https://www.opentrain.ai/papers/flashmemory-deepseek-v4-lightning-index-ultra-long-context-via-lookahead-sparse--arxiv-2606.09079/2026-06-09T04:12:49.560Z https://www.opentrain.ai/papers/beyond-scalar-rewards-by-internalizing-reasoning-into-score-distributions--arxiv-2606.09076/2026-06-11T02:47:07.304Z https://www.opentrain.ai/papers/hardening-agent-benchmarks-with-adversarial-hacker-fixer-loops--arxiv-2606.08960/2026-06-09T10:16:33.401Z https://www.opentrain.ai/papers/allospatial-agentic-harness-framework-for-spatial-reasoning-in-foundation-models--arxiv-2606.08952/2026-06-15T11:50:25.378Z https://www.opentrain.ai/papers/papermentor-a-human-centered-multi-agent-writing-tutor-for-ai-research-papers-on--arxiv-2606.08857/2026-06-10T20:43:53.695Z https://www.opentrain.ai/papers/pipe-cypher-automatic-enterprise-benchmark-generation-for-text-to-cypher-systems--arxiv-2606.08481/2026-06-09T05:29:29.389Z https://www.opentrain.ai/papers/bayesian-agent-posterior-guided-skill-evolution-for-llm-agent-harnesses--arxiv-2606.08348/2026-06-09T04:12:49.451Z https://www.opentrain.ai/papers/light-wam-efficient-world-action-models-with-state-fusion-action-decoding--arxiv-2606.08242/2026-06-09T14:32:34.409Z https://www.opentrain.ai/papers/mujoco-drones-gym-a-gpu-accelerated-multi-drone-simulator-for-control-and-reinfo--arxiv-2606.08039/2026-06-14T04:32:53.530Z https://www.opentrain.ai/papers/tbd-vla-temporal-block-diffusion-vision-language-action-model--arxiv-2606.07895/2026-06-09T02:48:40.729Z https://www.opentrain.ai/papers/the-cold-start-safety-gap-in-llm-agents--arxiv-2606.07867/2026-06-14T17:31:15.687Z https://www.opentrain.ai/papers/unisharp-universal-sharp-monocular-view-synthesis--arxiv-2606.07514/2026-06-08T04:33:45.842Z https://www.opentrain.ai/papers/streaming-video-generation-with-streaming-force-control--arxiv-2606.07508/2026-06-08T06:56:41.817Z https://www.opentrain.ai/papers/paperflow-profiling-recommending-and-adapting-across-daily-paper-streams--arxiv-2606.07454/2026-06-15T09:47:57.266Z https://www.opentrain.ai/papers/skill-3d-evolving-scene-aware-skills-for-agentic-3d-spatial-reasoning--arxiv-2606.07436/2026-06-09T13:50:40.248Z https://www.opentrain.ai/papers/socratic-swe-self-evolving-coding-agents-via-trace-derived-agent-skills--arxiv-2606.07412/2026-06-08T04:34:07.713Z https://www.opentrain.ai/papers/do-coding-agents-deceive-us-detecting-and-preventing-cheating-via-capped-evaluat--arxiv-2606.07379/2026-06-10T14:51:34.191Z https://www.opentrain.ai/papers/swe-explore-benchmarking-how-coding-agents-explore-repositories--arxiv-2606.07297/2026-06-09T02:39:32.501Z https://www.opentrain.ai/papers/dots-tts-technical-report--arxiv-2606.07080/2026-06-08T04:34:07.767Z https://www.opentrain.ai/papers/slimsearcher-training-efficiency-aware-web-agents-via-adaptive-reward-gating--arxiv-2606.07074/2026-06-09T10:16:27.123Z https://www.opentrain.ai/papers/empirical-study-on-the-characteristics-and-evolution-of-ai-usage-in-github-repos--arxiv-2606.06843/2026-06-08T21:35:30.744Z https://www.opentrain.ai/papers/regret-minimization-with-adaptive-opponents-in-repeated-games--arxiv-2606.06486/2026-06-08T04:35:30.714Z https://www.opentrain.ai/papers/thinking-with-imagination-agentic-visual-spatial-reasoning-with-world-simulators--arxiv-2606.06476/2026-06-08T04:33:18.278Z https://www.opentrain.ai/papers/latentskill-from-in-context-textual-skills-to-in-weight-latent-skills-for-llm-ag--arxiv-2606.06087/2026-06-09T07:32:57.418Z https://www.opentrain.ai/papers/memory-is-reconstructed-not-retrieved-graph-memory-for-llm-agents--arxiv-2606.06036/2026-06-15T02:43:41.846Z https://www.opentrain.ai/papers/oprd-on-policy-representation-distillation--arxiv-2606.06021/2026-06-05T02:54:57.620Z https://www.opentrain.ai/papers/robots-need-more-than-vla-and-world-models--arxiv-2606.06556/2026-06-08T11:56:24.774Z https://www.opentrain.ai/papers/when-tools-fail-benchmarking-dynamic-replanning-and-anomaly-recovery-in-llm-agen--arxiv-2606.05806/2026-06-08T04:33:38.771Z https://www.opentrain.ai/papers/drift-a-residual-flow-adapter-for-decoding-continuous-outputs-in-vision-language--arxiv-2606.05758/2026-06-11T15:46:12.968Z https://www.opentrain.ai/papers/discrete-wam-unified-discrete-vision-action-token-editing-for-world-policy-learn--arxiv-2606.05645/2026-06-05T06:19:31.935Z https://www.opentrain.ai/papers/asyncwebrl-efficient-multi-step-rl-for-visual-web-agents--arxiv-2606.05597/2026-06-09T19:42:33.362Z https://www.opentrain.ai/papers/socrates-towards-reliable-automated-evaluation-of-proactive-llm-mediation-across--arxiv-2606.05563/2026-06-08T07:34:15.215Z https://www.opentrain.ai/papers/almieyar-oryx-bloombench-a-bilingual-multimodal-benchmark-for-cognitively-inform--arxiv-2606.05531/2026-06-08T21:37:37.497Z https://www.opentrain.ai/papers/agents-last-exam--arxiv-2606.05405/2026-06-09T19:42:33.816Z https://www.opentrain.ai/papers/personal-ai-agent-for-camera-roll-vqa--arxiv-2606.05275/2026-06-05T02:33:29.097Z https://www.opentrain.ai/papers/streaming-communication-in-multi-agent-reasoning--arxiv-2606.05158/2026-06-04T04:32:38.166Z https://www.opentrain.ai/papers/reinforcement-learning-from-rich-feedback-with-distributional-dagger--arxiv-2606.05152/2026-06-08T16:25:27.586Z https://www.opentrain.ai/papers/autolab-can-frontier-models-solve-long-horizon-auto-research-and-engineering-tas--arxiv-2606.05080/2026-06-04T05:36:55.387Z