speech-restoration-with-one-step-latent-bridge-models--arxiv-2509.25275/2026-06-19T12:36:36.024Z https://www.opentrain.ai/papers/audiomog-guiding-audio-generation-with-mixture-of-guidance--arxiv-2509.23727/2026-06-19T12:34:55.610Z https://www.opentrain.ai/papers/mini-vec2vec-scaling-universal-geometry-alignment-with-linear-transformations--arxiv-2510.02348/2026-06-18T18:54:23.939Z https://www.opentrain.ai/papers/non-collaborative-user-simulators-for-tool-agents--arxiv-2509.23124/2026-05-22T07:22:19.283Z https://www.opentrain.ai/papers/blind-to-position-biased-in-language-probing-mid-layer-representational-bias-in--arxiv-2509.23098/2026-06-18T10:58:27.870Z https://www.opentrain.ai/papers/securevibebench-evaluating-secure-coding-capabilities-of-code-agents-with-realis--arxiv-2509.22097/2026-06-19T20:54:28.134Z https://www.opentrain.ai/papers/rejuvenating-cross-entropy-loss-in-knowledge-distillation-for-recommender-system--arxiv-2509.20989/2026-06-18T18:26:56.034Z https://www.opentrain.ai/papers/conversational-speech-reveals-structural-robustness-failures-in-speechllm-backbo--arxiv-2509.20321/2026-06-18T05:23:09.361Z https://www.opentrain.ai/papers/clearfairy-capturing-creative-workflows-through-decision-structuring-in-situ-que--arxiv-2509.14537/2026-06-19T17:31:23.618Z https://www.opentrain.ai/papers/bridging-past-and-future-distribution-aware-alignment-for-time-series-forecastin--arxiv-2509.14181/2026-06-18T13:16:46.291Z https://www.opentrain.ai/papers/a-simple-and-efficient-jailbreak-method-exploiting-llms-helpfulness--arxiv-2509.14297/2026-06-19T18:40:27.637Z https://www.opentrain.ai/papers/linear-probes-rely-on-textual-evidence-results-from-leakage-mitigation-studies-i--arxiv-2509.21344/2026-06-19T12:34:35.335Z https://www.opentrain.ai/papers/doubleagents-human-agent-alignment-in-a-socially-embedded-workflow--arxiv-2509.12626/2026-06-17T22:30:28.585Z https://www.opentrain.ai/papers/collaborative-document-editing-with-multiple-users-and-ai-agents--arxiv-2509.11826/2026-06-09T13:51:42.680Z https://www.opentrain.ai/papers/cognialign-survivability-grounded-multi-agent-moral-reasoning-for-safe-and-trans--arxiv-2509.13356/2026-06-17T15:48:55.611Z https://www.opentrain.ai/papers/index-preserving-lightweight-token-pruning-for-efficient-document-understanding--arxiv-2509.06415/2026-06-18T06:13:32.012Z https://www.opentrain.ai/papers/causalarc-abstract-reasoning-with-causal-world-models--arxiv-2509.03636/2026-06-18T12:03:03.059Z https://www.opentrain.ai/papers/bioblue-systematic-runaway-optimiser-like-llm-failure-modes-on-biologically-and--arxiv-2509.02655/2026-06-19T12:31:01.739Z https://www.opentrain.ai/papers/cmrag-co-modality-based-visual-document-retrieval-and-question-answering--arxiv-2509.02123/2026-06-19T01:39:19.258Z https://www.opentrain.ai/papers/l-mars-legal-multi-agent-workflow-with-orchestrated-reasoning-and-agentic-search--arxiv-2509.00761/2026-06-18T17:58:43.100Z https://www.opentrain.ai/papers/your-ai-bosses-are-still-prejudiced-the-emergence-of-stereotypes-in-llm-based-mu--arxiv-2508.19919/2026-05-22T07:35:50.776Z https://www.opentrain.ai/papers/language-and-experience-a-computational-model-of-social-learning-in-complex-task--arxiv-2509.00074/2026-06-19T12:31:58.546Z