Explorer

• .. (Parent Directory)
• pdfs/
• a-formula-driven-survey-and-research-agenda-for-on-policy-distillation-2606.22793.md
• a-quantitative-approximation-framework-for-flow-distillation-in-diffus-2606.03820.md
• aliyunconsoleagent-training-web-agents-in-real-world-cloud-environment-2606.09447.md
• arkd-adaptive-reinforcement-learning-guided-bidirectional-kl-divergenc-2606.29869.md
• asyncopd-how-stale-can-on-policy-distillation-be-2606.24143.md
• atod-annealed-turn-aware-on-policy-distillation-for-multi-turn-autonom-2606.27814.md
• aura-internalizing-audio-understanding-into-llms-as-lora-2606.11033.md
• bahsd-bridging-the-long-tail-gap-via-adaptive-distillation-in-black-bo-2606.03091.md
• be-my-tutor-on-policy-co-distillation-for-mutual-llm-improvement-via-p-2606.14368.md
• behavior-cloning-is-not-all-you-need-the-optimality-of-on-policy-disti-2606.30923.md
• beyond-dark-knowledge-mixup-based-distillation-for-reliable-prediction-2606.12171.md
• beyond-output-matching-preserving-internal-geometry-in-nvfp4-llm-disti-2606.05682.md
• beyond-trajectory-imitation-strategy-guided-policy-optimization-for-ll-2606.24064.md
• bitnet-text-embeddings-2606.25674.md
• blockwise-policy-drift-gating-for-on-policy-distillation-2606.24084.md
• breaking-the-tokenizer-barrier-on-policy-distillation-across-model-fam-2606.09456.md
• building-multi-task-agentic-llms-via-two-phase-distillation-2606.30044.md
• candle-character-level-arabic-noise-deduplication-using-lightweight-en-2606.24758.md
• cartridges-at-scale-training-modular-kv-caches-over-large-document-col-2606.04557.md
• characterize-then-distill-mechanistic-reasoning-in-large-output-spaces-2606.06840.md
• compress-distill-reasoning-trace-compression-for-efficient-knowledge-d-2606.05988.md
• context-aware-distillation-and-ablation-for-text2dsl-2606.22578.md
• cross-modal-knowledge-distillation-without-paired-data-theoretical-fou-2606.10504.md
• danceopd-on-policy-generative-field-distillation-2606.27377.md
• data-efficient-autoregressive-to-diffusion-language-models-via-on-poli-2606.06712.md
• dense-supervision-sparse-updates-on-the-sparsity-and-geometry-of-on-po-2606.13657.md
• distill-on-a-diet-efficient-knowledge-distillation-via-learnable-data-2606.25488.md
• distill-once-adapt-life-long-exploring-dataset-distillation-for-contin-2606.20196.md
• distilling-answer-set-programming-rules-from-llms-for-neurosymbolic-vi-2606.03269.md
• distilling-drifting-transformers-with-representation-autoencoders-2606.15553.md
• distilling-examples-into-task-instructions-enhanced-in-context-learnin-2606.15641.md
• distilling-safe-llm-systems-via-soft-prompts-for-on-device-settings-2606.09388.md
• doc-to-atom-learning-to-compile-and-compose-memory-atoms-2606.12400.md
• dopd-dual-on-policy-distillation-2606.30626.md
• drift-difficulty-routing-self-distillation-with-rhythm-gated-explorati-2606.30345.md
• dudi-dual-signal-distillation-with-cross-lingual-verbalizer-2606.04694.md
• duomem-towards-capable-on-device-memory-agents-via-dual-space-distilla-2606.29961.md
• efficient-financial-language-understanding-via-distillation-with-synth-2606.18875.md
• egtr-review-efficient-evidence-grounded-scientific-peer-review-generat-2606.06025.md
• escaping-the-kl-agreement-trap-in-on-policy-distillation-2606.09471.md