https://www.opentrain.ai/papers/dar-deontic-reasoning-with-agentic-harnesses--arxiv-2606.05009/2026-06-04T15:22:22.383Z https://www.opentrain.ai/papers/m-3-eval-multi-modal-memory-evaluation-through-cognitively-grounded-video-tasks--arxiv-2606.05008/2026-06-04T05:36:58.046Z https://www.opentrain.ai/papers/tide-proactive-multi-problem-discovery-via-template-guided-iteration--arxiv-2606.04743/2026-06-07T10:05:18.172Z https://www.opentrain.ai/papers/meshweaver-sparse-voxel-guided-surface-weaving-for-autoregressive-mesh-generatio--arxiv-2606.04688/2026-06-04T02:37:42.683Z https://www.opentrain.ai/papers/why-muon-outperforms-adam-a-curvature-perspective--arxiv-2606.04662/2026-06-09T05:00:32.960Z https://www.opentrain.ai/papers/geneb-why-genomic-models-are-hard-to-compare--arxiv-2606.04525/2026-06-08T11:56:29.778Z https://www.opentrain.ai/papers/mapagent-an-industrial-grade-agentic-framework-for-city-scale-lane-level-map-gen--arxiv-2606.04513/2026-06-04T05:39:27.949Z https://www.opentrain.ai/papers/the-meta-agent-challenge-are-current-agents-capable-of-autonomous-agent-developm--arxiv-2606.04455/2026-06-04T02:15:16.041Z https://www.opentrain.ai/papers/a-cookbook-of-3d-vision-data-learning-paradigms-and-application--arxiv-2606.04291/2026-06-08T21:35:34.125Z https://www.opentrain.ai/papers/maoam-unified-object-and-material-selection-with-vision-language-models--arxiv-2606.04880/2026-06-08T04:35:29.965Z https://www.opentrain.ai/papers/imaginative-perception-tokens-enhance-spatial-reasoning-in-multimodal-language-m--arxiv-2606.03988/2026-06-08T21:35:30.508Z https://www.opentrain.ai/papers/aad-1-asymmetric-adversarial-distillation-for-one-step-autoregressive-video-gene--arxiv-2606.03972/2026-06-04T05:04:14.878Z https://www.opentrain.ai/papers/thoughtfold-folding-reasoning-chains-via-introspective-preference-learning--arxiv-2606.03503/2026-06-04T05:36:57.311Z https://www.opentrain.ai/papers/token-budgets-an-empirical-catalog-of-63-llm-agent-budget-overrun-incidents-with--arxiv-2606.04056/2026-06-04T17:04:50.301Z https://www.opentrain.ai/papers/steady-forcing-balancing-spatial-persistence-and-motion-continuity-in-long-horiz--arxiv-2606.14732/2026-06-16T04:10:59.746Z https://www.opentrain.ai/papers/nvidia-omnidreams-real-time-generative-world-model-for-closed-loop-autonomous-ve--arxiv-2606.03159/2026-06-03T02:37:12.016Z https://www.opentrain.ai/papers/neural-networks-provably-learn-spectral-representations-for-group-composition--arxiv-2606.02993/2026-06-05T04:34:56.445Z https://www.opentrain.ai/papers/economy-of-minds-emerging-multi-agent-intelligence-with-economic-interactions--arxiv-2606.02859/2026-06-04T10:19:58.303Z https://www.opentrain.ai/papers/bench-evaluating-persona-sensitive-influencing-in-persuasive-dialogues--arxiv-2606.02754/2026-06-03T02:36:58.262Z https://www.opentrain.ai/papers/thinking-in-blender-staged-executable-inverse-graphics-with-vision-language-mode--arxiv-2606.02580/2026-06-02T04:26:34.846Z https://www.opentrain.ai/papers/skillharm-lifecycle-aware-skill-based-attacks-via-automated-construction--arxiv-2606.02540/2026-06-10T16:18:52.284Z https://www.opentrain.ai/papers/agentcl-toward-rigorous-evaluation-of-continual-learning-in-language-agents--arxiv-2606.02461/2026-06-04T02:15:15.668Z https://www.opentrain.ai/papers/harness-1-reinforcement-learning-for-search-agents-with-state-externalizing-harn--arxiv-2606.02373/2026-06-02T17:58:11.177Z https://www.opentrain.ai/papers/tvir-building-deep-research-agents-towards-text-visual-interleaved-report-genera--arxiv-2606.02320/2026-06-02T17:58:11.028Z https://www.opentrain.ai/papers/where-do-deep-research-agents-go-wrong-span-level-error-localization-in-agent-tr--arxiv-2606.02060/2026-06-04T02:41:46.379Z https://www.opentrain.ai/papers/mmg2skill-can-agents-distill-in-the-wild-guides-into-self-evolving-skills--arxiv-2606.01993/2026-06-04T02:41:47.240Z https://www.opentrain.ai/papers/automedbench-towards-medical-autoresearch-with-agentic-ai-models--arxiv-2606.01961/2026-06-03T12:54:56.775Z https://www.opentrain.ai/papers/platonicnav-unveiling-semantic-correspondence-in-navigation-with-platonic-topolo--arxiv-2606.01788/2026-06-03T02:39:12.820Z https://www.opentrain.ai/papers/harnessforge-joint-harness-and-policy-evolution-for-adaptive-agent-systems--arxiv-2606.01779/2026-06-08T08:02:10.416Z https://www.opentrain.ai/papers/adaptive-auto-harness-sustained-self-improvement-for-agentic-system-deployment-o--arxiv-2606.01770/2026-06-03T23:41:54.681Z https://www.opentrain.ai/papers/tron-targeted-rule-verifiable-online-environments-for-visual-reasoning-rl--arxiv-2606.01599/2026-06-03T12:54:41.848Z https://www.opentrain.ai/papers/multi-agent-computer-use--arxiv-2606.01533/2026-06-02T04:30:11.947Z https://www.opentrain.ai/papers/joint-agent-memory-and-exploration-learning-via-novelty-signals--arxiv-2606.01528/2026-06-02T05:05:44.963Z https://www.opentrain.ai/papers/omniopd-logit-free-on-policy-distillation-via-speculative-verification--arxiv-2606.01476/2026-06-03T23:41:51.425Z https://www.opentrain.ai/papers/an-enigma-of-artificial-reason-investigating-the-production-evaluation-gap-in-la--arxiv-2606.01462/2026-06-15T16:12:30.434Z https://www.opentrain.ai/papers/carve-certified-affordable-repair-of-vetoed-maneuvers-via-envelopes-for-interact--arxiv-2606.02641/2026-06-15T05:22:40.069Z https://www.opentrain.ai/papers/hakushobench-a-japanese-chart-and-table-vqa-benchmark-from-governmental-white-pa--arxiv-2606.01132/2026-06-02T04:27:08.318Z