https://www.opentrain.ai/papers/hybrid-deep-searcher-scalable-parallel-and-sequential-search-reasoning--arxiv-2508.19113/2026-06-19T17:13:18.162Z https://www.opentrain.ai/papers/why-synthetic-isn-t-real-yet-a-diagnostic-framework-for-contact-center-dialogue--arxiv-2508.18210/2026-06-07T11:42:34.633Z https://www.opentrain.ai/papers/vevo2-a-unified-and-controllable-framework-for-speech-and-singing-voice-generati--arxiv-2508.16332/2026-05-22T07:08:08.640Z https://www.opentrain.ai/papers/mapping-the-course-for-prompt-based-structured-prediction--arxiv-2508.15090/2026-06-18T03:19:13.136Z https://www.opentrain.ai/papers/tokens-with-meaning-a-hybrid-tokenization-approach-for-turkish--arxiv-2508.14292/2026-06-19T12:38:35.313Z https://www.opentrain.ai/papers/the-gpt-4o-shock-emotional-attachment-to-ai-models-and-its-impact-on-regulatory--arxiv-2508.16624/2026-06-19T12:37:35.445Z https://www.opentrain.ai/papers/sql-exchange-transforming-sql-queries-across-domains--arxiv-2508.07087/2026-06-17T23:38:24.360Z https://www.opentrain.ai/papers/mixed-initiative-dialog-for-human-robot-collaborative-manipulation--arxiv-2508.05535/2026-06-19T18:29:49.660Z https://www.opentrain.ai/papers/recode-reinforcing-code-generation-with-reasoning-process-rewards--arxiv-2508.05170/2026-06-18T17:56:14.235Z https://www.opentrain.ai/papers/layert2v-a-unified-multi-layer-video-generation-framework--arxiv-2508.04228/2026-06-17T18:46:21.800Z https://www.opentrain.ai/papers/speechrole-a-large-scale-dataset-and-benchmark-for-evaluating-speech-role-playin--arxiv-2508.02013/2026-04-08T16:12:55.381Z https://www.opentrain.ai/papers/robomemory-a-brain-inspired-multi-memory-agentic-framework-for-interactive-envir--arxiv-2508.01415/2026-06-18T20:32:58.548Z https://www.opentrain.ai/papers/webds-an-end-to-end-benchmark-for-web-based-data-science--arxiv-2508.01222/2026-06-18T03:26:29.461Z https://www.opentrain.ai/papers/neuralos-towards-simulating-operating-systems-via-neural-generative-models--arxiv-2507.08800/2026-06-18T14:41:42.649Z https://www.opentrain.ai/papers/traceable-evidence-enhanced-visual-grounded-reasoning-evaluation-and-methodology--arxiv-2507.07999/2026-06-18T16:38:16.753Z https://www.opentrain.ai/papers/from-fragments-to-facts-a-curriculum-driven-dpo-approach-for-generating-hindi-ne--arxiv-2507.05179/2026-06-19T01:39:30.494Z https://www.opentrain.ai/papers/xism-an-exploratory-and-interactive-graph-tool-to-visualize-and-evaluate-semanti--arxiv-2507.04070/2026-06-18T05:04:46.607Z https://www.opentrain.ai/papers/beyond-cognacy--arxiv-2507.03005/2026-06-19T12:32:51.576Z https://www.opentrain.ai/papers/skywork-reward-v2-scaling-preference-data-curation-via-human-ai-synergy--arxiv-2507.01352/2026-06-19T12:30:46.755Z https://www.opentrain.ai/papers/cognitive-models-can-reveal-interpretable-value-trade-offs-in-language-models--arxiv-2506.20666/2026-06-19T11:29:43.925Z https://www.opentrain.ai/papers/context-biasing-for-pronunciation-orthography-mismatch-in-automatic-speech-recog--arxiv-2506.18703/2026-06-18T14:02:56.124Z https://www.opentrain.ai/papers/a-simple-motivation-can-enhance-reinforcement-finetuning-of-large-reasoning-mode--arxiv-2506.18485/2026-06-18T13:21:14.363Z