活文档 · 论文卡 · 笔记 · 仓库 · 攻略
本综述尝试连接并系统化现有迁移学习研究，全面总结与阐释迁移学习的机制与策略，帮助读者更好地理解当前研究现状与思路。This survey attempts to connect and systematize the existing transfer learning research studies, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas.
提出 MultiMedQA 基准，整合六个现有医学问答数据集（涵盖专业医学、研究与消费者查询）及一个全新的在线医学问题搜索数据集，并提出针对模型答案的人工评估框架，揭示了 LLM 在医学领域的潜在应用价值。MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, is presented and a human evaluation framework for model answers is proposed, suggesting the potential utility of LLMs in medicine.
通过从概率分布的动态 nucleus 中采样文本，可在有效截断不可靠分布尾部的同时保持多样性，使生成文本更接近人类文本质量，在不牺牲流畅性与连贯性的前提下提升多样性。By sampling text from the dynamic nucleus of the probability distribution, which allows for diversity while effectively truncating the less reliable tail of the distribution, the resulting text better demonstrates the quality of human text, yielding enhanced diversity without sacrificing fluency and coherence.
采用迭代的在线训练模式，按周节奏用新的人类反馈数据更新偏好模型与 RL 策略，并发现 RL 奖励与策略相对其初始化的 KL 散度平方根之间近似呈线性关系。An iterated online mode of training, where preference models and RL policies are updated on a weekly cadence with fresh human feedback data, and a roughly linear relation between the RL reward and the square root of the KL divergence between the policy and its initialization is identified.
本文基于预训练 BLIP-2 模型，对视觉-语言指令微调展开系统全面研究，并提出指令感知的 Query Transformer，用于提取针对给定指令的信息丰富特征。This paper conducts a systematic and comprehensive study on vision-language instruction tuning based on the pretrained BLIP-2 models, and introduces an instruction-aware Query Transformer, which extracts informative features tailored to the given instruction.
本工作研究图结构输入的特征学习技术，并在程序验证任务上取得 SOTA 性能，该任务需将子图与抽象数据结构进行匹配。This work studies feature learning techniques for graph-structured inputs and achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.
全面概述了 LLM 幻觉检测方法与基准，并指出 LLM 幻觉领域有前景的研究方向，包括大视觉-语言模型中的幻觉以及 LLM 幻觉中的知识边界理解。A thorough overview of hallucination detection methods and benchmarks is presented and the promising research directions on LLM hallucinations are highlighted, including hallucination in large vision-language models and understanding of knowledge boundaries in LLM hallucinations.
本文针对 OOD 检测领域的近期技术发展空白，提出统一框架 generalized OOD detection（广义 OOD 检测），涵盖上述五类问题，即 AD、ND、OSR、OOD detection 与 OD。This paper addresses the gap in recent technical developments in recent technical developments in the field of OOD detection by presenting a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i.e.,AD, ND, OSR, OOD detection, and OD.
对 SOTA LLM GPT-4 在医学能力考试与基准数据集上进行全面评估，并通过案例研究定性探索其行为，展示了 GPT-4 解释医学推理、为学生定制个性化讲解以及围绕病例交互式构造新反事实场景的能力。A comprehensive evaluation of GPT-4, a state-of-the-art LLM, on medical competency examinations and benchmark datasets and explores the behavior of the model qualitatively through a case study that shows the ability of G PT-4 to explain medical reasoning, personalize explanations to students, and interactively craft new counterfactual scenarios around a medical case.
本文介绍 Gemma，一族基于 Gemini 模型所使用的研究与技术构建的轻量级 SOTA 开源模型，并全面评估模型的安全性与责任性，同时详细描述模型开发过程。This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models, and presents comprehensive evaluations of safety and responsibility aspects of the models, alongside a detailed description of model development.
本文给出 ICL 的形式化定义，厘清其与相关研究的联系，并梳理讨论训练策略、提示设计策略及相关分析等高级技术。This paper presents a formal definition of ICL and clarify its correlation to related studies, and organizes and discusses advanced techniques, including training strategies, prompt designing strategies, and related analysis.
结果表明，通过结合基础 LLM 改进（PaLM 2）、医学领域微调以及包括新颖集成精化方法在内的提示策略，医学问答正快速接近医生水平的表现。Results highlight rapid progress towards physician-level performance in medical question answering by leveraging a combination of base LLM improvements (PaLM 2), medical domain finetuning, and prompting strategies including a novel ensemble refinement approach.
π RuView 将现成 WiFi 信号转化为实时空间智能、生命体征监测和存在检测，全程无需任何视频画面。π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端
Agent harness 性能优化系统。为 Claude Code、Codex、Opencode、Cursor 等提供 Skill、本能、记忆、安全性与研究优先的开发能力。The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
独立 iOS 应用，可在无需越狱的情况下模拟 GPS 定位。包含 Shadowrocket/Surge/Loon/QX/Stash 模块。Standalone iOS app to spoof GPS location without jailbreak. Includes Shadowrocket/Surge/Loon/QX/Stash module.
OpenAI 的 Codex Security CLI 与 TypeScript SDK，用于发现、验证和修复安全漏洞。npm: https://www.npmjs.com/package/@openai/codex-securityOpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security
A Codex jailbreak prompt and test pack for gpt-5.6-sol. 针对 gpt-5.6 系列的 Codex 破甲提示词与测试包。