https://www.opentrain.ai/papers/3dcodebench-benchmarking-agentic-procedural-3d-modeling-via-code--arxiv-2606.01057/2026-06-02T04:37:53.477Z https://www.opentrain.ai/papers/trust-functions-near-lossless-weak-to-strong-generalization-by-learning-when-to--arxiv-2606.01000/2026-06-15T01:40:20.507Z https://www.opentrain.ai/papers/mbench-a-comprehensive-benchmark-on-memory-capability-for-video-world-models--arxiv-2606.00793/2026-06-15T03:31:38.384Z https://www.opentrain.ai/papers/confidence-adaptive-swiglu-for-mixture-of-experts--arxiv-2606.00761/2026-06-02T12:38:26.560Z https://www.opentrain.ai/papers/occ-rag-optimal-cognitive-core-for-faithful-question-answering--arxiv-2606.00683/2026-06-03T12:59:52.692Z https://www.opentrain.ai/papers/foresci-evaluating-llm-agents-for-forward-looking-ai-research-judgment--arxiv-2606.00644/2026-06-08T04:33:55.205Z https://www.opentrain.ai/papers/do-text-edits-generalize-to-visual-generation-benchmarking-cross-modal-knowledge--arxiv-2606.00477/2026-06-04T10:20:15.474Z https://www.opentrain.ai/papers/masking-stale-observations-helps-search-agents-until-it-doesn-t-a-regime-map-and--arxiv-2606.00408/2026-06-02T03:09:38.537Z https://www.opentrain.ai/papers/representation-forcing-for-bottleneck-free-unified-multimodal-models--arxiv-2605.31604/2026-06-01T02:37:18.624Z https://www.opentrain.ai/papers/soco-benchmarking-semantic-object-correspondence-in-vision-foundation-models--arxiv-2605.31597/2026-06-02T13:01:36.589Z https://www.opentrain.ai/papers/svi-bench-a-dynamic-microworld-for-strategic-video-intelligence--arxiv-2605.31529/2026-06-02T17:58:11.105Z https://www.opentrain.ai/papers/how-can-embedding-models-bind-concepts--arxiv-2605.31503/2026-06-01T14:38:31.987Z https://www.opentrain.ai/papers/scalable-inference-time-annealing-with-surrogate-likelihood-estimators--arxiv-2605.31498/2026-06-04T17:48:18.339Z https://www.opentrain.ai/papers/paintbench-deterministic-evaluation-of-precise-visual-editing--arxiv-2606.00188/2026-06-04T15:50:18.757Z https://www.opentrain.ai/papers/decmem-towards-minute-long-consistent-world-generation-with-decoupled-memory--arxiv-2605.31336/2026-06-01T10:17:29.831Z https://www.opentrain.ai/papers/emergent-languages-in-populations-of-language-model-agents-from-token-efficiency--arxiv-2605.31170/2026-06-01T10:17:34.097Z https://www.opentrain.ai/papers/trust-region-behavior-blending-for-on-policy-distillation--arxiv-2605.31159/2026-06-01T11:29:06.662Z https://www.opentrain.ai/papers/light-interaction-training-free-inference-acceleration-for-interactive-video-wor--arxiv-2605.31158/2026-06-01T02:39:08.081Z https://www.opentrain.ai/papers/spatialact-probing-spatial-reasoning-to-action-capabilities-of-vlm-agents-in-3d--arxiv-2605.31148/2026-06-04T15:13:44.929Z https://www.opentrain.ai/papers/task-focused-memorization-for-multimodal-agents--arxiv-2605.31075/2026-06-01T03:45:12.437Z https://www.opentrain.ai/papers/ggt-100k-generative-ground-truth-for-generalizable-real-world-image-restoration--arxiv-2605.31039/2026-06-01T02:37:11.725Z https://www.opentrain.ai/papers/peek-picking-essential-frames-via-efficient-knowledge-distillation--arxiv-2605.31029/2026-06-01T08:20:33.094Z https://www.opentrain.ai/papers/swanvoice-expressive-long-form-zero-shot-speech-synthesis-for-both-monologue-and--arxiv-2605.30993/2026-06-01T04:05:43.874Z https://www.opentrain.ai/papers/speculative-pipeline-decoding-higher-accruacy-and-zero-bubble-speculation-via-pi--arxiv-2605.30852/2026-06-02T02:47:32.484Z https://www.opentrain.ai/papers/llm-anonymization-against-agentic-re-identification--arxiv-2605.30848/2026-06-08T04:33:50.646Z https://www.opentrain.ai/papers/send-a-scout-first-pre-hoc-reasoning-for-adaptive-detector-allocation-in-prompt--arxiv-2605.30837/2026-06-10T04:32:52.049Z https://www.opentrain.ai/papers/smaller-models-are-natural-explorers-for-policy-level-diversity-in-grpo--arxiv-2605.30789/2026-06-15T04:46:02.331Z https://www.opentrain.ai/papers/crafter-a-multi-agent-harness-for-editable-scientific-figure-generation-from-div--arxiv-2605.30611/2026-06-02T02:47:48.806Z https://www.opentrain.ai/papers/semantic-motion-anchors-bridging-motion-and-meaning-in-co-speech-gestures--arxiv-2605.30608/2026-06-02T21:57:31.456Z https://www.opentrain.ai/papers/seeing-isn-t-knowing-do-vlms-know-when-not-to-answer-spatial-questions-and-why--arxiv-2605.30557/2026-06-01T05:32:28.759Z https://www.opentrain.ai/papers/maat-multi-phase-adapter-aware-targeted-unlearning--arxiv-2605.30514/2026-06-06T08:15:43.528Z https://www.opentrain.ai/papers/linear-ensembles-wash-away-watermarks-on-the-fragility-of-distributional-perturb--arxiv-2605.30501/2026-06-14T08:00:11.399Z https://www.opentrain.ai/papers/longds-bench-on-the-failure-of-long-horizon-agentic-data-analysis--arxiv-2605.30434/2026-06-01T02:08:18.025Z https://www.opentrain.ai/papers/dynaflip-rethinking-robotics-perception-via-tri-modal-dynamics-guided-representa--arxiv-2605.30350/2026-05-31T09:54:25.709Z https://www.opentrain.ai/papers/neurok-generative-4d-neural-object-kinematics--arxiv-2605.30347/2026-05-29T05:00:51.990Z https://www.opentrain.ai/papers/yocausal-how-far-is-video-generation-from-world-model-a-causality-perspective--arxiv-2605.30346/2026-05-29T05:00:33.342Z https://www.opentrain.ai/papers/locally-coherent-globally-incoherent-bounding-compositional-incoherence-in-multi--arxiv-2605.30335/2026-06-15T19:48:28.281Z https://www.opentrain.ai/papers/colored-noise-diffusion-sampling--arxiv-2605.30332/2026-05-31T09:54:30.993Z