提出可学习的零阶优化器，无需梯度即可高效微调大模型，大幅降低内存开销。
arXiv:2510.00419v2 Announce Type: replace Abstract: Zeroth-order optimizers have recently emerged as an attractive approach for fine-tuning large lang…
dMoE提出可学习块专家机制，为大型语言模型混合专家设计提供新思路，架构简洁高效。
arXiv:2605.30876v1 Announce Type: new Abstract: Diffusion Large Language Models (dLLMs) have recently emerged as a promising alternative to autoregres…
通过pass-rate加权自蒸馏，恢复LLM推理的“甜蜜点”，破解GRPO归一化带来的学习偏差。
arXiv:2605.27765v1 Announce Type: cross Abstract: Self-Distillation Policy Optimization (SDPO) provides dense token-level credit assignment for reinfo…
非线性变换防御不可学习数据集，对抗数据爬取，保护隐私的学术新方法
arXiv:2406.02883v2 Announce Type: replace Abstract: Automated scraping stands out as a common method for collecting data in deep learning models witho…
提出可学习的逐步语言反馈机制STRIDE，让LLM在推理过程中自动修正错误，提升复杂推理任务准确性。
arXiv:2605.18851v1 Announce Type: new Abstract: Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reason…
医学影像生成新挑战：揭示Latent Diffusion模型在医学数据上的可学习性差距，推动更可靠的AI诊断工具发展。
arXiv:2605.17087v1 Announce Type: new Abstract: Generative data augmentation with latent diffusion models is a promising strategy for addressing class…
揭示自我对弈仅在自合成数据提供可学习信息增益时才有效演化，为AI训练策略提供关键理论指导。
arXiv:2603.02218v2 Announce Type: replace Abstract: Large language models (LLMs) make it plausible to build systems that improve through self-evolving…
提出LEAP可学习端到端自适应剪枝方法，在保持大语言模型性能的同时实现高效压缩
arXiv:2605.17289v1 Announce Type: new Abstract: Unstructured sparsity is now natively accelerated by recent GPU kernels and dataflow hardware, shiftin…
揭示RLVR训练中LLM对困难样本无法学习的反直觉现象，挑战现有认知
arXiv:2605.16787v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language …
探讨Chain-of-Thought验证器的在线可学习性，深入分析正确性与完备性间的权衡关系。
arXiv:2603.03538v3 Announce Type: replace Abstract: Large Language Models (LLMs) with chain-of-thought generation have demonstrated great potential fo…