https://www.opentrain.ai/papers/panoworld-a-generative-spatial-world-model-for-consistent-whole-house-panorama-s--arxiv-2605.17916/2026-06-18T08:02:21.492Z https://www.opentrain.ai/papers/ethical-hyper-velocity-ehv-a-provably-deterministic-governance-aware-jit-compile--arxiv-2605.17909/2026-05-21T04:33:08.872Z https://www.opentrain.ai/papers/latentumm-dual-latent-alignment-for-unified-multimodal-models--arxiv-2605.17766/2026-06-18T23:07:40.093Z https://www.opentrain.ai/papers/harnessing-llm-agents-with-skill-programs--arxiv-2605.17734/2026-06-18T23:03:36.202Z https://www.opentrain.ai/papers/stop-when-reasoning-converges-semantic-preserving-early-exit-for-reasoning-model--arxiv-2605.17672/2026-06-18T08:20:14.984Z https://www.opentrain.ai/papers/causal-intervention-based-memory-selection-for-long-horizon-llm-agents--arxiv-2605.17641/2026-06-19T19:25:56.568Z https://www.opentrain.ai/papers/safelens-deliberate-and-efficient-video-guardrails-with-fast-and-slow-screening--arxiv-2605.17610/2026-06-18T23:07:34.153Z https://www.opentrain.ai/papers/don-t-guess-just-ask-resolving-ambiguity-in-referring-segmentation-via-multi-tur--arxiv-2605.17531/2026-06-18T23:06:11.365Z https://www.opentrain.ai/papers/saasbench-exploring-the-boundaries-of-coding-agents-in-long-horizon-enterprise-s--arxiv-2605.17526/2026-06-19T12:18:53.281Z https://www.opentrain.ai/papers/self-improving-cad-generation-agents-with-finite-element-analysis-as-feedback--arxiv-2605.17448/2026-06-18T11:55:16.849Z https://www.opentrain.ai/papers/soap2soap-long-cinematic-video-remaking-via-multi-agent-collaboration--arxiv-2605.17423/2026-06-18T08:02:46.980Z https://www.opentrain.ai/papers/a2rbench-an-automatic-paradigm-for-formally-verifiable-abstract-reasoning-benchm--arxiv-2605.17278/2026-06-18T23:10:18.856Z https://www.opentrain.ai/papers/geometric-phase-transition-enables-extreme-hippocampal-memory-capacity--arxiv-2605.17199/2026-06-18T23:08:04.181Z https://www.opentrain.ai/papers/capturing-llm-capabilities-via-evidence-calibrated-query-clustering--arxiv-2605.17110/2026-06-18T13:16:46.758Z https://www.opentrain.ai/papers/s-bus-automatic-read-set-reconstruction-for-multi-agent-llm-state-coordination--arxiv-2605.17076/2026-06-19T10:42:28.266Z https://www.opentrain.ai/papers/tobench-a-task-oriented-omni-modal-benchmark-for-real-world-tool-using-agents--arxiv-2605.16909/2026-06-18T22:44:44.177Z https://www.opentrain.ai/papers/ngm-a-plug-and-play-training-free-memory-module-for-llms--arxiv-2605.16893/2026-06-18T23:04:55.731Z https://www.opentrain.ai/papers/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujo--arxiv-2605.16257/2026-06-18T11:52:18.063Z https://www.opentrain.ai/papers/videoseeker-incentivizing-instance-level-video-understanding-via-native-agentic--arxiv-2605.16079/2026-06-18T14:18:55.386Z https://www.opentrain.ai/papers/worldact-activating-monolithic-3d-worlds-into-interactive-ready-object-centric-s--arxiv-2605.15843/2026-06-18T08:18:37.748Z https://www.opentrain.ai/papers/fashionchameleon-towards-real-time-and-interactive-human-garment-video-customiza--arxiv-2605.15824/2026-06-18T08:05:42.672Z https://www.opentrain.ai/papers/physbrain-1-0-technical-report--arxiv-2605.15298/2026-06-18T07:55:32.285Z https://www.opentrain.ai/papers/atlas-agentic-or-latent-visual-reasoning-one-word-is-enough-for-both--arxiv-2605.15198/2026-06-18T08:02:44.380Z https://www.opentrain.ai/papers/futuresim-replaying-world-events-to-evaluate-adaptive-agents--arxiv-2605.15188/2026-06-19T11:52:14.089Z https://www.opentrain.ai/papers/quantitative-video-world-model-evaluation-for-geometric-consistency--arxiv-2605.15185/2026-06-18T09:13:29.447Z https://www.opentrain.ai/papers/warp-as-history-generalizable-camera-controlled-video-generation-from-one-traini--arxiv-2605.15182/2026-06-18T23:05:29.052Z https://www.opentrain.ai/papers/memeye-a-visual-centric-evaluation-framework-for-multimodal-agent-memory--arxiv-2605.15128/2026-06-18T12:16:39.954Z https://www.opentrain.ai/papers/learning-from-language-feedback-via-variational-policy-distillation--arxiv-2605.15113/2026-06-18T14:18:55.230Z https://www.opentrain.ai/papers/beyond-individual-intelligence-surveying-collaboration-failure-attribution-and-s--arxiv-2605.14892/2026-06-18T08:02:17.038Z https://www.opentrain.ai/papers/known-by-their-actions-fingerprinting-llm-browser-agents-via-ui-traces--arxiv-2605.14786/2026-06-18T23:06:13.612Z https://www.opentrain.ai/papers/vimu-benchmarking-video-metaphorical-understanding--arxiv-2605.14607/2026-06-19T22:45:26.665Z https://www.opentrain.ai/papers/lisa-lifelong-safety-adaptation-via-conservative-policy-induction--arxiv-2605.14454/2026-06-18T08:05:43.096Z https://www.opentrain.ai/papers/frontiersmith-synthesizing-open-ended-coding-problems-at-scale--arxiv-2605.14445/2026-06-18T21:38:38.460Z https://www.opentrain.ai/papers/nexus-an-agentic-framework-for-time-series-forecasting--arxiv-2605.14389/2026-06-18T13:16:45.540Z https://www.opentrain.ai/papers/llm-based-detection-of-manipulative-political-narratives--arxiv-2605.14354/2026-06-20T03:47:40.016Z https://www.opentrain.ai/papers/kvpo-ode-native-grpo-for-autoregressive-video-alignment-via-kv-semantic-explorat--arxiv-2605.14278/2026-06-18T01:26:01.765Z https://www.opentrain.ai/papers/auditing-agent-harness-safety--arxiv-2605.14271/2026-06-18T14:19:34.809Z https://www.opentrain.ai/papers/bookmarks-efficient-active-storyline-memory-for-role-playing--arxiv-2605.14169/2026-06-18T23:06:32.394Z