https://www.opentrain.ai/papers/resolution-diagnostics-for-paired-llm-evaluation--arxiv-2605.30315/2026-06-14T11:36:04.507Z https://www.opentrain.ai/papers/self-trained-verification-for-training-and-test-time-self-improvement--arxiv-2605.30290/2026-06-14T20:36:51.512Z https://www.opentrain.ai/papers/lomo-local-modality-substitution-for-deeper-vision-language-fusion--arxiv-2605.30265/2026-06-14T11:50:48.207Z https://www.opentrain.ai/papers/videofdb-evaluating-full-duplex-vision-speech-capabilities-in-conversational-age--arxiv-2605.30256/2026-06-12T21:18:22.822Z https://www.opentrain.ai/papers/genclaw-code-driven-agentic-image-generation--arxiv-2605.30248/2026-05-29T05:08:28.261Z https://www.opentrain.ai/papers/communityfact-a-dynamic-multilingual-multi-domain-benchmark-for-misinformation-d--arxiv-2605.30241/2026-06-15T19:49:16.312Z https://www.opentrain.ai/papers/researchclawbench-a-benchmark-for-end-to-end-autonomous-scientific-research--arxiv-2606.07591/2026-06-09T02:48:46.988Z https://www.opentrain.ai/papers/why-far-looks-up-probing-spatial-representation-in-vision-language-models--arxiv-2605.30161/2026-05-31T09:54:27.491Z https://www.opentrain.ai/papers/do-proactive-agents-really-need-an-llm-to-decide-when-to-wake-and-what-to-anchor--arxiv-2605.30152/2026-06-14T22:11:38.207Z https://www.opentrain.ai/papers/ccs-clinical-consensus-selection-for-radiology-report-generation--arxiv-2605.30131/2026-06-16T01:43:18.256Z https://www.opentrain.ai/papers/parcel-pool-anchored-resampling-with-conditioned-elastic-queries-for-efficient-v--arxiv-2605.30126/2026-06-16T01:44:26.151Z https://www.opentrain.ai/papers/directorbench-diagnosing-long-form-video-generation-with-personalized-multi-agen--arxiv-2605.30090/2026-06-14T09:47:36.116Z https://www.opentrain.ai/papers/multimodal-music-recommendation-system-using-llms--arxiv-2606.00125/2026-06-07T10:05:20.078Z https://www.opentrain.ai/papers/conformal-certification-of-reasoning-trace-prefixes--arxiv-2605.30085/2026-06-16T01:44:01.861Z https://www.opentrain.ai/papers/native-audio-visual-alignment-for-generation--arxiv-2605.30073/2026-05-29T02:21:59.308Z https://www.opentrain.ai/papers/heart-bench-do-llm-agents-exhibit-human-like-psychology--arxiv-2605.30058/2026-06-16T01:44:22.011Z https://www.opentrain.ai/papers/audio-jailbreaks-in-large-audio-language-models-taxonomy-attack-defense-analysis--arxiv-2605.30031/2026-06-15T21:25:42.290Z https://www.opentrain.ai/papers/discovering-cooperative-pipelines-autoresearch-for-sequential-social-dilemmas--arxiv-2605.30003/2026-05-31T09:54:33.240Z https://www.opentrain.ai/papers/adapting-multilingual-embedding-models-to-turkish-via-cross-lingual-tokenizer-su--arxiv-2605.29992/2026-06-16T01:44:13.057Z https://www.opentrain.ai/papers/mic-maximizing-informational-capacity-in-adaptive-representations-via-isotropic--arxiv-2605.29987/2026-06-15T20:08:47.482Z https://www.opentrain.ai/papers/muphi-learning-implicit-multimodal-harm-reasoning-via-semantically-grounded-rewa--arxiv-2605.29951/2026-06-16T03:01:42.322Z https://www.opentrain.ai/papers/does-the-way-you-plan-matter-an-empirical-study-of-planning-representations-for--arxiv-2605.29927/2026-06-14T13:25:45.397Z https://www.opentrain.ai/papers/nine-judges-two-effective-votes-correlated-errors-undermine-llm-evaluation-panel--arxiv-2605.29800/2026-06-11T21:50:31.327Z https://www.opentrain.ai/papers/ui-kobe-knowledge-oriented-behavior-exploration-for-lightweight-graph-guided-gui--arxiv-2605.29534/2026-05-29T05:09:04.717Z https://www.opentrain.ai/papers/xetrieval-mechanistically-explaining-dense-retrieval--arxiv-2605.29507/2026-05-31T15:30:24.749Z https://www.opentrain.ai/papers/anymo-scaling-any-modality-conditional-motion-generation-with-masked-modeling--arxiv-2605.29488/2026-06-01T04:26:45.421Z https://www.opentrain.ai/papers/honest-lying-understanding-memory-confabulation-in-reflexive-agents--arxiv-2605.29463/2026-06-09T05:29:42.458Z https://www.opentrain.ai/papers/recovering-policy-induced-errors-benchmarking-and-trajectory-synthesis-for-robus--arxiv-2605.29447/2026-06-01T09:50:48.366Z https://www.opentrain.ai/papers/learning-design-skills-as-memory-policies-for-agentic-photonic-inverse-design--arxiv-2605.29421/2026-06-15T14:00:34.495Z https://www.opentrain.ai/papers/revisiting-observation-reduction-for-web-agents-comprehensive-evaluation-with-a--arxiv-2605.29397/2026-06-10T07:43:43.377Z https://www.opentrain.ai/papers/offloading-score-measuring-ai-reliance-through-counterfactual-workflows--arxiv-2605.29392/2026-06-16T03:32:13.121Z https://www.opentrain.ai/papers/draft-opd-on-policy-distillation-for-speculative-draft-models--arxiv-2605.29343/2026-06-02T04:27:12.640Z https://www.opentrain.ai/papers/cohyde-iterative-co-training-of-llm-rewriter-dense-encoder-for-tool-retrieval--arxiv-2605.29271/2026-05-31T15:30:24.001Z https://www.opentrain.ai/papers/guidance-contrastive-token-credit-assignment-for-discrete-policy-optimization--arxiv-2605.29198/2026-06-01T16:55:09.614Z https://www.opentrain.ai/papers/the-chain-holds-the-answer-folds-trace-answer-dissociation-in-reasoning-models-u--arxiv-2605.29087/2026-06-02T16:33:21.211Z https://www.opentrain.ai/papers/frappe-full-input-residual-output-autoencoding-with-projection-pursuit-encoder--arxiv-2605.28992/2026-06-01T04:05:37.145Z https://www.opentrain.ai/papers/self-improving-language-models-with-bidirectional-evolutionary-search--arxiv-2605.28814/2026-05-28T02:42:38.676Z