https://www.opentrain.ai/papers/improving-black-box-generative-attacks-via-generator-semantic-consistency--arxiv-2506.18248/2026-06-18T09:16:28.102Z https://www.opentrain.ai/papers/towards-ai-search-paradigm--arxiv-2506.17188/2026-06-18T04:40:57.486Z https://www.opentrain.ai/papers/multimodal-fused-learning-for-solving-the-generalized-traveling-salesman-problem--arxiv-2506.16931/2026-06-18T04:33:28.045Z https://www.opentrain.ai/papers/the-fid-lottery-quantifying-hidden-randomness-in-generative-model-evaluation--arxiv-2606.20536/2026-06-19T21:27:40.142Z https://www.opentrain.ai/papers/freeing-the-law-with-locus-a-local-ordinance-corpus-for-the-united-states--arxiv-2606.19334/2026-06-19T21:27:14.941Z https://www.opentrain.ai/papers/when-does-trajectory-level-supervision-permit-efficient-offline-reinforcement-le--arxiv-2606.18531/2026-06-20T03:32:17.997Z https://www.opentrain.ai/papers/adaptive-volumetric-mechanical-property-fields-invariant-to-resolution--arxiv-2606.18231/2026-06-20T03:05:54.034Z https://www.opentrain.ai/papers/sae-interventions-are-unreliable-post-intervention-recovery-of-suppressed-behavi--arxiv-2606.18322/2026-06-19T22:31:11.955Z https://www.opentrain.ai/papers/brdfusion-physics-meets-generation-for-urban-scene-inverse-rendering--arxiv-2606.17049/2026-06-18T13:16:40.279Z https://www.opentrain.ai/papers/hierarchical-advantage-weighting-for-online-rl-fine-tuning-of-vlas-from-sparse-e--arxiv-2606.17043/2026-06-18T04:24:44.176Z https://www.opentrain.ai/papers/the-ghosts-of-polymarket-when-off-chain-matches-meet-on-chain-reverts--arxiv-2606.16852/2026-06-18T20:46:41.956Z https://www.opentrain.ai/papers/sp-3-spherical-priors-for-plug-and-play-restoration--arxiv-2606.16396/2026-06-18T19:16:39.520Z https://www.opentrain.ai/papers/egophys-learning-generalizable-physics-models-of-deformable-objects-from-egocent--arxiv-2606.16202/2026-06-19T10:39:54.866Z https://www.opentrain.ai/papers/you-don-t-need-strong-assumptions-visual-representation-learning-via-temporal-di--arxiv-2606.15956/2026-06-19T10:39:32.229Z https://www.opentrain.ai/papers/the-data-manifold-under-the-microscope--arxiv-2606.15760/2026-06-19T21:27:39.658Z https://www.opentrain.ai/papers/dragmesh-2-physically-plausible-dexterous-hand-object-interaction-with-articulat--arxiv-2606.15133/2026-06-19T09:33:59.930Z https://www.opentrain.ai/papers/memento-reconstruct-to-remember-for-consistent-long-video-generation--arxiv-2606.14667/2026-06-19T12:33:33.478Z https://www.opentrain.ai/papers/squeeze-release-iterative-pruning-with-exact-structural-minimization--arxiv-2606.14346/2026-06-18T03:57:31.397Z https://www.opentrain.ai/papers/a-benchmark-and-framework-for-evaluating-next-action-predictions-in-spreadsheets--arxiv-2606.13802/2026-06-18T12:33:14.898Z https://www.opentrain.ai/papers/maxproof-scaling-mathematical-proof-with-generative-verifier-rl-and-population-l--arxiv-2606.13473/2026-06-18T17:56:49.444Z https://www.opentrain.ai/papers/rethinking-rag-in-long-videos-what-to-retrieve-and-how-to-use-it--arxiv-2606.13141/2026-06-15T05:22:40.110Z https://www.opentrain.ai/papers/the-hidden-power-of-scaling-factor-in-lora-optimization--arxiv-2606.12883/2026-06-19T12:34:08.351Z