https://www.opentrain.ai/papers/curvebench-a-benchmark-for-exact-topological-reasoning-over-nested-jordan-curves--arxiv-2605.14068/2026-06-18T09:50:48.354Z https://www.opentrain.ai/papers/spin-structural-llm-planning-via-iterative-navigation-for-industrial-tasks--arxiv-2605.14051/2026-06-18T11:54:38.418Z https://www.opentrain.ai/papers/hodgecover-higher-order-topological-coverage-drives-compression-of-sparse-mixtur--arxiv-2605.13997/2026-06-18T22:52:17.513Z https://www.opentrain.ai/papers/eva-bench-a-new-end-to-end-framework-for-evaluating-voice-agents--arxiv-2605.13841/2026-06-18T15:41:36.142Z https://www.opentrain.ai/papers/evolvemem-self-evolving-memory-architecture-via-autoresearch-for-llm-agents--arxiv-2605.13941/2026-06-20T08:04:45.265Z https://www.opentrain.ai/papers/mint-managed-infrastructure-for-training-and-serving-millions-of-llms--arxiv-2605.13779/2026-06-18T23:03:59.326Z https://www.opentrain.ai/papers/roboevolve-co-evolving-planner-simulator-for-robotic-manipulation-with-limited-d--arxiv-2605.13775/2026-06-18T15:39:35.445Z https://www.opentrain.ai/papers/frameskip-learning-from-fewer-but-more-informative-frames-in-vla-training--arxiv-2605.13757/2026-06-18T17:33:43.656Z https://www.opentrain.ai/papers/learning-pomdp-world-models-from-observations-with-language-model-priors--arxiv-2605.13740/2026-06-18T22:46:00.340Z https://www.opentrain.ai/papers/anyflow-any-step-video-diffusion-model-with-on-policy-flow-map-distillation--arxiv-2605.13724/2026-06-19T08:13:53.381Z https://www.opentrain.ai/papers/mmskills-towards-multimodal-skills-for-general-visual-agents--arxiv-2605.13527/2026-06-20T09:02:22.953Z https://www.opentrain.ai/papers/inducing-overthink-hierarchical-genetic-algorithm-based-dos-attack-on-black-box--arxiv-2605.13338/2026-06-18T01:37:52.709Z https://www.opentrain.ai/papers/achieving-gold-medal-level-olympiad-reasoning-via-simple-and-unified-scaling--arxiv-2605.13301/2026-06-18T08:05:41.882Z https://www.opentrain.ai/papers/retrieval-is-cheap-show-me-the-code-executable-multi-hop-reasoning-for-retrieval--arxiv-2605.12975/2026-06-19T13:39:28.498Z https://www.opentrain.ai/papers/writesae-sparse-autoencoders-for-recurrent-state--arxiv-2605.12770/2026-06-18T14:46:02.168Z https://www.opentrain.ai/papers/docatlas-multilingual-document-understanding-across-80-languages--arxiv-2605.12623/2026-06-18T22:47:57.210Z https://www.opentrain.ai/papers/longmemeval-v2-evaluating-long-term-agent-memory-toward-experienced-colleagues--arxiv-2605.12493/2026-06-19T23:09:47.636Z https://www.opentrain.ai/papers/beyond-grpo-and-on-policy-distillation-an-empirical-sparse-to-dense-reward-princ--arxiv-2605.12483/2026-06-18T08:25:11.729Z https://www.opentrain.ai/papers/meme-multi-entity-evolving-memory-evaluation--arxiv-2605.12477/2026-06-18T14:30:49.258Z https://www.opentrain.ai/papers/reward-hacking-in-rubric-based-reinforcement-learning--arxiv-2605.12474/2026-06-18T08:18:50.500Z https://www.opentrain.ai/papers/lychsim-a-controllable-and-interactive-simulation-framework-for-vision-research--arxiv-2605.12449/2026-06-18T08:16:01.822Z https://www.opentrain.ai/papers/mocam-unified-novel-view-synthesis-via-structured-denoising-dynamics--arxiv-2605.12119/2026-06-18T22:54:09.206Z https://www.opentrain.ai/papers/world-action-models-the-next-frontier-in-embodied-ai--arxiv-2605.12090/2026-06-19T08:55:28.509Z https://www.opentrain.ai/papers/entropy-polarity-in-reinforcement-fine-tuning-direction-asymmetry-and-control--arxiv-2605.11775/2026-06-18T02:14:50.701Z https://www.opentrain.ai/papers/shapecodebench-a-renewable-benchmark-for-perception-to-program-reconstruction-of--arxiv-2605.11680/2026-06-18T17:37:17.828Z https://www.opentrain.ai/papers/the-dawn-of-world-action-interactive-models--arxiv-2605.11550/2026-06-18T22:46:33.932Z https://www.opentrain.ai/papers/overcoming-dynamics-blindness-training-free-pace-and-path-correction-for-vla-mod--arxiv-2605.11459/2026-06-18T22:54:36.974Z https://www.opentrain.ai/papers/adaptive-teacher-exposure-for-self-distillation-in-llm-reasoning--arxiv-2605.11458/2026-06-20T05:43:47.525Z https://www.opentrain.ai/papers/presentagent-2-towards-generalist-multimodal-presentation-agents--arxiv-2605.11363/2026-06-19T16:04:18.397Z https://www.opentrain.ai/papers/revision-scaling-computer-use-agents-via-temporal-visual-redundancy-reduction--arxiv-2605.11212/2026-06-18T11:54:19.409Z https://www.opentrain.ai/papers/deco-sparse-mixture-of-experts-with-dense-comparable-performance-on-end-side-dev--arxiv-2605.10933/2026-06-18T07:58:17.164Z https://www.opentrain.ai/papers/shepherd-a-runtime-substrate-empowering-meta-agents-with-a-formalized-execution--arxiv-2605.10913/2026-06-18T07:57:14.984Z https://www.opentrain.ai/papers/capvector-learning-transferable-capability-vectors-in-parametric-space-for-visio--arxiv-2605.10903/2026-06-18T11:50:52.737Z https://www.opentrain.ai/papers/rubricem-meta-rl-with-rubric-guided-policy-decomposition-beyond-verifiable-rewar--arxiv-2605.10899/2026-06-18T08:23:35.380Z https://www.opentrain.ai/papers/unmasking-on-policy-distillation-where-it-helps-where-it-hurts-and-why--arxiv-2605.10889/2026-06-18T11:52:47.427Z https://www.opentrain.ai/papers/beacon-a-multimodal-dataset-for-learning-behavioral-fingerprints-from-gameplay-d--arxiv-2605.10867/2026-06-19T19:14:36.850Z https://www.opentrain.ai/papers/towards-on-policy-data-evolution-for-visual-native-multimodal-deep-search-agents--arxiv-2605.10832/2026-06-20T07:58:59.328Z https://www.opentrain.ai/papers/gridprobe-posterior-probing-for-adaptive-test-time-compute-in-long-video-vlms--arxiv-2605.10762/2026-06-19T23:16:36.484Z