What is Multimodality?

什么驱动了智能体文本到Cypher查询的恢复？LAST-CQ：一种LLM智能体自精炼框架

What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework

LAST-CQ五智能体框架通过反事实实验证明，文本到Cypher生成中驱动恢复的关键是失败检测与重试路由，而非反馈复杂度或采样数量，且能恢复91.7%的失败查询。

我知道你去年夏天训练了什么：机器学习模型窃取与防御综述

I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences

本文综述 MLaaS 场景下的模型窃取攻击与防御，系统分类、比较攻击方法及对应防御，并给出按目标和资源选择策略的指南。

Explainability in Human-Agent Systems

This paper presents a taxonomy of explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability, and its relationship to the related terms of interpretability, transparency, explicitness, and faithfulness. These definitions allow us to answer why explainability is needed in the system, whom it is geared to and what explanations can be generated to meet this need. We then consider when the user should be presented with this information. Last, we consider how objective and subjective measures can…

Differential Privacy: What is all the noise about?

Differential Privacy (DP) is a formal definition of privacy that provides rigorous guarantees against risks of privacy breaches during data processing. It makes no assumptions about the knowledge or computational power of adversaries, and provides an interpretable, quantifiable and composable formalism. DP has been actively researched during the last 15 years, but it is still hard to master for many Machine Learning (ML)) practitioners. This paper aims to provide an overview of the most important ideas, concepts and uses of DP in ML, with special focus on its intersection with Federated Learni…

缓存什么更持久：用于LLMs中内存受限KV缓存的令牌保留

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

TRIM-KV通过学习令牌的内在重要性实现内存受限的KV缓存优化，有效提升LLM在低内存环境下的推理性能。