Explorer
- .. (Parent Directory)
- pdfs/
- answer-conditioned-chains-of-thought-degrade-verifiable-reasoning-dist-2607.14552.md
- anticipate-before-acting-future-state-conditioned-vision-language-navi-2607.18042.md
- behavior-leverage-imbalance-in-multi-teacher-on-policy-distillation-2607.07050.md
- compete-then-collaborate-frontier-ai-teachers-build-a-verifiable-curri-2607.08255.md
- condensing-large-scale-datasets-directly-with-minimal-information-loss-2607.00916.md
- consensus-as-privileged-context-for-label-free-self-distillation-2607.13643.md
- cross4d-jepa-dense-cross-modal-correspondence-distillation-for-4d-poin-2607.00514.md
- deepsearch-world-self-distillation-for-deep-search-agents-in-a-verifia-2607.07820.md
- demopsd-disagreement-modulated-policy-self-distillation-2607.02502.md
- demystifying-on-policy-distillation-roles-pathologies-and-regulations-2607.13399.md
- denser-neq-better-limits-of-on-policy-self-distillation-for-continual-2607.01763.md
- diagnosing-and-calibrating-tool-call-boundary-drift-in-multi-teacher-o-2607.07050.md
- diagnosing-and-mitigating-thinking-collapse-in-on-policy-self-distilla-2607.10805.md
- different-teachers-different-capabilities-sub-1b-on-device-distillatio-2607.08268.md
- diffusion-gr2-diffusion-generative-reasoning-re-ranker-2607.01170.md
- distill-to-detect-exposing-stealth-biases-in-llms-through-cartridge-di-2607.01208.md
- distill-where-the-student-goes-teacher-regularized-rl-for-english-evid-2607.02966.md
- do-we-really-need-multimodal-emotion-language-models-larger-than-1b-pa-2607.12787.md
- dopsd-on-policy-self-distillation-for-diffusion-language-models-2607.04428.md
- easyopd-an-easy-to-use-on-policy-distillation-framework-for-large-lang-2607.11012.md
- efficient-multilingual-reasoning-transfer-via-progressive-code-switchi-2607.00485.md
- fedagentke-federated-semantic-knowledge-evolution-for-heterogeneous-ag-2607.21361.md
- few-medoids-an-embarrassingly-simple-coreset-selection-method-for-few-2607.05891.md
- geometric-foundation-model-distillation-for-efficient-lunar-3d-reconst-2607.01851.md
- gold-guided-programmatic-distillation-for-financial-reasoning-over-hyb-2607.14709.md
- hawk-harnessing-hardware-aware-knowledge-for-high-performance-npu-kern-2607.01590.md
- knowledge-distillation-for-automated-ai-tutor-evaluation-2607.10647.md
- laguadia-language-guided-adaptive-distillation-from-pathology-foundati-2607.11257.md
- met-theory-grounded-and-culture-aware-multilingual-moral-reasoning-2607.11736.md
- multi-turn-on-policy-distillation-with-prefix-replay-2607.04763.md
- neuron-aware-data-selection-for-annotation-free-llm-self-distillation-2607.02460.md
- non-vacuous-generalization-bounds-for-reinforcement-learning-with-veri-2607.14506.md
- on-policy-delta-distillation-2607.15161.md
- opod-on-policy-omni-distillation-2607.20918.md
- opsd-v-on-policy-self-distillation-for-post-training-few-step-autoregr-2607.08766.md
- optimal-self-distillation-for-rectified-flow-via-linear-probing-2607.14947.md
- pretraining-multiple-instance-learning-networks-with-multi-teacher-dis-2607.14703.md
- purified-opsd-on-policy-self-distillation-without-losing-how-to-think-2607.02234.md
- rethinking-on-policy-self-distillation-for-thinking-models-2607.05184.md
- seed-self-evolving-on-policy-distillation-for-agentic-reinforcement-le-2607.14777.md
- self-conditioned-flow-map-language-models-via-fixed-point-flows-2607.00714.md
- sfkd-spatial-frequency-joint-aware-heterogeneous-knowledge-distillatio-2607.01906.md
- shortopd-recovering-pruned-llms-with-short-to-long-on-policy-distillat-2607.13124.md
- squad-sql-efficient-text-to-sql-with-small-language-models-via-llm-gui-2607.08161.md
- symbiosis-inspired-knowledge-distillation-for-incremental-object-detec-2607.13452.md
- turnopd-making-on-policy-distillation-turn-aware-for-efficient-long-ho-2607.05804.md
- understanding-layer-patching-in-model-size-interpolation-2607.08170.md
- visual-contrastive-self-distillation-2607.21556.md
- weak-to-strong-generalization-via-direct-on-policy-distillation-2607.05394.md
- x-3-opd-distilling-reasoning-into-large-audio-language-models-via-on-p-2607.21550.md