https://www.opentrain.ai/papers/multabench-benchmarking-multimodal-tabular-learning-with-text-and-image--arxiv-2605.10616/2026-06-18T08:07:13.176Z https://www.opentrain.ai/papers/paperfit-vision-in-the-loop-typesetting-optimization-for-scientific-documents--arxiv-2605.10341/2026-06-18T14:18:55.613Z https://www.opentrain.ai/papers/follow-the-mean-reference-guided-flow-matching--arxiv-2605.10302/2026-06-18T13:03:56.507Z https://www.opentrain.ai/papers/continual-harness-online-adaptation-for-self-improving-foundation-agents--arxiv-2605.09998/2026-06-20T04:42:54.024Z https://www.opentrain.ai/papers/preping-building-agent-memory-without-tasks--arxiv-2605.13880/2026-06-18T14:17:35.761Z https://www.opentrain.ai/papers/g-zero-self-play-for-open-ended-generation-from-zero-data--arxiv-2605.09959/2026-06-18T23:07:26.390Z https://www.opentrain.ai/papers/metal-sci-a-scientific-compute-benchmark-for-evolutionary-llm-kernel-search-on-a--arxiv-2605.09708/2026-06-19T18:01:16.308Z https://www.opentrain.ai/papers/make-each-token-count-towards-improving-long-context-performance-with-kv-cache-e--arxiv-2605.09649/2026-06-18T22:59:50.625Z https://www.opentrain.ai/papers/scratchpad-patching-decoupling-compute-from-patch-size-in-byte-level-language-mo--arxiv-2605.09630/2026-06-18T07:54:15.764Z https://www.opentrain.ai/papers/tacomas-test-time-co-evolution-of-topology-and-capability-in-llm-based-multi-age--arxiv-2605.09539/2026-06-20T04:59:31.598Z https://www.opentrain.ai/papers/loopus-recasting-pretrained-llms-into-looped-latent-refinement-models--arxiv-2605.11011/2026-06-20T05:34:00.223Z https://www.opentrain.ai/papers/offline-preference-optimization-for-rectified-flow-with-noise-tracked-pairs--arxiv-2605.09433/2026-06-20T06:42:50.691Z https://www.opentrain.ai/papers/sub-jepa-subspace-gaussian-regularization-for-stable-end-to-end-world-models--arxiv-2605.09241/2026-06-18T11:54:38.821Z https://www.opentrain.ai/papers/fortis-benchmarking-over-privilege-in-agent-skills--arxiv-2605.09163/2026-06-19T13:08:47.928Z https://www.opentrain.ai/papers/soohak-a-mathematician-curated-benchmark-for-evaluating-research-level-math-capa--arxiv-2605.09063/2026-06-18T17:32:32.164Z https://www.opentrain.ai/papers/oracle-anticipating-scams-from-partial-trajectories-in-streaming-app-usage--arxiv-2605.16363/2026-06-18T18:43:54.339Z https://www.opentrain.ai/papers/collabvr-collaborative-video-reasoning-with-vision-language-and-video-generation--arxiv-2605.08735/2026-06-18T15:05:45.451Z https://www.opentrain.ai/papers/pushing-biomolecular-utility-diversity-frontiers-with-supergroup-relative-policy--arxiv-2605.08659/2026-06-18T08:23:03.871Z https://www.opentrain.ai/papers/flashevolve-accelerating-agent-self-evolution-with-asynchronous-stage-orchestrat--arxiv-2605.08520/2026-06-18T17:35:31.731Z https://www.opentrain.ai/papers/results-and-retrospective-analysis-of-the-cods-2025-assetopsbench-challenge--arxiv-2605.08518/2026-06-18T12:52:47.762Z https://www.opentrain.ai/papers/momo-conditioned-contrastive-representation-learning-for-preference-modulated-pl--arxiv-2605.08512/2026-06-18T22:45:11.737Z https://www.opentrain.ai/papers/jina-embeddings-v5-omni-text-geometry-preserving-multimodal-embeddings-via-froze--arxiv-2605.08384/2026-06-19T10:26:27.346Z https://www.opentrain.ai/papers/auto-rubric-as-reward-from-implicit-preferences-to-explicit-multimodal-generativ--arxiv-2605.08354/2026-06-18T17:31:36.251Z https://www.opentrain.ai/papers/normalizing-trajectory-models--arxiv-2605.08078/2026-06-20T01:45:08.093Z https://www.opentrain.ai/papers/conformal-path-reasoning-trustworthy-knowledge-graph-question-answering-via-path--arxiv-2605.08077/2026-06-18T22:52:59.126Z https://www.opentrain.ai/papers/the-memory-curse-how-expanded-recall-erodes-cooperative-intent-in-llm-agents--arxiv-2605.08060/2026-06-18T23:00:41.626Z https://www.opentrain.ai/papers/accurate-and-efficient-statistical-testing-for-word-semantic-breadth--arxiv-2605.08048/2026-06-19T17:48:46.622Z https://www.opentrain.ai/papers/uncertainty-aware-structured-data-extraction-from-full-cmr-reports-via-distilled--arxiv-2605.08045/2026-06-18T22:50:12.064Z https://www.opentrain.ai/papers/scope-structured-decomposition-and-conditional-skill-orchestration-for-complex-i--arxiv-2605.08043/2026-06-18T17:33:05.737Z https://www.opentrain.ai/papers/position-mechanistic-interpretability-must-disclose-identification-assumptions-f--arxiv-2605.08012/2026-06-18T22:42:12.709Z https://www.opentrain.ai/papers/cocoreviewbench-a-completeness-and-correctness-oriented-benchmark-for-ai-reviewe--arxiv-2605.07905/2026-06-18T17:31:35.859Z https://www.opentrain.ai/papers/scene-recognizing-social-norms-and-sanctioning-in-group-chats--arxiv-2605.07823/2026-06-18T22:56:24.141Z https://www.opentrain.ai/papers/simct-recovering-lost-supervision-for-cross-tokenizer-on-policy-distillation--arxiv-2605.07711/2026-06-20T07:31:45.157Z https://www.opentrain.ai/papers/drip-r-a-benchmark-for-decision-making-and-reasoning-under-real-world-policy-amb--arxiv-2605.07699/2026-06-18T17:33:27.752Z https://www.opentrain.ai/papers/maven-multi-agent-verification-elaboration-network-with-in-step-epistemic-auditi--arxiv-2605.07646/2026-06-18T17:46:50.276Z https://www.opentrain.ai/papers/learning-to-communicate-locally-for-large-scale-multi-agent-pathfinding--arxiv-2605.07637/2026-06-18T12:09:04.849Z https://www.opentrain.ai/papers/safe-or-simply-incapable-rethinking-safety-evaluation-for-phone-use-agents--arxiv-2605.07630/2026-06-18T22:49:57.643Z