https://www.opentrain.ai/papers/learn-from-weaknesses-automated-domain-specialization-for-small-computer-use-age--arxiv-2605.28775/2026-05-28T02:54:32.628Z https://www.opentrain.ai/papers/agent-explorative-policy-optimization-for-multimodal-agentic-reasoning--arxiv-2605.28774/2026-05-28T02:42:38.681Z https://www.opentrain.ai/papers/cubepart-an-open-vocabulary-part-controllable-3d-generator--arxiv-2605.28763/2026-05-28T02:33:00.123Z https://www.opentrain.ai/papers/core-contrastive-reflection-enables-rapid-improvements-in-reasoning--arxiv-2605.28742/2026-06-08T21:35:36.455Z https://www.opentrain.ai/papers/autoscientists-self-organizing-agent-teams-for-long-running-scientific-experimen--arxiv-2605.28655/2026-05-28T02:33:51.450Z https://www.opentrain.ai/papers/lacuna-safe-agents-as-recursive-program-holes--arxiv-2605.28617/2026-05-28T21:40:17.997Z https://www.opentrain.ai/papers/compositional-text-to-image-generation-via-region-aware-bimodal-direct-preferenc--arxiv-2605.28615/2026-06-02T02:47:36.129Z https://www.opentrain.ai/papers/a-matter-of-taste-improving-coverage-and-difficulty-of-agent-benchmarks--arxiv-2605.28556/2026-06-02T07:38:41.445Z https://www.opentrain.ai/papers/gem-generative-supervision-helps-embodied-intelligence--arxiv-2605.28548/2026-05-28T04:06:05.216Z https://www.opentrain.ai/papers/review-arcade-on-the-human-alignment-and-gameability-of-llm-reviews--arxiv-2605.28897/2026-06-02T13:23:24.841Z https://www.opentrain.ai/papers/category-level-3d-correspondence-in-camera-space-via-morphable-object-priors--arxiv-2605.28257/2026-05-28T15:02:13.391Z https://www.opentrain.ai/papers/ai-take-the-wheel-what-drives-delegation-and-trust-in-human-computer-cooperative--arxiv-2605.28255/2026-06-02T13:01:33.269Z https://www.opentrain.ai/papers/which-pretraining-paradigm-better-serves-spatial-intelligence-an-empirical-compa--arxiv-2605.28132/2026-06-02T02:47:57.601Z https://www.opentrain.ai/papers/ask-now-use-later-benchmarking-the-proactivity-gap-in-long-lived-llm-agents--arxiv-2605.28108/2026-06-15T10:19:46.433Z https://www.opentrain.ai/papers/researchmath-14k-scaling-research-level-mathematics-via-agents--arxiv-2605.28003/2026-05-28T02:38:07.006Z https://www.opentrain.ai/papers/esc-skills-discovering-and-self-evolving-skills-for-emotional-support-conversati--arxiv-2605.27908/2026-05-28T06:24:41.942Z https://www.opentrain.ai/papers/peam-parametric-embodied-agent-memory-through-contrastive-internalization-of-exp--arxiv-2605.27762/2026-05-28T03:19:45.208Z https://www.opentrain.ai/papers/skillgrad-optimizing-agent-skills-like-gradient-descent--arxiv-2605.27760/2026-05-28T08:52:08.075Z https://www.opentrain.ai/papers/spatialbench-is-your-spatial-foundation-model-an-all-round-player--arxiv-2605.27367/2026-05-27T02:52:30.299Z https://www.opentrain.ai/papers/locateanything-fast-and-high-quality-vision-language-grounding-with-parallel-box--arxiv-2605.27365/2026-05-27T03:47:37.025Z https://www.opentrain.ai/papers/chartographer-counterfactual-chart-generation-for-evaluating-vision-language-mod--arxiv-2605.27311/2026-05-28T02:38:07.238Z https://www.opentrain.ai/papers/how-and-what-to-imagine-visual-thinking-in-unified-multimodal-models-for-cross-v--arxiv-2605.27310/2026-05-28T17:38:05.428Z https://www.opentrain.ai/papers/gemini-embedding-2-a-native-multimodal-embedding-model-from-gemini--arxiv-2605.27295/2026-05-27T10:20:10.042Z https://www.opentrain.ai/papers/less-is-more-early-stopping-rollout-for-on-policy-distillation--arxiv-2605.27028/2026-06-06T01:59:13.717Z https://www.opentrain.ai/papers/not-all-disagreement-is-learnable-token-teachability-in-on-policy-distillation--arxiv-2605.26844/2026-06-01T02:37:14.490Z https://www.opentrain.ai/papers/beyond-holistic-models-systematic-component-level-benchmarking-of-deep-multivari--arxiv-2605.26562/2026-06-01T11:29:06.531Z https://www.opentrain.ai/papers/verus-specgym-an-agentic-environment-for-evaluating-specification-autoformalizat--arxiv-2605.26457/2026-05-28T03:19:11.330Z https://www.opentrain.ai/papers/advancing-creative-physical-intelligence-in-large-multimodal-models--arxiv-2605.26396/2026-05-28T04:20:41.130Z https://www.opentrain.ai/papers/scientistone-towards-human-level-autonomous-research-via-chain-of-evidence--arxiv-2605.26340/2026-05-28T03:58:48.295Z https://www.opentrain.ai/papers/your-agents-are-aging-too-agent-lifespan-engineering-for-deployed-systems--arxiv-2605.26302/2026-05-28T16:58:57.487Z https://www.opentrain.ai/papers/longav-compass-towards-unified-evaluation-of-minute-scale-audio-visual-generatio--arxiv-2605.26244/2026-05-27T02:37:12.999Z https://www.opentrain.ai/papers/helix4d-complex-4d-mesh-generation--arxiv-2605.26109/2026-05-26T04:22:20.667Z https://www.opentrain.ai/papers/on-policy-adversarial-flow-distillation-for-autoregressive-video-generation--arxiv-2605.26105/2026-05-26T04:22:20.717Z https://www.opentrain.ai/papers/causalab-a-scalable-environment-for-interactive-causal-discovery-toward-ai-scien--arxiv-2605.26029/2026-05-29T05:08:28.574Z https://www.opentrain.ai/papers/sembridge-language-transfer-in-sparse-encoders-via-multilingual-semantic-bridges--arxiv-2605.26002/2026-05-26T04:23:00.350Z https://www.opentrain.ai/papers/wbench-a-comprehensive-multi-turn-benchmark-for-interactive-video-world-model-ev--arxiv-2605.25874/2026-05-26T04:22:53.170Z https://www.opentrain.ai/papers/rethinking-vlm-representation-for-vla-initialization--arxiv-2605.25802/2026-05-27T08:34:06.465Z