从谱几何切入推理链，揭示大模型任务难度的隐藏规律，视角新颖。
arXiv:2607.01571v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by gen…
首次揭示离线推理训练中权重空间的几何演化规律，为理解大模型推理能力提供新视角。
arXiv:2606.23740v1 Announce Type: cross Abstract: Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill…
探讨控制问题中贝尔曼残差最小化的几何与收敛理论，为强化学习提供新视角
arXiv:2601.18840v4 Announce Type: replace Abstract: Markov decision problems are most commonly solved via dynamic programming. Another approach is Bel…
用几何流方法定量分析大脑沟回形态，揭示个体差异与神经疾病关联。
arXiv:2606.08404v1 Announce Type: new Abstract: Cortical folding reflects coordinated neurodevelopmental processes and is increasingly recognized as a…
用几何方法剖析多轮对话中LLM的对抗性攻击模式，为AI安全提供全新视角
arXiv:2606.03136v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks on large language models (LLMs) reveal a mismatch in current guardrails…