https://www.opentrain.ai/papers/implicit-preference-alignment-for-human-image-animation--arxiv-2605.07545/2026-06-18T17:32:46.982Z https://www.opentrain.ai/papers/specblock-block-iterative-speculative-decoding-with-dynamic-tree-drafting--arxiv-2605.07243/2026-06-18T22:48:54.325Z https://www.opentrain.ai/papers/hypereyes-dual-grained-efficiency-aware-reinforcement-learning-for-parallel-mult--arxiv-2605.07177/2026-06-18T08:18:13.367Z https://www.opentrain.ai/papers/cliper-tailoring-diverse-user-preference-via-classifier-guided-inference-time-pe--arxiv-2605.07162/2026-06-18T15:50:36.189Z https://www.opentrain.ai/papers/learning-visual-feature-based-world-models-via-residual-latent-action--arxiv-2605.07079/2026-06-18T13:03:22.394Z https://www.opentrain.ai/papers/relit-live-relight-video-by-jointly-learning-environment-video--arxiv-2605.06658/2026-06-18T08:01:17.579Z https://www.opentrain.ai/papers/ai-co-mathematician-accelerating-mathematicians-with-agentic-ai--arxiv-2605.06651/2026-06-18T17:19:14.586Z https://www.opentrain.ai/papers/pianocore-combined-and-refined-piano-midi-dataset--arxiv-2605.06627/2026-06-18T23:02:41.947Z https://www.opentrain.ai/papers/skillos-learning-skill-curation-for-self-evolving-agents--arxiv-2605.06614/2026-06-18T14:18:48.045Z https://www.opentrain.ai/papers/geostack-a-framework-for-quasi-abelian-knowledge-composition-in-vlms--arxiv-2605.06477/2026-06-18T08:20:44.466Z https://www.opentrain.ai/papers/mia-signature-approximating-global-activation-for-long-context-understanding--arxiv-2605.06416/2026-06-18T08:03:00.527Z https://www.opentrain.ai/papers/humannet-scaling-human-centric-video-learning-to-one-million-hours--arxiv-2605.06747/2026-06-18T23:06:23.021Z https://www.opentrain.ai/papers/continuous-time-distribution-matching-for-few-step-diffusion-distillation--arxiv-2605.06376/2026-06-18T22:53:21.579Z https://www.opentrain.ai/papers/teaching-thinking-models-to-reason-with-tools-a-full-pipeline-recipe-for-tool-in--arxiv-2605.06326/2026-06-18T17:33:14.461Z https://www.opentrain.ai/papers/opsd-compresses-what-rlvr-teaches-a-post-rl-compaction-stage-for-reasoning-model--arxiv-2605.06188/2026-06-18T02:24:35.139Z https://www.opentrain.ai/papers/on-time-within-budget-constraint-driven-online-resource-allocation-for-agentic-w--arxiv-2605.06110/2026-06-18T23:10:06.709Z https://www.opentrain.ai/papers/uncovering-entity-identity-confusion-in-multimodal-knowledge-editing--arxiv-2605.06096/2026-06-18T09:50:48.085Z https://www.opentrain.ai/papers/milestone-guided-policy-learning-for-long-horizon-language-agents--arxiv-2605.06078/2026-06-19T21:52:03.708Z https://www.opentrain.ai/papers/personakit-pk-a-plug-and-play-platform-for-user-testing-diverse-roles-in-full-du--arxiv-2605.06007/2026-06-18T23:03:15.454Z https://www.opentrain.ai/papers/steering-visual-generation-in-unified-multimodal-models-with-understanding-super--arxiv-2605.05781/2026-06-18T23:10:55.683Z https://www.opentrain.ai/papers/x-omniclaw-technical-report-a-unified-mobile-agent-for-multimodal-understanding--arxiv-2605.05765/2026-06-20T08:33:33.291Z https://www.opentrain.ai/papers/belief-memory-agent-memory-under-partial-observability--arxiv-2605.05583/2026-06-18T23:08:42.227Z https://www.opentrain.ai/papers/who-prices-cognitive-labor-in-the-age-of-agents-compute-anchored-wages--arxiv-2605.05558/2026-06-18T22:53:47.654Z https://www.opentrain.ai/papers/physforge-generating-physics-grounded-3d-assets-for-interactive-virtual-world--arxiv-2605.05163/2026-06-19T12:58:19.444Z https://www.opentrain.ai/papers/self-induced-outcome-potential-turn-level-credit-assignment-for-agents-without-v--arxiv-2605.04984/2026-06-18T19:15:16.842Z https://www.opentrain.ai/papers/a-foundation-model-for-zero-shot-logical-rule-induction--arxiv-2605.04916/2026-06-18T17:32:52.592Z https://www.opentrain.ai/papers/decodingtrust-agent-platform-dtap-a-controllable-and-interactive-red-teaming-pla--arxiv-2605.04808/2026-06-18T14:19:06.532Z https://www.opentrain.ai/papers/che-tkg-collaborative-historical-evidence-and-evolutionary-dynamics-learning-for--arxiv-2605.04652/2026-06-18T19:03:40.202Z https://www.opentrain.ai/papers/swe-webdevbench-evaluating-coding-agent-application-platforms-as-virtual-softwar--arxiv-2605.04637/2026-06-18T06:51:28.221Z https://www.opentrain.ai/papers/remotezero-geospatial-reasoning-with-zero-human-annotations--arxiv-2605.04451/2026-06-20T05:41:16.451Z https://www.opentrain.ai/papers/the-scaling-properties-of-implicit-deductive-reasoning-in-transformers--arxiv-2605.04330/2026-06-18T22:42:21.602Z https://www.opentrain.ai/papers/self-prompting-small-language-models-for-privacy-sensitive-clinical-information--arxiv-2605.04221/2026-06-18T22:48:45.146Z https://www.opentrain.ai/papers/frontier-lag-a-bibliometric-audit-of-capability-misrepresentation-in-academic-ai--arxiv-2605.04135/2026-06-18T23:08:54.633Z https://www.opentrain.ai/papers/rethinking-reasoning-intensive-retrieval-evaluating-and-advancing-retrievers-in--arxiv-2605.04018/2026-06-18T22:48:53.781Z https://www.opentrain.ai/papers/symptomai-towards-a-conversational-ai-agent-for-everyday-symptom-assessment--arxiv-2605.04012/2026-06-19T16:59:47.183Z https://www.opentrain.ai/papers/a-benchmark-for-interactive-world-models-with-a-unified-action-generation-framew--arxiv-2605.03941/2026-06-18T22:49:14.636Z https://www.opentrain.ai/papers/the-counterexample-game-iterated-conceptual-analysis-and-repair-in-language-mode--arxiv-2605.03936/2026-06-18T10:51:29.110Z