https://www.opentrain.ai/papers/streamchar-long-horizon-streaming-character-audio-video-generation-with-decouple--arxiv-2605.25659/2026-06-02T02:47:21.537Z https://www.opentrain.ai/papers/controllight-towards-controllable-consistent-and-generalizable-low-light-enhance--arxiv-2605.25569/2026-05-26T04:22:33.628Z https://www.opentrain.ai/papers/does-seeing-more-mean-knowing-more-mono-anchored-advantage-normalization-for-mul--arxiv-2605.25437/2026-05-27T02:56:21.296Z https://www.opentrain.ai/papers/collectionlora-collecting-50-effects-in-1-lora-via-multi-teacher-on-policy-disti--arxiv-2605.25378/2026-05-29T05:04:42.597Z https://www.opentrain.ai/papers/toward-native-multimodal-modeling-a-roadmap--arxiv-2605.25343/2026-05-26T04:27:51.936Z https://www.opentrain.ai/papers/multi-view-consistent-3d-gaussian-head-avatars-without-multi-view-generation--arxiv-2605.25220/2026-05-31T15:32:53.206Z https://www.opentrain.ai/papers/darkforest-less-talk-higher-accuracy-for-multi-agent-llms--arxiv-2605.25188/2026-05-27T08:34:13.925Z https://www.opentrain.ai/papers/worldcraft-from-camera-navigation-to-object-manipulation-in-interactive-video-wo--arxiv-2605.25077/2026-06-09T13:50:41.408Z https://www.opentrain.ai/papers/your-embedding-model-is-smarter-than-you-think--arxiv-2605.24938/2026-05-26T02:43:16.048Z https://www.opentrain.ai/papers/pando-efficient-multimodal-ai-agents-via-online-skill-distillation--arxiv-2605.24785/2026-05-31T09:54:24.846Z https://www.opentrain.ai/papers/agentfugue-agent-scaling-for-long-horizon-tasks-through-collective-reasoning--arxiv-2605.24486/2026-05-28T06:31:36.549Z https://www.opentrain.ai/papers/benchmarking-composed-image-retrieval-for-applied-earth-observation--arxiv-2605.24442/2026-06-01T09:44:07.988Z https://www.opentrain.ai/papers/quest-training-frontier-deep-research-agents-with-fully-synthetic-tasks--arxiv-2605.24218/2026-05-26T07:12:30.242Z https://www.opentrain.ai/papers/spacenum-revisiting-spatial-numerical-understanding-in-vlms--arxiv-2605.23898/2026-06-08T16:25:27.756Z https://www.opentrain.ai/papers/from-activation-to-causality-discovery-of-causal-visual-representations-in-the-h--arxiv-2605.23895/2026-06-03T12:51:30.644Z https://www.opentrain.ai/papers/horizonstream-long-horizon-attention-for-streaming-3d-reconstruction--arxiv-2605.23889/2026-05-26T08:38:02.226Z https://www.opentrain.ai/papers/cronos-benchmarking-counterfactual-physical-consistency-in-video-models--arxiv-2605.23699/2026-05-26T08:38:26.054Z https://www.opentrain.ai/papers/one-forcing-towards-stable-one-step-autoregressive-video-generation--arxiv-2605.23458/2026-06-01T19:10:55.240Z https://www.opentrain.ai/papers/coloring-the-noise-adversarial-sobolev-alignment-for-faithful-image-super-resolu--arxiv-2605.23264/2026-05-26T07:59:27.002Z https://www.opentrain.ai/papers/foundation-protocol-a-coordination-layer-for-agentic-society--arxiv-2605.23218/2026-05-26T04:22:30.504Z https://www.opentrain.ai/papers/autoresearch-ai-towards-ai-powered-research-automation-for-scientific-discovery--arxiv-2605.23204/2026-05-26T02:43:16.041Z https://www.opentrain.ai/papers/emma-extracting-multiple-physical-parameters-from-multimodal-data--arxiv-2605.24047/2026-06-09T05:54:39.066Z https://www.opentrain.ai/papers/motimotion-motion-controlled-video-generation-with-visual-reasoning--arxiv-2605.22818/2026-05-27T02:52:37.537Z https://www.opentrain.ai/papers/evaluating-commercial-ai-chatbots-as-news-intermediaries--arxiv-2605.22785/2026-06-12T08:53:38.777Z https://www.opentrain.ai/papers/diversed-model-discovery-via-structured-table-discovery--arxiv-2605.22766/2026-05-22T06:16:27.757Z https://www.opentrain.ai/papers/the-distillation-game-adaptive-attacks-efficient-defenses--arxiv-2605.22737/2026-06-09T02:48:43.263Z https://www.opentrain.ai/papers/chronomedkg-a-temporally-grounded-biomedical-knowledge-graph-and-benchmark-for-c--arxiv-2605.22734/2026-06-14T17:14:32.469Z https://www.opentrain.ai/papers/live-music-diffusion-models-efficient-fine-tuning-and-post-training-of-interacti--arxiv-2605.22717/2026-05-25T01:04:19.753Z https://www.opentrain.ai/papers/terminalworld-benchmarking-agents-on-real-world-terminal-tasks--arxiv-2605.22535/2026-05-22T06:27:50.804Z https://www.opentrain.ai/papers/search-e1-self-distillation-drives-self-evolution-in-search-augmented-reasoning--arxiv-2605.22511/2026-06-15T21:29:34.645Z https://www.opentrain.ai/papers/reflecti-mate-a-conversational-agent-for-adaptive-decision-making-support-throug--arxiv-2605.22509/2026-06-16T06:06:56.310Z https://www.opentrain.ai/papers/pattern-and-root-inflectional-morphology-the-arabic-broken-plural--arxiv-2605.22310/2026-06-16T01:42:40.637Z https://www.opentrain.ai/papers/ghi-graphormer-over-conditioned-hypergraph-incidence-for-aspect-based-sentiment--arxiv-2605.22228/2026-06-16T01:43:50.190Z https://www.opentrain.ai/papers/do-factual-recall-mechanisms-carry-over-from-text-to-speech-in-multimodal-langua--arxiv-2605.22170/2026-06-16T01:43:24.347Z https://www.opentrain.ai/papers/one-sentence-one-drama-personalized-short-form-drama-generation-via-multi-agent--arxiv-2605.22144/2026-05-24T07:23:18.780Z https://www.opentrain.ai/papers/same-architecture-different-capacity-optimizer-induced-spectral-scaling-laws--arxiv-2605.21803/2026-05-22T06:47:20.811Z https://www.opentrain.ai/papers/genevolve-self-evolving-image-generation-agents-via-tool-orchestrated-visual-exp--arxiv-2605.21605/2026-05-24T07:07:25.527Z