共计 390 篇文章
2026
多个问题的Token 成本对比与决策公式
Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
Harnessing the Universal Geometry of Embeddings
20260907
规模化安全：大型模型与智能体安全的综合调查
AOPS一则美妙不等式
Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
如何避免成为“脚本小子”
Small LLMs Are Weak Tool Learners： A Multi-LLM Agen
KVSmooth： Mitigating Hallucination in Multi-modal Large Language Models through Key-Value Smoothing