• escaping-the-self-confirmation-trap-an-execute-distill-verify-paradigm-2606.24428.md
• fada-accessible-fetal-ultrasound-interpretation-and-annotation-with-a-2606.11106.md
• fast-speech-foundation-model-distillation-using-interleaved-stacking-2606.11766.md
• filter-then-reweight-rethinking-optimization-granularity-in-on-policy-2606.02684.md
• finding-the-evidence-discovering-decision-supporting-tokens-for-on-pol-2606.22830.md
• force-efficient-vla-reinforcement-fine-tuning-via-value-calibrated-war-2606.26006.md
• from-clicks-to-intent-cross-platform-session-embeddings-with-llm-disti-2606.26277.md
• gr2-technical-report-2606.31984.md
• harnessbridge-learnable-bidirectional-controller-for-llm-agent-harness-2606.12882.md
• heterophily-aware-adaptive-knowledge-distillation-for-hypergraph-neura-2606.08978.md
• hilda-hierarchical-distillation-with-diffusion-for-advancing-self-supe-2606.20189.md
• hump-kd-a-hybrid-uncertainty-aware-multi-stage-progressive-knowledge-d-2606.14684.md
• hyperdflash-hyper-connection-aligned-block-speculative-decoding-with-g-2606.26744.md
• improving-the-efficiency-and-effectiveness-of-llm-knowledge-distillati-2606.04650.md
• influcoder-distilling-decoders-gradient-influence-rankings-into-an-enc-2606.13668.md
• invariant-gradient-alignment-for-robust-reasoning-distillation-2606.05025.md
• k-forcing-joint-next-k-token-decoding-via-push-forward-language-modeli-2606.10820.md
• keep-policy-gradient-in-charge-sibling-guided-credit-distillation-for-2606.12634.md
• knowledge-cascade-reverse-knowledge-distillation-on-nonparametric-mult-2606.25927.md
• knowledge-distillation-for-visual-autoregressive-models-2606.06078.md
• knowledge-distillation-from-large-reasoning-models-to-compact-student-2606.31048.md
• language-models-need-sleep-learning-to-self-modify-and-consolidate-mem-2606.03979.md
• large-language-model-teaches-visual-students-cross-modality-transfer-o-2606.27527.md
• latent-reasoning-with-normalizing-flows-2606.06447.md
• learning-from-own-solutions-self-conditioned-credit-assignment-for-rei-2606.18810.md
• learning-from-the-self-future-on-policy-self-distillation-for-dllms-2606.18195.md
• learning-from-your-own-mistakes-constructing-learnable-micro-reflectiv-2606.18844.md
• learning-to-reason-by-analogy-via-retrieval-augmented-reinforcement-fi-2606.13680.md
• learning-visual-spatial-planning-from-symbolic-state-via-modality-gap-2606.06076.md
• leveraging-audio-llms-to-filter-speech-to-speech-training-data-2606.13507.md
• localizing-credit-at-the-divergence-path-conditioned-self-distillation-2606.15576.md
• localnav-distilling-frontier-vlms-and-embodied-rl-for-on-device-object-2606.27871.md
• lori-low-rank-distillation-for-implicit-reasoning-2606.05315.md
• marginal-advantage-accumulation-for-memory-driven-agent-self-evolution-2606.20475.md
• masked-language-flow-models-2606.27617.md
• metis-bridging-text-and-code-memory-for-self-evolving-agents-2606.24151.md
• mmg2skill-can-agents-distill-in-the-wild-guides-into-self-evolving-ski-2606.01993.md
• modf-sir-a-multi-agent-omni-modal-distilled-framework-for-social-intel-2606.12018.md
• mopd-multi-teacher-on-policy-distillation-for-capability-integration-i-2606.30406.md
• nebulaexp-8b-an-empirical-post-training-pipeline-via-full-scale-ablati-2606.26671.md
• odyssim-building-foundation-models-for-human-behavior-simulation-2606.14199.md
