提出可证明安全的高效聚类方案，为大规模LLM推理保驾护航。
arXiv:2607.19704v1 Announce Type: new Abstract: Scaling LLM-based applications to millions of users is bottlenecked by the inference cost and latency …
提出“无窥视调优”方法，为大模型后训练提供可证明的泛化界限与鲁棒性保障。
arXiv:2507.01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalab…
从理论层面形式化语言反馈学习，提供可证明的保证，为机器学习新范式奠定基础。
arXiv:2506.10341v2 Announce Type: replace Abstract: Interactively learning from observation and language feedback is an increasingly studied area driv…
基于人类编写本体论，实现LLM代理的可证明安全与可审计性，为智能体可靠性提供新路径。
arXiv:2606.04903v1 Announce Type: cross Abstract: We introduce the LLM agent architecture Agentic Redux, intended for use with nontrivial problem doma…
这篇论文提出了一种可证明安全的智能体护栏机制，为AI Agent的安全性提供了理论保障。
arXiv:2605.29251v1 Announce Type: new Abstract: As large language models transition from bounded generative engines to agents with expansive execution…
从理论角度证明Transformer能内化思维链，揭示大模型推理能力的新机制。
arXiv:2605.28600v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducin…
可证明自校正的掩码扩散微调方法，提升生成模型可靠性的创新框架
arXiv:2510.01384v4 Announce Type: replace Abstract: A natural desideratum for generative models is self-correction--detecting and revising low-quality…
新研究用可证明方式保护微调大模型免遭训练数据窃取，同时维持模型效能，隐私与实用兼得。
arXiv:2602.00688v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on sensitive datasets raises privacy concerns, as trainin…
可证明的联合去污染方法，解决多LLM基准测试中的数据污染难题
arXiv:2605.21543v1 Announce Type: new Abstract: Benchmark data contamination has become a central challenge in LLM evaluation: when evaluation example…
首次证明带接口约束的工作流学习能保证收敛，理论突破为自动化流程生成奠基。
arXiv:2605.19140v1 Announce Type: new Abstract: We study workflow learning in a setting where specialized agents hand off control through a shared art…
深度神经网络公平性修复新突破，提供可证明保证，已被ASE 2025录用。
arXiv:2605.19549v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In …
后量子时代多智能体AI治理系统，提出可证明安全的MAGIQ架构，解决新兴计算范式下的安全挑战。
arXiv:2605.06933v2 Announce Type: replace Abstract: Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment o…