https://www.opentrain.ai/papers/pianokontext-expressive-performance-rendering-from-deadpan-context--arxiv-2606.12282/2026-06-18T19:18:09.513Z https://www.opentrain.ai/papers/unstable-features-reproducible-subspaces-understanding-seed-dependence-in-sparse--arxiv-2606.12138/2026-06-19T19:42:39.138Z https://www.opentrain.ai/papers/on-the-limits-of-llm-as-judge-for-scientific-novelty-assessment--arxiv-2606.12071/2026-06-19T10:41:44.496Z https://www.opentrain.ai/papers/time-series-foundation-model-embeddings-for-remaining-useful-life-estimation--arxiv-2606.11990/2026-06-16T15:51:42.547Z https://www.opentrain.ai/papers/a-stationary-and-therefore-compatible-representation-is-all-you-need--arxiv-2606.12488/2026-06-14T15:35:36.076Z https://www.opentrain.ai/papers/quickest-detection-of-hallucination-onset-delay-bounds-and-learned-cusum-statist--arxiv-2606.12476/2026-06-18T13:17:15.891Z https://www.opentrain.ai/papers/apex-a-network-native-time-series-foundation-model-for-forecasting-and-anomaly-d--arxiv-2606.11553/2026-06-16T15:34:44.951Z https://www.opentrain.ai/papers/i1-a-simple-and-fully-open-recipe-for-strong-text-to-image-models--arxiv-2606.11289/2026-06-19T12:36:38.779Z https://www.opentrain.ai/papers/flash-gmm-a-memory-efficient-kernel-for-scalable-soft-clustering--arxiv-2606.10896/2026-06-16T22:11:12.320Z https://www.opentrain.ai/papers/fademem-distance-aware-memory-consolidation-for-autoregressive-video-diffusion--arxiv-2606.10671/2026-06-19T08:07:59.684Z https://www.opentrain.ai/papers/interpreting-and-steering-a-text-to-speech-language-model-with-sparse-autoencode--arxiv-2606.10029/2026-06-18T13:17:18.331Z https://www.opentrain.ai/papers/abot-earth-0-5-generative-3d-earth-model--arxiv-2606.09967/2026-06-18T19:15:40.909Z https://www.opentrain.ai/papers/evaluation-cards-an-interpretive-layer-for-ai-evaluation-reporting--arxiv-2606.09809/2026-06-09T04:12:53.681Z https://www.opentrain.ai/papers/brainsurgery-reproducible-and-reliable-declarative-weight-manipulations-for-mode--arxiv-2606.09707/2026-06-18T11:31:02.078Z https://www.opentrain.ai/papers/precision-is-not-faithfulness-coverage-aware-evaluation-of-grounded-generation-w--arxiv-2606.09376/2026-06-19T12:36:34.571Z https://www.opentrain.ai/papers/trl-bench-standardizing-cross-paradigm-representation-level-evaluation-of-tabula--arxiv-2606.09323/2026-06-19T18:43:57.145Z https://www.opentrain.ai/papers/oasis-from-simulation-data-collection-to-real-world-humanoid-loco-manipulation--arxiv-2606.08548/2026-06-09T04:12:50.711Z https://www.opentrain.ai/papers/set-based-transformer-for-atmospheric-compensation-in-standoff-lwir-hyperspectra--arxiv-2606.08324/2026-06-18T05:30:27.965Z https://www.opentrain.ai/papers/breaking-the-bubble-asynchronous-pipeline-parallel-training-with-bounded-weight--arxiv-2606.07881/2026-06-20T01:42:19.896Z https://www.opentrain.ai/papers/whisper-hallucination-detection-and-mitigation-via-hidden-representation-steerin--arxiv-2606.07473/2026-06-16T05:56:51.012Z https://www.opentrain.ai/papers/where-rectified-flows-leak-characterising-membership-signals-along-the-interpola--arxiv-2606.07271/2026-06-18T13:15:39.333Z https://www.opentrain.ai/papers/entropy-as-a-structural-prior-how-a-log-barrier-on-dit-belief-space-drives-music--arxiv-2606.07207/2026-06-19T12:18:28.508Z