• omniopsd-rationale-privileged-on-policy-self-distillation-for-affectiv-2606.15920.md
• on-policy-distillation-with-curriculum-turn-level-guidance-for-multi-t-2606.15912.md
• on-policy-self-distillation-with-sampled-demonstrations-reduces-output-2606.26091.md
• on-the-geometry-of-on-policy-distillation-2606.07082.md
• on-the-position-bias-of-on-policy-distillation-2606.22600.md
• opd-evolver-cultivating-holistic-agent-evolver-via-on-policy-distillat-2606.17628.md
• open-swe-traces-advancing-dual-mode-multilingual-distillation-for-soft-2606.16038.md
• opid-on-policy-skill-distillation-for-agentic-reinforcement-learning-2606.26790.md
• oprd-on-policy-representation-distillation-2606.06021.md
• optimizing-teacher-student-partitioning-for-scalable-knowledge-distill-2606.27797.md
• padd-path-aligned-decompression-distillation-for-non-router-teacher-to-2606.10369.md
• parabridge-bridging-paralinguistic-perception-and-dialogue-behavior-in-2606.10581.md
• paved-with-true-intents-intent-aware-training-improves-llm-safety-clas-2606.27210.md
• pbsd-privileged-bayesian-self-distillation-for-long-horizon-credit-ass-2606.09348.md
• pguda-pressure-guided-unsupervised-domain-adaptation-with-cross-modal-2606.31349.md
• physics-guided-policy-optimization-with-self-distillation-2606.03620.md
• pool-select-refine-for-allocation-aware-generative-dataset-distillatio-2606.01920.md
• poweropd-stabilizing-on-policy-distillation-with-bounded-power-transfo-2606.17199.md
• pride-privileged-information-enhanced-distillation-for-empathetic-dial-2606.23124.md
• pythagoras-prover-advancing-efficient-formal-proving-via-augmented-lea-2606.12594.md
• q0-primitives-for-hyper-epoch-pretraining-2606.03938.md
• quantifying-subliminal-behavioral-transfer-ratios-in-language-model-di-2606.11270.md
• qval-cheaply-evaluating-dense-supervision-signals-for-long-horizon-llm-2606.32034.md
• qwen-image-2-0-rl-technical-report-2606.27608.md
• rank-aware-hyperbolic-alignment-for-vision-language-dataset-distillati-2606.29464.md
• rcem-robust-conversational-search-embedder-in-distributional-shift-2606.01697.md
• recover-lora-for-aggressive-quantization-reclaiming-accuracy-in-2-bit-2606.04238.md
• reinforcement-learning-from-rich-feedback-with-distributional-dagger-2606.05152.md
• renio-reweighting-negative-trajectory-importance-for-llm-on-policy-dis-2606.23104.md
• resaware-cross-environment-website-fingerprinting-via-resource-privile-2606.17462.md
• rethinking-continual-experience-internalization-for-self-evolving-llm-2606.04703.md
• rethinking-dataset-distillation-for-classification-do-distilled-sets-o-2606.18209.md
• rethinking-reward-supervision-rubric-conditioned-self-distillation-2606.19327.md
• rlcsd-reinforcement-learning-with-contrastive-on-policy-self-distillat-2606.11709.md
• road-vla-robust-online-adaptation-via-self-distillation-for-vision-lan-2606.25800.md
• robust-trajectory-distillation-hybrid-reweighting-meets-teacher-inspir-2606.29837.md
• rt-vla-real-time-vision-language-action-models-via-knowledge-distillat-2606.14010.md
• rubric-guided-self-distillation-post-training-without-rubric-verifiers-2606.12507.md
• safesteer-localized-on-policy-distillation-for-efficient-safety-alignm-2606.02530.md
• sage-opd-selective-agent-guided-intervention-for-multi-turn-on-policy-2606.19659.md