https://www.opentrain.ai/papers/lens-rethinking-training-efficiency-for-foundational-text-to-image-models--arxiv-2605.21573/2026-05-26T02:34:34.204Z https://www.opentrain.ai/papers/equilibrium-reasoners-learning-attractors-enables-scalable-reasoning--arxiv-2605.21488/2026-05-25T21:27:25.259Z https://www.opentrain.ai/papers/physx-omni-unified-simulation-ready-physical-3d-generation-for-rigid-deformable--arxiv-2605.21572/2026-05-24T06:41:26.652Z https://www.opentrain.ai/papers/specbench-measuring-reward-hacking-in-long-horizon-coding-agents--arxiv-2605.21384/2026-05-21T04:32:41.667Z https://www.opentrain.ai/papers/sciatlas-a-large-scale-knowledge-graph-for-automated-scientific-research--arxiv-2605.22878/2026-05-25T09:53:08.755Z https://www.opentrain.ai/papers/ranke-end-to-end-post-training-for-discrete-text-to-image-generation-with-decode--arxiv-2605.21195/2026-05-25T03:39:22.944Z https://www.opentrain.ai/papers/decoupling-communication-from-policy-robust-marl-under-bandwidth-constraints--arxiv-2605.21085/2026-05-26T12:54:28.529Z https://www.opentrain.ai/papers/flowlong-inference-time-long-video-generation-via-manifold-constrained-tweedie-m--arxiv-2605.20910/2026-05-22T06:46:58.245Z https://www.opentrain.ai/papers/conditional-equivalence-of-dpo-and-rlhf-implicit-assumption-failure-modes-and-pr--arxiv-2605.20834/2026-05-21T04:31:58.179Z https://www.opentrain.ai/papers/on-the-limits-and-opportunities-of-ai-reviewers-reviewing-the-reviews-of-nature--arxiv-2605.20668/2026-05-21T04:32:41.765Z https://www.opentrain.ai/papers/paravt-taming-the-tool-prior-paradox-for-parallel-tool-use-in-agentic-video-rein--arxiv-2605.20342/2026-05-26T04:23:06.928Z https://www.opentrain.ai/papers/not-every-rubric-teaches-equally-policy-aware-rubric-rewards-for-rlvr--arxiv-2605.20164/2026-05-20T22:41:07.297Z https://www.opentrain.ai/papers/draft-less-retrieve-more-hybrid-tree-construction-for-speculative-decoding--arxiv-2605.20104/2026-05-20T04:32:39.598Z https://www.opentrain.ai/papers/autoresearchclaw-self-reinforcing-autonomous-research-with-human-ai-collaboratio--arxiv-2605.20025/2026-05-20T04:32:32.031Z https://www.opentrain.ai/papers/rethinking-how-to-remember-beyond-atomic-facts-in-lifelong-llm-agent-memory--arxiv-2605.19952/2026-05-28T14:46:34.502Z https://www.opentrain.ai/papers/opencomputer-verifiable-software-worlds-for-computer-use-agents--arxiv-2605.19769/2026-05-20T04:32:31.168Z https://www.opentrain.ai/papers/oscar-the-occam-s-razor-for-extreme-kv-cache-quantization-in-llms-and-beyond--arxiv-2605.19660/2026-05-21T04:32:29.504Z https://www.opentrain.ai/papers/scenecode-executable-world-programs-for-editable-indoor-scenes-with-articulated--arxiv-2605.19587/2026-05-20T04:32:31.785Z https://www.opentrain.ai/papers/cutverse-a-compositional-gui-agents-benchmark-for-media-post-production-editing--arxiv-2605.19484/2026-05-21T15:35:40.325Z https://www.opentrain.ai/papers/generative-recursive-reasoning--arxiv-2605.19376/2026-05-21T04:33:08.699Z https://www.opentrain.ai/papers/next-acceleration-scale-prediction-for-autoregressive-mri-reconstruction--arxiv-2605.19354/2026-05-25T23:14:47.752Z https://www.opentrain.ai/papers/wavflow-audio-generation-in-waveform-space--arxiv-2605.18749/2026-05-19T21:32:50.530Z https://www.opentrain.ai/papers/dexholdem-playing-texas-hold-em-with-dexterous-embodied-system--arxiv-2605.18727/2026-05-19T21:32:51.302Z https://www.opentrain.ai/papers/semantic-generative-tuning-for-unified-multimodal-models--arxiv-2605.18714/2026-05-20T17:23:04.023Z https://www.opentrain.ai/papers/lance-unified-multimodal-modeling-by-multi-task-synergy--arxiv-2605.18678/2026-05-19T05:09:11.626Z https://www.opentrain.ai/papers/ai-for-auto-research-roadmap-user-guide--arxiv-2605.18661/2026-05-19T05:09:20.011Z https://www.opentrain.ai/papers/forecasting-downstream-performance-of-llms-with-proxy-metrics--arxiv-2605.18607/2026-05-24T14:57:36.243Z https://www.opentrain.ai/papers/minteval-evaluating-memory-under-multi-target-interference-in-long-horizon-agent--arxiv-2605.18565/2026-05-21T04:32:27.959Z https://www.opentrain.ai/papers/monitoring-the-internal-monologue-probe-trajectories-reveal-reasoning-dynamics--arxiv-2605.18549/2026-05-19T08:36:54.554Z https://www.opentrain.ai/papers/code-as-room-generating-3d-rooms-from-top-down-view-images-via-agentic-code-synt--arxiv-2605.18451/2026-05-19T05:34:20.164Z https://www.opentrain.ai/papers/newton-agentic-planning-for-physically-grounded-video-generation--arxiv-2605.18396/2026-05-19T05:34:19.984Z https://www.opentrain.ai/papers/enhancing-train-free-infinite-frame-generation-for-consistent-long-videos--arxiv-2605.18233/2026-05-21T10:20:17.834Z https://www.opentrain.ai/papers/symmetry-compatible-principle-for-optimizer-design-embeddings-lm-heads-swiglu-ml--arxiv-2605.18106/2026-05-19T21:32:50.184Z https://www.opentrain.ai/papers/panoworld-a-generative-spatial-world-model-for-consistent-whole-house-panorama-s--arxiv-2605.17916/2026-05-21T04:32:28.508Z 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-2605.17766/2026-05-25T10:33:56.149Z https://www.opentrain.ai/papers/harnessing-llm-agents-with-skill-programs--arxiv-2605.17734/2026-05-20T17:22:32.245Z https://www.opentrain.ai/papers/stop-when-reasoning-converges-semantic-preserving-early-exit-for-reasoning-model--arxiv-2605.17672/2026-05-19T05:09:24.171Z https://www.opentrain.ai/papers/causal-intervention-based-memory-selection-for-long-horizon-llm-agents--arxiv-2605.17641/2026-06-13T18:08:40.414Z