https://www.opentrain.ai/papers/limmt-less-is-more-for-motion-tracking--arxiv-2606.06953/2026-06-18T18:40:33.484Z https://www.opentrain.ai/papers/direct-3d-aware-object-insertion-via-decomposed-visual-proxies--arxiv-2606.06601/2026-06-18T13:16:42.314Z https://www.opentrain.ai/papers/complexity-balanced-diffusion-splitting--arxiv-2606.06477/2026-06-16T16:04:21.073Z https://www.opentrain.ai/papers/in-context-multiple-instance-learning--arxiv-2606.06458/2026-06-19T12:03:54.211Z https://www.opentrain.ai/papers/physics-in-2-steps-locking-motion-priors-before-visual-refinement-erases-them--arxiv-2606.06361/2026-06-18T13:15:17.638Z https://www.opentrain.ai/papers/activemimic-egocentric-video-pretraining-with-active-perception--arxiv-2606.06194/2026-06-19T18:39:40.758Z https://www.opentrain.ai/papers/towards-truly-multilingual-asr-generalizing-code-switching-asr-to-unseen-languag--arxiv-2606.05846/2026-06-19T12:05:48.298Z https://www.opentrain.ai/papers/deep-embedded-multiplicative-dmd-for-algebra-preserving-koopman-learning--arxiv-2606.05131/2026-06-04T10:26:13.707Z https://www.opentrain.ai/papers/zipsplat-fewer-gaussians-better-splats--arxiv-2606.05102/2026-06-20T00:30:42.246Z https://www.opentrain.ai/papers/dream-exe-can-video-generation-models-dream-executable-robot-manipulation--arxiv-2606.04811/2026-06-19T12:05:19.730Z https://www.opentrain.ai/papers/measuring-model-robustness-via-fisher-information-spectral-bounds-theoretical-gu--arxiv-2606.04767/2026-06-19T12:05:55.076Z https://www.opentrain.ai/papers/syncred-bench-benchmarking-synthetic-credibility-in-ai-generated-visual-misinfor--arxiv-2606.03348/2026-06-19T13:37:01.558Z https://www.opentrain.ai/papers/ba-t-an-iterative-transformer-for-two-view-bundle-adjustment--arxiv-2606.03287/2026-06-19T17:26:50.773Z https://www.opentrain.ai/papers/afun-towards-an-affordance-foundation-model-for-functionality-understanding--arxiv-2606.02551/2026-06-19T17:29:07.659Z https://www.opentrain.ai/papers/on-the-scaling-of-peft-towards-million-personal-models-of-trillion-parameters--arxiv-2606.02437/2026-06-19T19:35:25.767Z https://www.opentrain.ai/papers/quality-guided-semi-supervised-learning-for-medical-image-segmentation--arxiv-2606.01753/2026-06-19T17:33:01.911Z https://www.opentrain.ai/papers/two-fidelity-best-action-identification-for-stochastic-minimax-tree--arxiv-2606.01708/2026-06-19T12:05:21.398Z https://www.opentrain.ai/papers/a-formally-verified-library-of-mathematical-finance-in-lean-4--arxiv-2606.01356/2026-06-19T17:33:07.164Z https://www.opentrain.ai/papers/measuring-the-symmetry-data-exchange-rate--arxiv-2606.01090/2026-06-19T17:33:40.155Z https://www.opentrain.ai/papers/semi-supervised-noise-adaptation-transferring-knowledge-from-noise-domain--arxiv-2606.00558/2026-06-19T12:05:34.184Z https://www.opentrain.ai/papers/depth-learning-single-pass-soft-boundary-decomposition-for-stereo-conversion--arxiv-2606.00386/2026-06-19T17:22:33.082Z https://www.opentrain.ai/papers/score-control-for-hallucination-reduction-in-diffusion-models--arxiv-2606.00377/2026-06-18T18:43:54.164Z https://www.opentrain.ai/papers/rayder-scalable-self-supervised-novel-view-synthesis-from-real-world-video--arxiv-2605.31535/2026-06-19T17:33:48.339Z