https://www.opentrain.ai/papers/reproducing-complex-set-compositional-information-retrieval--arxiv-2605.03824/2026-06-18T23:08:50.935Z https://www.opentrain.ai/papers/patre-a-full-stage-office-action-and-rebuttal-generation-benchmark-for-patent-ex--arxiv-2605.03571/2026-06-19T13:12:42.555Z https://www.opentrain.ai/papers/skcc-portable-and-secure-skill-compilation-for-cross-framework-llm-agents--arxiv-2605.03353/2026-06-18T22:56:47.683Z https://www.opentrain.ai/papers/adapts-agentic-decomposition-for-automated-protocol-agnostic-tracking-of-symptom--arxiv-2605.03212/2026-06-18T21:51:47.009Z https://www.opentrain.ai/papers/aris-autonomous-research-via-adversarial-multi-agent-collaboration--arxiv-2605.03042/2026-06-19T16:59:18.389Z https://www.opentrain.ai/papers/heavyskill-heavy-thinking-as-the-inner-skill-in-agentic-harness--arxiv-2605.02396/2026-06-19T16:58:43.020Z https://www.opentrain.ai/papers/distilling-long-cot-reasoning-through-collaborative-step-wise-multi-teacher-deco--arxiv-2605.02290/2026-06-19T16:20:18.586Z https://www.opentrain.ai/papers/physicianbench-evaluating-llm-agents-in-real-world-ehr-environments--arxiv-2605.02240/2026-06-20T07:10:45.618Z https://www.opentrain.ai/papers/perturbation-dose-responses-in-recursive-llm-loops-raw-switching-stochastic-floo--arxiv-2605.02236/2026-06-19T16:57:26.340Z https://www.opentrain.ai/papers/generative-modeling-with-orbit-space-particle-flow-matching--arxiv-2605.02222/2026-06-19T16:59:17.327Z https://www.opentrain.ai/papers/t-2-po-uncertainty-guided-exploration-control-for-stable-multi-turn-agentic-rein--arxiv-2605.02178/2026-06-18T08:02:44.602Z https://www.opentrain.ai/papers/video-generation-with-predictive-latents--arxiv-2605.02134/2026-06-19T16:59:31.381Z https://www.opentrain.ai/papers/hallucinations-undermine-trust-metacognition-is-a-way-forward--arxiv-2605.01428/2026-06-19T16:59:20.683Z https://www.opentrain.ai/papers/tt4d-a-pipeline-and-dataset-for-table-tennis-4d-reconstruction-from-monocular-vi--arxiv-2605.01234/2026-06-18T22:59:19.024Z https://www.opentrain.ai/papers/agentic-ai-systems-should-be-designed-as-marginal-token-allocators--arxiv-2605.01214/2026-06-19T16:58:42.926Z https://www.opentrain.ai/papers/wildtablebench-benchmarking-multimodal-foundation-models-on-table-understanding--arxiv-2605.01018/2026-06-19T14:20:47.136Z https://www.opentrain.ai/papers/lase-language-adversarial-speaker-encoding-for-indic-cross-script-identity-prese--arxiv-2605.00777/2026-06-18T22:46:12.313Z https://www.opentrain.ai/papers/medmosaic-a-challenging-large-scale-benchmark-of-diverse-medical-audio--arxiv-2605.00969/2026-06-19T16:58:49.056Z https://www.opentrain.ai/papers/blenderrag-high-fidelity-3d-object-generation-via-retrieval-augmented-code-synth--arxiv-2605.00632/2026-06-19T23:30:17.214Z https://www.opentrain.ai/papers/learning-while-deploying-fleet-scale-reinforcement-learning-for-generalist-robot--arxiv-2605.00416/2026-06-19T16:58:33.061Z https://www.opentrain.ai/papers/trees-to-flows-and-back-unifying-decision-trees-and-diffusion-models--arxiv-2605.00414/2026-06-18T07:58:14.430Z https://www.opentrain.ai/papers/towards-customized-multimodal-role-play--arxiv-2605.08129/2026-06-18T23:04:14.742Z https://www.opentrain.ai/papers/cgm-jepa-learning-consistent-continuous-glucose-monitor-representations-via-pred--arxiv-2605.00933/2026-06-18T22:59:33.680Z https://www.opentrain.ai/papers/online-self-calibration-against-hallucination-in-vision-language-models--arxiv-2605.00323/2026-06-19T14:34:26.525Z https://www.opentrain.ai/papers/code-world-model-preparedness-report--arxiv-2605.00932/2026-06-19T14:23:00.152Z https://www.opentrain.ai/papers/linking-spatial-biology-and-clinical-histology-via-haiku--arxiv-2605.00925/2026-06-18T22:49:12.988Z https://www.opentrain.ai/papers/representation-frechet-loss-for-visual-generation--arxiv-2604.28190/2026-06-18T23:08:47.679Z https://www.opentrain.ai/papers/synthetic-computers-at-scale-for-long-horizon-productivity-simulation--arxiv-2604.28181/2026-06-19T16:57:51.280Z https://www.opentrain.ai/papers/intern-atlas-a-methodological-evolution-graph-as-research-infrastructure-for-ai--arxiv-2604.28158/2026-06-18T22:57:15.520Z https://www.opentrain.ai/papers/mocapanything-v2-end-to-end-motion-capture-for-arbitrary-skeletons--arxiv-2604.28130/2026-06-18T22:58:08.982Z https://www.opentrain.ai/papers/beyond-sft-to-rl-pre-alignment-via-black-box-on-policy-distillation-for-multimod--arxiv-2604.28123/2026-06-19T16:58:45.209Z https://www.opentrain.ai/papers/world-model-for-robot-learning-a-comprehensive-survey--arxiv-2605.00080/2026-06-19T14:23:38.991Z https://www.opentrain.ai/papers/windowsworld-a-process-centric-benchmark-of-autonomous-gui-agents-in-professiona--arxiv-2604.27776/2026-06-18T23:03:54.711Z https://www.opentrain.ai/papers/heterogeneous-scientific-foundation-model-collaboration--arxiv-2604.27351/2026-06-18T23:01:03.435Z https://www.opentrain.ai/papers/step-level-optimization-for-efficient-computer-use-agents--arxiv-2604.27151/2026-06-18T23:03:25.588Z https://www.opentrain.ai/papers/length-value-model-scalable-value-pretraining-for-token-level-length-modeling--arxiv-2604.27039/2026-06-19T16:58:39.300Z https://www.opentrain.ai/papers/accelerating-rl-post-training-rollouts-via-system-integrated-speculative-decodin--arxiv-2604.26779/2026-06-19T22:11:13.000Z https://www.opentrain.ai/papers/fash-icnn-making-editorial-fashion-identity-inspectable-through-multimodal-cnn-p--arxiv-2604.26186/2026-06-18T23:12:13.141Z