AI智能体自主实现、调优并重组26种CT重建方法，以0.4%参数达到冠军级水平，效率惊人。
arXiv:2607.22824v1 Announce Type: cross Abstract: Comparing CT reconstruction methods fairly is labor-intensive and largely manual, and many benchmark…
单层Transformer训练竟能媲美全参数强化学习？突破性发现重塑参数效率认知。
arXiv:2607.01232v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a central component of post-training large language models (LLM…
可分离神经架构破解强化学习参数效率难题，资源受限场景下价值函数建模更轻快。
arXiv:2601.23225v2 Announce Type: replace Abstract: Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, ye…
针对KAN网络参数爆炸与高频特征捕捉难题，提出基于傅里叶变换的改进架构，理论与实验俱佳
arXiv:2502.06018v3 Announce Type: replace-cross Abstract: Although Kolmogorov-Arnold-based interpretable networks (KANs) possess strong theoretical ex…
混合全微调与低秩适应的新方法，专为后训练场景优化，效率与性能兼得
arXiv:2605.18822v1 Announce Type: new Abstract: Post-training has become essential for adapting large language models (LLMs) to complex downstream beh…
循环语言模型量化面临三大挑战，首次系统性研究揭秘其脆弱性根源
arXiv:2605.16343v1 Announce Type: new Abstract: Looped language models (LoopLMs) improve parameter efficiency by recursively reusing Transformer block…