https://www.opentrain.ai/papers/vlm3-vision-language-models-are-native-3d-learners--arxiv-2605.30561/2026-06-19T17:34:26.130Z https://www.opentrain.ai/papers/on-language-generation-in-the-limit-with-bounded-memory--arxiv-2605.30324/2026-06-19T17:20:17.652Z https://www.opentrain.ai/papers/mira-mid-training-rubric-anchoring-for-source-aware-data-selection--arxiv-2605.30288/2026-06-19T17:42:56.266Z https://www.opentrain.ai/papers/grasp-plan-guided-graph-retrieval-with-adaptive-fusion-and-reranking-on-semi-str--arxiv-2605.30237/2026-06-19T17:42:56.152Z https://www.opentrain.ai/papers/token-level-generalization-in-lora-adapter-backdoors-attack-characterization-and--arxiv-2605.30189/2026-06-19T01:26:36.402Z https://www.opentrain.ai/papers/corpipe-at-crac-2026-empty-nodes-and-cross-lingual-transfer-in-multilingual-core--arxiv-2605.30133/2026-06-19T17:37:41.290Z https://www.opentrain.ai/papers/dial-healthdial-for-advice-a-multilingual-and-multi-parallel-spoken-dialogue-dat--arxiv-2605.30107/2026-06-19T17:27:30.366Z https://www.opentrain.ai/papers/geometry-matters-3d-foundation-priors-for-learning-semantic-correspondence--arxiv-2605.30093/2026-06-19T17:36:15.590Z https://www.opentrain.ai/papers/towards-consistent-video-geometry-estimation--arxiv-2605.30060/2026-06-19T11:36:58.440Z https://www.opentrain.ai/papers/meld-mel-spectrogram-based-speech-language-modeling-with-discrete-latent-variabl--arxiv-2605.29859/2026-06-19T17:30:58.170Z https://www.opentrain.ai/papers/data-filtering-methods-for-training-language-models--arxiv-2605.29807/2026-06-19T22:26:03.704Z https://www.opentrain.ai/papers/metric-dependent-annotation-saturation-for-learning-from-label-distributions--arxiv-2605.29797/2026-06-19T01:00:13.493Z https://www.opentrain.ai/papers/why-larger-models-learn-more-effects-of-capacity-interference-and-rare-task-rete--arxiv-2605.29548/2026-06-19T17:22:58.893Z https://www.opentrain.ai/papers/access-sets-matter-budgeting-expert-reads-for-scalable-weight-space-model-mergin--arxiv-2605.29489/2026-06-19T12:05:52.906Z https://www.opentrain.ai/papers/one-click-per-cell-type-suffices-training-free-group-interaction-for-cell-instan--arxiv-2605.29429/2026-06-19T17:36:26.035Z https://www.opentrain.ai/papers/the-good-the-bad-and-the-ugly-of-markov-boundary-for-tabular-prediction--arxiv-2605.29411/2026-06-19T12:04:18.350Z https://www.opentrain.ai/papers/freeform-reduced-order-deformable-simulation-from-particle-based-skinning-eigenm--arxiv-2605.29318/2026-06-18T18:34:48.395Z https://www.opentrain.ai/papers/childvox-a-speech-audio-and-large-audio-language-model-benchmark-in-understandin--arxiv-2605.29257/2026-06-18T18:34:37.882Z https://www.opentrain.ai/papers/omniretrieval-unified-retrieval-across-heterogeneous-knowledge-sources--arxiv-2605.29250/2026-06-19T17:40:48.561Z https://www.opentrain.ai/papers/rubric-arrow-alternating-pointwise-rubric-reward-modeling-for-llm-post-training--arxiv-2605.29156/2026-05-31T15:30:24.387Z https://www.opentrain.ai/papers/same-question-different-source-different-answer-auditing-source-dependence-in-me--arxiv-2605.29084/2026-06-19T01:33:28.418Z