https://www.opentrain.ai/papers/safelens-deliberate-and-efficient-video-guardrails-with-fast-and-slow-screening--arxiv-2605.17610/2026-06-14T16:16:02.803Z https://www.opentrain.ai/papers/don-t-guess-just-ask-resolving-ambiguity-in-referring-segmentation-via-multi-tur--arxiv-2605.17531/2026-05-28T16:30:18.408Z https://www.opentrain.ai/papers/saasbench-exploring-the-boundaries-of-coding-agents-in-long-horizon-enterprise-s--arxiv-2605.17526/2026-05-21T21:33:23.931Z https://www.opentrain.ai/papers/self-improving-cad-generation-agents-with-finite-element-analysis-as-feedback--arxiv-2605.17448/2026-05-26T00:42:55.314Z https://www.opentrain.ai/papers/soap2soap-long-cinematic-video-remaking-via-multi-agent-collaboration--arxiv-2605.17423/2026-05-27T02:52:18.265Z https://www.opentrain.ai/papers/a2rbench-an-automatic-paradigm-for-formally-verifiable-abstract-reasoning-benchm--arxiv-2605.17278/2026-05-19T08:36:55.317Z https://www.opentrain.ai/papers/geometric-phase-transition-enables-extreme-hippocampal-memory-capacity--arxiv-2605.17199/2026-05-19T05:09:30.583Z https://www.opentrain.ai/papers/capturing-llm-capabilities-via-evidence-calibrated-query-clustering--arxiv-2605.17110/2026-05-22T06:28:04.432Z https://www.opentrain.ai/papers/s-bus-automatic-read-set-reconstruction-for-multi-agent-llm-state-coordination--arxiv-2605.17076/2026-05-21T04:33:08.980Z https://www.opentrain.ai/papers/tobench-a-task-oriented-omni-modal-benchmark-for-real-world-tool-using-agents--arxiv-2605.16909/2026-05-19T12:32:41.060Z https://www.opentrain.ai/papers/ngm-a-plug-and-play-training-free-memory-module-for-llms--arxiv-2605.16893/2026-05-19T12:33:00.313Z https://www.opentrain.ai/papers/chi-bench-can-ai-agents-automate-end-to-end-long-horizon-policy-rich-healthcare--arxiv-2605.16679/2026-05-19T12:35:45.684Z https://www.opentrain.ai/papers/dexjoco-a-benchmark-and-toolkit-for-task-oriented-dexterous-manipulation-on-mujo--arxiv-2605.16257/2026-05-18T08:39:52.345Z https://www.opentrain.ai/papers/videoseeker-incentivizing-instance-level-video-understanding-via-native-agentic--arxiv-2605.16079/2026-05-19T12:32:59.877Z https://www.opentrain.ai/papers/worldact-activating-monolithic-3d-worlds-into-interactive-ready-object-centric-s--arxiv-2605.15843/2026-05-18T06:24:12.364Z https://www.opentrain.ai/papers/fashionchameleon-towards-real-time-and-interactive-human-garment-video-customiza--arxiv-2605.15824/2026-05-18T08:39:53.107Z https://www.opentrain.ai/papers/rule2drc-benchmarking-llm-agents-for-drc-script-synthesis-with-execution-guided--arxiv-2605.15669/2026-05-25T21:27:26.473Z https://www.opentrain.ai/papers/physbrain-1-0-technical-report--arxiv-2605.15298/2026-05-18T08:39:24.151Z https://www.opentrain.ai/papers/atlas-agentic-or-latent-visual-reasoning-one-word-is-enough-for-both--arxiv-2605.15198/2026-05-15T04:28:27.808Z https://www.opentrain.ai/papers/futuresim-replaying-world-events-to-evaluate-adaptive-agents--arxiv-2605.15188/2026-05-15T04:28:27.856Z https://www.opentrain.ai/papers/quantitative-video-world-model-evaluation-for-geometric-consistency--arxiv-2605.15185/2026-05-15T04:28:24.829Z https://www.opentrain.ai/papers/warp-as-history-generalizable-camera-controlled-video-generation-from-one-traini--arxiv-2605.15182/2026-05-15T04:28:07.768Z https://www.opentrain.ai/papers/memeye-a-visual-centric-evaluation-framework-for-multimodal-agent-memory--arxiv-2605.15128/2026-05-15T04:28:02.056Z https://www.opentrain.ai/papers/learning-from-language-feedback-via-variational-policy-distillation--arxiv-2605.15113/2026-05-21T21:33:23.727Z https://www.opentrain.ai/papers/beyond-individual-intelligence-surveying-collaboration-failure-attribution-and-s--arxiv-2605.14892/2026-05-15T04:28:28.204Z https://www.opentrain.ai/papers/known-by-their-actions-fingerprinting-llm-browser-agents-via-ui-traces--arxiv-2605.14786/2026-05-18T15:35:07.181Z https://www.opentrain.ai/papers/vimu-benchmarking-video-metaphorical-understanding--arxiv-2605.14607/2026-05-17T15:24:39.023Z https://www.opentrain.ai/papers/lisa-lifelong-safety-adaptation-via-conservative-policy-induction--arxiv-2605.14454/2026-05-17T15:24:38.317Z https://www.opentrain.ai/papers/frontiersmith-synthesizing-open-ended-coding-problems-at-scale--arxiv-2605.14445/2026-05-17T15:24:38.425Z https://www.opentrain.ai/papers/nexus-an-agentic-framework-for-time-series-forecasting--arxiv-2605.14389/2026-05-15T04:28:09.338Z https://www.opentrain.ai/papers/llm-based-detection-of-manipulative-political-narratives--arxiv-2605.14354/2026-05-15T04:28:24.839Z https://www.opentrain.ai/papers/kvpo-ode-native-grpo-for-autoregressive-video-alignment-via-kv-semantic-explorat--arxiv-2605.14278/2026-05-19T04:28:22.532Z https://www.opentrain.ai/papers/auditing-agent-harness-safety--arxiv-2605.14271/2026-05-19T00:21:52.062Z https://www.opentrain.ai/papers/bookmarks-efficient-active-storyline-memory-for-role-playing--arxiv-2605.14169/2026-05-15T04:28:36.137Z https://www.opentrain.ai/papers/curvebench-a-benchmark-for-exact-topological-reasoning-over-nested-jordan-curves--arxiv-2605.14068/2026-05-17T15:24:38.493Z https://www.opentrain.ai/papers/spin-structural-llm-planning-via-iterative-navigation-for-industrial-tasks--arxiv-2605.14051/2026-05-15T04:15:29.601Z https://www.opentrain.ai/papers/hodgecover-higher-order-topological-coverage-drives-compression-of-sparse-mixtur--arxiv-2605.13997/2026-05-18T06:24:50.114Z