https://www.opentrain.ai/papers/operating-layer-controls-for-onchain-language-model-agents-under-real-capital--arxiv-2604.26091/2026-06-19T14:49:48.556Z https://www.opentrain.ai/papers/dv-world-benchmarking-data-visualization-agents-in-real-world-scenarios--arxiv-2604.25914/2026-06-18T22:46:14.356Z https://www.opentrain.ai/papers/how-fast-should-a-model-commit-to-supervision-training-reasoning-models-on-the-t--arxiv-2604.25907/2026-06-18T23:04:14.689Z https://www.opentrain.ai/papers/mutual-forcing-dual-mode-self-evolution-for-fast-autoregressive-audio-video-char--arxiv-2604.25819/2026-06-19T16:59:24.781Z https://www.opentrain.ai/papers/maic-ui-making-interactive-courseware-with-generative-ui--arxiv-2604.25806/2026-06-18T02:38:37.094Z https://www.opentrain.ai/papers/kinder-a-physical-reasoning-benchmark-for-robot-learning-and-planning--arxiv-2604.25788/2026-06-18T23:05:36.087Z https://www.opentrain.ai/papers/psp-an-interpretable-per-dimension-accent-benchmark-for-indic-text-to-speech--arxiv-2604.25476/2026-06-19T16:58:32.249Z https://www.opentrain.ai/papers/r-3-sql-ranking-reward-and-resampling-for-text-to-sql--arxiv-2604.25325/2026-06-18T22:44:29.018Z https://www.opentrain.ai/papers/barred-synthetic-training-of-custom-policy-guardrails-via-asymmetric-debate--arxiv-2604.25203/2026-06-19T16:57:19.709Z https://www.opentrain.ai/papers/iam-identity-aware-human-motion-and-shape-joint-generation--arxiv-2604.25164/2026-06-18T22:57:02.245Z https://www.opentrain.ai/papers/vipo-visual-preference-optimization-at-scale--arxiv-2604.24953/2026-06-19T15:03:42.320Z https://www.opentrain.ai/papers/learning-from-noisy-preferences-a-semi-supervised-learning-approach-to-direct-pr--arxiv-2604.24952/2026-06-18T22:55:22.690Z https://www.opentrain.ai/papers/co-director-agentic-generative-video-storytelling--arxiv-2604.24842/2026-06-19T16:57:57.807Z https://www.opentrain.ai/papers/autogui-v2-a-comprehensive-multi-modal-gui-functionality-understanding-benchmark--arxiv-2604.24441/2026-06-19T16:59:10.879Z https://www.opentrain.ai/papers/diffusion-templates-a-unified-plugin-framework-for-controllable-diffusion--arxiv-2604.24351/2026-06-19T15:21:24.533Z https://www.opentrain.ai/papers/revsi-rebuilding-visual-spatial-intelligence-evaluation-for-accurate-assessment--arxiv-2604.24300/2026-06-19T15:22:25.921Z https://www.opentrain.ai/papers/muss-a-large-scale-dataset-and-cinematic-narrative-benchmark-for-multi-shot-subj--arxiv-2604.23789/2026-06-19T16:58:19.131Z https://www.opentrain.ai/papers/clawmark-a-living-world-benchmark-for-multi-turn-multi-day-multimodal-coworker-a--arxiv-2604.23781/2026-06-19T14:19:28.351Z https://www.opentrain.ai/papers/vision-language-action-safety-threats-challenges-evaluations-and-mechanisms--arxiv-2604.23775/2026-06-19T16:58:14.620Z https://www.opentrain.ai/papers/analogretriever-learning-cross-modal-representations-for-analog-circuit-retrieva--arxiv-2604.23195/2026-06-18T23:01:44.000Z https://www.opentrain.ai/papers/proeval-proactive-failure-discovery-and-efficient-performance-estimation-for-gen--arxiv-2604.23099/2026-06-20T08:17:20.566Z https://www.opentrain.ai/papers/code-broker-a-multi-agent-system-for-automated-code-quality-assessment--arxiv-2604.23088/2026-06-19T16:20:25.619Z https://www.opentrain.ai/papers/representational-harms-in-llm-generated-narratives-against-global-majority-natio--arxiv-2604.22749/2026-06-18T23:04:25.721Z https://www.opentrain.ai/papers/agentic-world-modeling-foundations-capabilities-laws-and-beyond--arxiv-2604.22748/2026-06-20T05:39:55.789Z https://www.opentrain.ai/papers/rethinking-xai-evaluation-a-human-centered-audit-of-shapley-benchmarks-in-high-s--arxiv-2604.22662/2026-06-18T07:01:53.812Z https://www.opentrain.ai/papers/from-graphemic-dependence-to-lexical-structure-a-markovian-perspective-on-dante--arxiv-2604.22626/2026-06-18T23:07:19.117Z https://www.opentrain.ai/papers/flowanchor-stabilizing-the-editing-signal-for-inversion-free-video-editing--arxiv-2604.22586/2026-06-20T03:52:40.142Z https://www.opentrain.ai/papers/quantclaw-precision-where-it-matters-for-openclaw--arxiv-2604.22577/2026-06-18T14:18:55.478Z https://www.opentrain.ai/papers/data-free-contribution-estimation-in-federated-learning-using-gradient-von-neuma--arxiv-2604.22562/2026-06-19T13:40:26.001Z https://www.opentrain.ai/papers/cross-stage-coherence-in-hierarchical-driving-vqa-explicit-baselines-and-learned--arxiv-2604.22560/2026-06-18T23:09:34.256Z https://www.opentrain.ai/papers/armssl-adversarial-robust-black-box-watermarking-for-self-supervised-learning-pr--arxiv-2604.22550/2026-06-19T15:24:00.173Z https://www.opentrain.ai/papers/superminds-test-actively-evaluating-collective-intelligence-of-agent-society-via--arxiv-2604.22452/2026-06-19T13:40:34.916Z https://www.opentrain.ai/papers/from-skills-to-talent-organising-heterogeneous-agents-as-a-real-world-company--arxiv-2604.22446/2026-06-18T16:23:38.397Z https://www.opentrain.ai/papers/cognitivetwin-robust-multi-modal-digital-twins-for-predicting-cognitive-decline--arxiv-2604.22428/2026-06-18T12:42:03.153Z https://www.opentrain.ai/papers/from-local-to-cluster-a-unified-framework-for-causal-discovery-with-latent-varia--arxiv-2604.22416/2026-06-18T11:52:49.066Z https://www.opentrain.ai/papers/contexts-are-never-long-enough-structured-reasoning-for-scalable-question-answer--arxiv-2604.22294/2026-06-18T15:04:58.182Z https://www.opentrain.ai/papers/stem-structure-tracing-evidence-mining-for-knowledge-graphs-driven-retrieval-aug--arxiv-2604.22282/2026-06-18T13:03:16.011Z