https://www.opentrain.ai/papers/the-hamilton-jacobi-theory-of-deep-learning--arxiv-2605.28983/2026-06-19T12:05:39.306Z https://www.opentrain.ai/papers/alphatransit-learning-to-design-city-scale-transit-routes--arxiv-2605.28730/2026-06-19T17:32:29.540Z https://www.opentrain.ai/papers/demon-diffusion-engine-for-musical-orchestrated-noise--arxiv-2605.28657/2026-06-18T18:39:02.853Z https://www.opentrain.ai/papers/graphlit-learning-text-enriched-dynamic-character-network-representations-for-li--arxiv-2605.28643/2026-06-20T00:20:31.892Z https://www.opentrain.ai/papers/comprehensive-benchmarking-of-long-form-speech-generation-in-diverse-scenarios--arxiv-2605.28618/2026-06-19T13:42:19.587Z https://www.opentrain.ai/papers/models-that-know-how-evaluations-are-designed-score-safer--arxiv-2605.28591/2026-06-18T23:17:12.626Z https://www.opentrain.ai/papers/prorl-effective-reinforcement-learning-for-proactive-recommendation-via-rectifie--arxiv-2605.28293/2026-06-19T12:05:50.595Z https://www.opentrain.ai/papers/frequency-guided-action-diffusion-via-sub-frequency-manifold-traversal--arxiv-2605.27919/2026-06-19T17:23:36.173Z https://www.opentrain.ai/papers/smartdirector-keyframe-conditioned-cinematic-video-generation-with-narrative-pac--arxiv-2605.27891/2026-06-18T18:36:57.477Z https://www.opentrain.ai/papers/merit-learning-disentangled-music-representations-for-audio-similarity--arxiv-2605.27346/2026-06-19T17:42:30.666Z https://www.opentrain.ai/papers/trust-region-q-adjoint-matching--arxiv-2605.27079/2026-06-18T18:39:59.925Z https://www.opentrain.ai/papers/batterymformer-multi-level-learning-for-battery-degradation-trajectory-forecasti--arxiv-2605.27044/2026-06-18T18:30:55.691Z https://www.opentrain.ai/papers/prism-a-multi-dimensional-benchmark-for-evaluating-llm-peer-reviewers--arxiv-2605.26730/2026-06-19T17:34:24.173Z https://www.opentrain.ai/papers/is-position-bias-in-dense-retrievers-built-in-or-learned-from-data--arxiv-2605.26578/2026-06-19T17:41:49.690Z https://www.opentrain.ai/papers/unified-panoramic-geometry-estimation-via-multi-view-foundation-models--arxiv-2605.26368/2026-06-19T17:24:31.102Z https://www.opentrain.ai/papers/unified-neural-scaling-laws--arxiv-2605.26248/2026-06-19T17:16:16.041Z https://www.opentrain.ai/papers/geometry-aware-representation-denoising-for-robust-multi-view-3d-reconstruction--arxiv-2605.26230/2026-06-19T17:26:45.968Z https://www.opentrain.ai/papers/channel-wise-vector-quantization--arxiv-2605.26089/2026-06-19T17:28:23.120Z https://www.opentrain.ai/papers/confidence-and-calibration-of-activation-oracles-for-reliable-interpretation-of--arxiv-2605.26045/2026-06-19T12:03:53.392Z https://www.opentrain.ai/papers/everything-at-every-scale-scale-invariant-diffusion-with-continuous-super-resolu--arxiv-2605.26032/2026-06-18T18:37:18.325Z https://www.opentrain.ai/papers/how-accurate-are-video-quality-models-for-diffusion-based-video-super-resolution--arxiv-2605.25940/2026-06-19T17:38:55.860Z https://www.opentrain.ai/papers/growing-a-neural-network-in-breadth-depth-and-time--arxiv-2605.25174/2026-06-19T17:18:34.523Z https://www.opentrain.ai/papers/learning-high-frequency-continuous-action-chunks-in-latent-space--arxiv-2605.24931/2026-06-19T17:27:18.277Z