• sara-unlocking-multilingual-knowledge-in-mixture-of-experts-via-semant-2606.25821.md
• scalable-behaviour-cloning-on-browser-using-via-skill-distillation-2606.32014.md
• scaling-laws-for-task-specific-llm-distillation-2606.24747.md
• scaling-the-horizon-not-the-parameters-reaching-trillion-parameter-per-2606.30616.md
• seeing-before-reasoning-decoupling-perception-and-reasoning-for-shortc-2606.19120.md
• self-distilled-policy-gradient-2606.04036.md
• self-evaluation-is-already-there-eliciting-latent-judge-calibration-in-2606.05122.md
• self-study-reconsidered-the-hidden-fragility-of-learning-from-self-gen-2606.32002.md
• sg-opd-sign-gated-on-policy-distillation-via-sign-consistency-gating-a-2606.09304.md
• shard-safe-and-helpful-alignment-via-self-reframing-distillation-2606.15517.md
• siri-self-internalizing-reinforcement-learning-with-intrinsic-skills-f-2606.02355.md
• skill-disco-distilling-and-compiling-agent-traces-into-reusable-proced-2606.26669.md
• skill-guided-continuation-distillation-for-gui-agents-2606.18890.md
• spotattention-plug-in-block-sparse-routing-for-pretrained-long-context-2606.22874.md
• stabilizing-on-policy-distillation-for-mllm-reasoning-with-global-norm-2606.09091.md
• streamkl-fast-and-memory-efficient-kl-divergence-for-boosting-attentio-2606.20005.md
• structured-testbench-generation-for-llm-driven-hdl-design-and-verifica-2606.12983.md
• talk-text-attributed-graph-dataset-distillation-via-coupling-language-2606.22975.md
• taylor-calibrate-principled-initialization-for-hybrid-linear-attention-2606.16429.md
• teaching-the-way-not-the-answer-privileged-tutoring-distillation-for-m-2606.07000.md
• ternary-mamba-grouped-quantization-aware-training-of-w1-58a16-state-sp-2606.18114.md
• the-quality-utility-paradox-why-high-reward-data-impairs-small-model-m-2606.16152.md
• the-role-of-feedback-alignment-in-self-distillation-2606.11173.md
• towards-direct-latent-space-synthesis-for-parallel-branches-in-llm-age-2606.14672.md
• trust-the-right-teacher-quality-aware-self-distillation-for-gui-ground-2606.18101.md
• understanding-knowledge-distillation-in-post-training-when-it-helps-an-2606.22942.md
• uniego-proxies-as-mediators-for-unified-egocentric-video-representatio-2606.20559.md
• unsupervised-continual-clustering-via-forward-backward-knowledge-disti-2606.07474.md
• unsupervised-skill-discovery-for-agentic-data-analysis-2606.06416.md
• usad-2-0-scaling-representation-distillation-for-universal-audio-under-2606.06444.md
• vibethinker-3b-exploring-the-frontier-of-verifiable-reasoning-in-small-2606.16140.md
• vicur-visual-cues-as-recoverable-privilege-for-multimodal-on-policy-di-2606.05718.md
• visual-opsd-cross-modal-on-policy-self-distillation-for-efficient-unif-2606.18974.md
• what-does-it-mean-to-break-a-distillation-defense-2606.25059.md
• when-should-the-teacher-move-temporal-coupling-and-stability-in-self-o-2606.03532.md
• why-are-dmd-students-lazy-understanding-the-copying-behavior-in-few-st-2606.02237.md
• windom-self-family-distillation-for-small-model-gui-grounding-2606.25964.md
• youzhi-towards-high-concurrency-financial-llms-via-adaptive-gqa-to-mla-2606.05868.md
• zone-of-proximal-policy-optimization-teacher-in-prompts-not-gradients-2606.18216.md
• zooclaw-fashionsiglip2-distilled-fine-tuning-for-robust-fashion-retrie-2606.27708.md