https://www.opentrain.ai/papers/navigating-large-scale-document-collections-mudabench-for-multi-document-analyti--arxiv-2604.22239/2026-06-19T20:17:52.479Z https://www.opentrain.ai/papers/preserve-support-not-correspondence-dynamic-routing-for-offline-reinforcement-le--arxiv-2604.22229/2026-06-19T17:14:18.887Z https://www.opentrain.ai/papers/a-co-evolutionary-theory-of-human-ai-coexistence-mutualism-governance-and-dynami--arxiv-2604.22227/2026-06-18T08:05:04.261Z https://www.opentrain.ai/papers/an-llm-driven-closed-loop-autonomous-learning-framework-for-robots-facing-uncove--arxiv-2604.22199/2026-06-18T12:34:00.481Z https://www.opentrain.ai/papers/reliable-self-harm-risk-screening-via-adaptive-multi-agent-llm-systems--arxiv-2604.22154/2026-06-20T01:33:19.556Z https://www.opentrain.ai/papers/removing-sandbagging-in-llms-by-training-with-weak-supervision--arxiv-2604.22082/2026-06-18T22:57:53.939Z https://www.opentrain.ai/papers/sound-agentic-science-requires-adversarial-experiments--arxiv-2604.22080/2026-06-18T07:58:16.525Z https://www.opentrain.ai/papers/layerboost-layer-aware-attention-reduction-for-efficient-llms--arxiv-2604.22050/2026-06-18T12:35:44.028Z https://www.opentrain.ai/papers/source-modality-monitoring-in-vision-language-models--arxiv-2604.22038/2026-06-19T09:13:44.609Z https://www.opentrain.ai/papers/probing-visual-planning-in-image-editing-models--arxiv-2604.22868/2026-06-19T15:41:54.040Z https://www.opentrain.ai/papers/universal-transformers-need-memory-depth-state-trade-offs-in-adaptive-recursive--arxiv-2604.21999/2026-06-20T08:45:26.667Z https://www.opentrain.ai/papers/soft-anisotropic-diagrams-for-differentiable-image-representation--arxiv-2604.21984/2026-06-18T09:42:17.647Z https://www.opentrain.ai/papers/seeing-fast-and-slow-learning-the-flow-of-time-in-videos--arxiv-2604.21931/2026-06-18T03:14:37.027Z https://www.opentrain.ai/papers/unigendet-a-unified-generative-discriminative-framework-for-co-evolutionary-imag--arxiv-2604.21904/2026-06-18T08:42:53.543Z https://www.opentrain.ai/papers/worldmark-a-unified-benchmark-suite-for-interactive-video-world-models--arxiv-2604.21686/2026-06-18T08:22:12.398Z https://www.opentrain.ai/papers/seeing-isn-t-believing-uncovering-blind-spots-in-evaluator-vision-language-model--arxiv-2604.21523/2026-06-18T12:45:36.870Z https://www.opentrain.ai/papers/vlaa-gui-knowing-when-to-stop-recover-and-search-a-modular-framework-for-gui-aut--arxiv-2604.21375/2026-06-20T03:33:30.750Z https://www.opentrain.ai/papers/cross-entropy-is-load-bearing-a-pre-registered-scope-test-of-the-k-way-energy-pr--arxiv-2604.21286/2026-06-18T22:54:24.032Z https://www.opentrain.ai/papers/cross-session-threats-in-ai-agents-benchmark-evaluation-and-algorithms--arxiv-2604.21131/2026-06-19T19:19:58.969Z https://www.opentrain.ai/papers/weighting-what-matters-boosting-sample-efficiency-in-medical-report-generation-v--arxiv-2604.21082/2026-06-18T23:10:12.357Z https://www.opentrain.ai/papers/traces-tagging-reasoning-steps-for-adaptive-cost-efficient-early-stopping--arxiv-2604.21057/2026-06-18T23:06:39.562Z https://www.opentrain.ai/papers/the-last-harness-you-ll-ever-build--arxiv-2604.21003/2026-06-20T06:35:33.687Z https://www.opentrain.ai/papers/devi-physics-based-dexterous-human-object-interaction-via-synthetic-video-imitat--arxiv-2604.20841/2026-06-18T23:07:23.298Z https://www.opentrain.ai/papers/swe-chat-coding-agent-interactions-from-real-users-in-the-wild--arxiv-2604.20779/2026-06-19T18:23:20.694Z https://www.opentrain.ai/papers/ask-only-when-needed-proactive-retrieval-from-memory-and-skills-for-experience-d--arxiv-2604.20572/2026-06-18T16:38:23.198Z https://www.opentrain.ai/papers/momo-a-framework-for-seamless-physical-verbal-and-graphical-robot-skill-learning--arxiv-2604.20468/2026-06-18T16:37:57.218Z https://www.opentrain.ai/papers/medskillaudit-a-domain-specific-audit-framework-for-medical-research-agent-skill--arxiv-2604.20441/2026-06-18T08:01:37.541Z https://www.opentrain.ai/papers/building-a-precise-video-language-with-human-ai-oversight--arxiv-2604.21718/2026-06-19T22:54:16.835Z https://www.opentrain.ai/papers/cortex-2-0-grounding-world-models-in-real-world-industrial-deployment--arxiv-2604.20246/2026-06-18T12:35:26.356Z https://www.opentrain.ai/papers/unit-toward-a-unified-physical-language-for-human-to-humanoid-policy-learning-an--arxiv-2604.19734/2026-06-18T08:04:15.388Z https://www.opentrain.ai/papers/taming-actor-observer-asymmetry-in-agents-via-dialectical-alignment--arxiv-2604.19548/2026-06-18T16:35:24.255Z https://www.opentrain.ai/papers/attn-fiqa-interpretable-attention-based-face-image-quality-assessment-with-visio--arxiv-2604.22841/2026-06-18T08:01:08.773Z https://www.opentrain.ai/papers/does-self-consistency-improve-the-recall-of-encyclopedic-knowledge--arxiv-2604.19395/2026-06-18T16:26:25.099Z https://www.opentrain.ai/papers/tempo-scaling-test-time-training-for-large-reasoning-models--arxiv-2604.19295/2026-06-19T19:12:14.657Z https://www.opentrain.ai/papers/clawnet-human-symbiotic-agent-network-for-cross-user-autonomous-cooperation--arxiv-2604.19211/2026-06-19T19:20:52.583Z https://www.opentrain.ai/papers/multiworld-scalable-multi-agent-multi-view-video-world-models--arxiv-2604.18564/2026-06-18T14:18:51.874Z https://www.opentrain.ai/papers/clawenvkit-automatic-environment-generation-for-claw-like-agents--arxiv-2604.18543/2026-06-19T17:39:51.144Z