https://www.opentrain.ai/papers/can-predicted-dynamics-exist-in-the-physical-world--arxiv-2606.00089/2026-06-19T17:19:41.807Z https://www.opentrain.ai/papers/towards-evaluation-engineering-an-empirical-study-of-ml-evaluation-harnesses-in--arxiv-2605.24213/2026-06-19T17:17:41.243Z https://www.opentrain.ai/papers/good-token-hunting-a-hitchhiker-s-guide-to-token-selection-for-visual-geometry-t--arxiv-2605.23892/2026-06-19T17:33:40.153Z https://www.opentrain.ai/papers/convex-low-resource-accent-robust-language-detection-in-speech-recognition--arxiv-2605.23235/2026-06-19T12:05:46.449Z https://www.opentrain.ai/papers/tokenisation-via-convex-relaxations--arxiv-2605.22821/2026-06-17T19:21:57.897Z https://www.opentrain.ai/papers/sensor2sensor-cross-embodiment-sensor-conversion-for-autonomous-driving--arxiv-2605.22809/2026-06-19T17:36:39.235Z https://www.opentrain.ai/papers/decq-detail-condensing-queries-for-enhanced-reconstruction-and-generation-in-rep--arxiv-2605.22777/2026-06-19T17:25:18.362Z https://www.opentrain.ai/papers/tokenization-with-split-trees--arxiv-2605.22705/2026-06-19T17:37:37.830Z https://www.opentrain.ai/papers/seeing-the-poem-image-semantic-detection-of-ai-generated-modern-chinese-poetry-w--arxiv-2605.22654/2026-06-19T17:30:20.990Z https://www.opentrain.ai/papers/whose-voice-counts-mapping-stakeholder-perspectives-on-ai-through-public-submiss--arxiv-2605.22650/2026-06-19T17:22:01.057Z https://www.opentrain.ai/papers/the-double-dilemma-in-multi-task-radiology-report-generation-a-gradient-dynamics--arxiv-2605.22635/2026-06-19T17:22:18.511Z https://www.opentrain.ai/papers/chinese-sensorimotor-and-embodiment-norms-for-3-000-lexicalized-concepts--arxiv-2605.22616/2026-06-19T17:28:34.277Z https://www.opentrain.ai/papers/a-tutorial-on-diffusion-theory-from-differential-equations-to-diffusion-models--arxiv-2605.22586/2026-06-19T17:32:53.518Z https://www.opentrain.ai/papers/segment-anything-with-motion-geometry-and-semantic-adaptation-for-complex-nonlin--arxiv-2605.22538/2026-06-19T12:03:54.333Z https://www.opentrain.ai/papers/in-silico-modeling-of-the-rampho-buffer-dissociating-informational-and-energetic--arxiv-2605.22465/2026-06-19T17:27:40.722Z https://www.opentrain.ai/papers/cohesion-6k-an-arabic-dataset-for-analyzing-social-cohesion-and-conflict-in-onli--arxiv-2605.22447/2026-06-20T02:35:54.192Z https://www.opentrain.ai/papers/epicure-navigating-the-emergent-geometry-of-food-ingredient-embeddings--arxiv-2605.22391/2026-06-18T14:03:54.837Z https://www.opentrain.ai/papers/multi-stage-training-for-abusive-comment-detection-in-indic-languages--arxiv-2605.22380/2026-06-19T17:29:35.190Z https://www.opentrain.ai/papers/idiolink-retrieving-meaning-beyond-words-across-idiomatic-and-literal-expression--arxiv-2605.22247/2026-06-19T17:31:43.130Z https://www.opentrain.ai/papers/evaluation-of-chunking-strategies-for-effective-text-embedding-in-low-resource-l--arxiv-2605.22203/2026-06-19T17:24:41.250Z https://www.opentrain.ai/papers/structure-retention-in-embedding-spaces-as-a-predictor-of-benchmark-performance--arxiv-2605.22202/2026-06-19T17:26:33.417Z https://www.opentrain.ai/papers/learning-a-unified-risk-map-for-autonomous-driving-in-partially-observable-envir--arxiv-2605.22189/2026-06-19T17:23:52.502Z