https://www.opentrain.ai/papers/onevl-one-step-latent-reasoning-and-planning-with-vision-language-explanation--arxiv-2604.18486/2026-06-19T21:16:12.132Z https://www.opentrain.ai/papers/marco-navigating-the-unseen-space-of-semantic-correspondence--arxiv-2604.18267/2026-06-18T16:27:30.926Z https://www.opentrain.ai/papers/mitigating-multimodal-hallucination-via-phase-wise-self-reward--arxiv-2604.17982/2026-06-18T08:55:28.295Z https://www.opentrain.ai/papers/modeling-multiple-support-strategies-within-a-single-turn-for-emotional-support--arxiv-2604.17972/2026-06-18T09:50:55.162Z https://www.opentrain.ai/papers/latent-preference-modeling-for-cross-session-personalized-tool-calling--arxiv-2604.17886/2026-06-18T14:19:29.840Z https://www.opentrain.ai/papers/grasp-graph-structured-skill-compositions-for-llm-agents--arxiv-2604.17870/2026-06-18T12:35:14.780Z https://www.opentrain.ai/papers/answer-only-as-precisely-as-justified-calibrated-claim-level-specificity-control--arxiv-2604.17487/2026-06-18T22:43:56.120Z https://www.opentrain.ai/papers/unimesh-unifying-3d-mesh-understanding-and-generation--arxiv-2604.17472/2026-06-19T19:46:20.012Z https://www.opentrain.ai/papers/skillflow-benchmarking-lifelong-skill-discovery-and-evolution-for-autonomous-age--arxiv-2604.17308/2026-06-18T11:54:18.437Z https://www.opentrain.ai/papers/the-continuity-layer-why-intelligence-needs-an-architecture-for-what-it-carries--arxiv-2604.17273/2026-06-20T06:51:13.838Z https://www.opentrain.ai/papers/bolzano-case-studies-in-llm-assisted-mathematical-research--arxiv-2604.16989/2026-06-20T06:41:16.570Z https://www.opentrain.ai/papers/the-cognitive-penalty-ablating-system-1-and-system-2-reasoning-in-edge-native-sl--arxiv-2604.16913/2026-06-20T06:55:55.770Z https://www.opentrain.ai/papers/crowded-in-b-space-calibrating-shared-directions-for-lora-merging--arxiv-2604.16826/2026-06-20T06:54:49.911Z https://www.opentrain.ai/papers/benign-fine-tuning-breaks-safety-alignment-in-audio-llms--arxiv-2604.16659/2026-06-19T19:46:15.730Z https://www.opentrain.ai/papers/revisiting-a-pain-in-the-neck-a-semantic-reasoning-benchmark-for-language-models--arxiv-2604.16593/2026-06-20T06:50:52.900Z https://www.opentrain.ai/papers/chain-of-thought-degrades-visual-spatial-reasoning-capabilities-of-multimodal-ll--arxiv-2604.16060/2026-06-20T06:40:47.526Z https://www.opentrain.ai/papers/elucidating-the-snr-t-bias-of-diffusion-probabilistic-models--arxiv-2604.16044/2026-06-20T00:32:21.107Z https://www.opentrain.ai/papers/cut-your-losses-learning-to-prune-paths-early-for-efficient-parallel-reasoning--arxiv-2604.16029/2026-06-20T06:55:17.562Z https://www.opentrain.ai/papers/where-does-output-diversity-collapse-in-post-training--arxiv-2604.16027/2026-06-20T05:33:50.694Z https://www.opentrain.ai/papers/voxmind-an-end-to-end-agentic-spoken-dialogue-system--arxiv-2604.15710/2026-04-22T03:33:42.733Z https://www.opentrain.ai/papers/stargazer-a-scalable-model-fitting-benchmark-environment-for-ai-agents-under-ast--arxiv-2604.15664/2026-06-19T04:43:23.351Z https://www.opentrain.ai/papers/symbolic-guardrails-for-domain-specific-agents-stronger-safety-and-security-guar--arxiv-2604.15579/2026-06-19T20:44:24.855Z https://www.opentrain.ai/papers/1d-ordered-tokens-enable-efficient-test-time-search--arxiv-2604.15453/2026-06-20T06:40:51.582Z https://www.opentrain.ai/papers/leapalign-post-training-flow-matching-models-at-any-generation-step-by-building--arxiv-2604.15311/2026-06-19T21:53:53.304Z https://www.opentrain.ai/papers/globalsplat-efficient-feed-forward-3d-gaussian-splatting-via-global-scene-tokens--arxiv-2604.15284/2026-06-19T22:30:36.347Z https://www.opentrain.ai/papers/prism-symbolic-superoptimization-of-tensor-programs--arxiv-2604.15272/2026-06-20T06:45:17.434Z https://www.opentrain.ai/papers/coopeval-benchmarking-cooperation-sustaining-mechanisms-and-llm-agents-in-social--arxiv-2604.15267/2026-06-20T06:38:17.303Z https://www.opentrain.ai/papers/agentic-microphysics-a-manifesto-for-generative-ai-safety--arxiv-2604.15236/2026-06-20T06:42:17.132Z https://www.opentrain.ai/papers/blue-data-intelligence-layer-streaming-data-and-agents-for-multi-source-multi-mo--arxiv-2604.15233/2026-06-20T06:54:16.855Z https://www.opentrain.ai/papers/radagent-a-tool-using-ai-agent-for-stepwise-interpretation-of-chest-computed-tom--arxiv-2604.15231/2026-06-20T06:54:19.786Z https://www.opentrain.ai/papers/context-over-content-exposing-evaluation-faking-in-automated-judges--arxiv-2604.15224/2026-06-18T12:55:32.128Z https://www.opentrain.ai/papers/ai-assisted-requirements-engineering-an-empirical-evaluation-relative-to-expert--arxiv-2604.15222/2026-06-20T06:42:25.387Z https://www.opentrain.ai/papers/learning-to-think-like-a-cartoon-captionist-incongruity-resolution-supervision-f--arxiv-2604.15210/2026-06-19T19:17:14.810Z https://www.opentrain.ai/papers/benchmarking-classical-coverage-path-planning-heuristics-on-irregular-hexagonal--arxiv-2604.15202/2026-06-20T06:51:25.362Z https://www.opentrain.ai/papers/meituan-merchant-business-diagnosis-via-policy-guided-dual-process-user-simulati--arxiv-2604.15190/2026-06-18T12:42:31.654Z https://www.opentrain.ai/papers/prl-bench-a-comprehensive-benchmark-evaluating-llms-capabilities-in-frontier-phy--arxiv-2604.15411/2026-06-18T11:51:24.296Z https://www.opentrain.ai/papers/vispco-visual-token-pruning-configuration-optimization-via-budget-aware-pareto-f--arxiv-2604.15188/2026-06-20T06:54:42.237Z https://www.opentrain.ai/papers/agent-aided-design-for-dynamic-cad-models--arxiv-2604.15184/2026-06-20T06:52:09.567Z