Field notes
2,348 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
2,348 notes and 295 topics.
- Question answered
- Source note
- Topic
- Shared notes
All notes, newest first
2,348 notes, page 14 of 98
Too hot to sleep? How heatwaves at night affect our health
This text contains three articles published on August 17, 2026 in Nature. The first article discusses the effects of heatwaves at night on human health. The second and third articles are a comment and a book review…
Topological Attribution Distance (TAD): Revealing Segment-Level RAG Influence on LLM Output Geometry for Incident Log Analysis
Researchers propose a method called Topological Attribution Distance (TAD) to help identify which parts of cyber incident logs are critical in influencing the outputs of Large Language Models (LLMs) used in…
UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
Researchers propose UniTAC, a universal image compression system for physical AI systems like autonomous vehicles and robots. The system can adapt to changing tasks without retraining, using task-specific importance…
学习贯彻党的二十届四中全会精神
The Ministry of Industry and Information Technology (MIIT) held a grand event commemorating the 100th birthday of Jiang Zemin, with Xi Jinping delivering an important speech. The theme was to study and carry forward…
熊继军率团访问香港、澳门
Xi Jinping attended a commemorative event for the 100th birthday of Jiang Zemin in Beijing and delivered an important speech. Xi Jinping also led a team to visit Hong Kong and Macau, and Li Lecong conducted a survey at…
李乐成到四川省通信管理局调研 强调深入学习贯彻习近平党建思想 推动信息通信业高质量发展
Li Lechen visited the Sichuan Provincial Communications Administration Bureau, emphasizing the deep study and implementation of Xi Jinping's party-building thoughts to promote the high-quality development of the…
一图读懂《安全应急装备产业发展“十五五”规划》
A summary of the 'Safety and Emergency Equipment Industry Development '15-5' Plan'. The plan was announced at a meeting to commemorate the 100th birthday of Jiang Zemin, where Xi Jinping delivered an important speech.
Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI
Researchers propose an automated dataset quality assurance mechanism using unsupervised anomaly detection and out-of-distribution detection for multi-center dynamic contrast-enhanced breast MRI. The study compares four…
When Agents Coordinate: Measuring Coordination in Multi-Agent AI Coding
The authors studied how AI coding agents coordinate while working on programming tasks. They developed a method to measure this coordination by representing each run as a network with nodes (agents and files) connected…
When State Becomes an Attack Surface: State-Semantic Injection in LLM-Driven Embodied Agents
The text discusses the evolution of Large Language Models (LLMs) from text generation models to core components of agents that can perceive environments, invoke tools, and execute tasks. These LLM-driven embodied…
Why AI systems are most useful as designers of new scientific tools
The article discusses the benefits of using AI systems to design new scientific tools.
Would this change your answer? Evaluating Explanations of LLM Behavior In The Wild with Counterfactual Experiments
The study introduces a new method called CHIVE (Counterfactual Hypothesis Investigation Via Edits) to investigate and explain the behavior of language models in real-world scenarios by creating counterfactual prompt…
Towards Risk-free AI Agent Deployment
The paper argues that trustworthy deployment of LLM agents requires testing and debugging the full execution trajectory, not only checking individual actions or final answers.
UniRL: A Framework for Unified Multimodal Model Reinforcement Learning
Tencent Hunyuan released UniRL, an open-source framework that applies one shared reinforcement-learning training loop across different kinds of generative models (diffusion/image models, text language models…
ACL Anthology team
The ACL Anthology is a collection of papers related to natural language processing, published by the ACL Anthology team. Papers from 2016 onwards are licensed under Creative Commons Attribution 4.0 International…
qwen-code-docs: documentation translation tool for the Qwen Code project
Alibaba's Qwen team released a small open-source tool that automatically translates the Qwen Code project's documentation into eight languages and builds a multilingual documentation website, using Qwen's own AI models…
Automating and Scaling Behavioral Scientific Research on AI Agents
The paper presents AEROBAT, a multi-agent system intended to automate parts of behavioral research on AI agents, from hypothesis generation through experiments, assessment, analysis, and reporting.
Secure all your internal vibe-coded applications — in one click
Cloudflare launched "Access for Workers," letting developers attach login/authentication policies directly to an individual Cloudflare Worker (a unit of deployed code) rather than to a hostname, aimed at securing…
How Cloudflare detects MCP traffic and helps secure it
Cloudflare announced Gateway features that detect Model Context Protocol (MCP) network traffic (the protocol AI agents use to call external tools) and let organizations block or route it through an approved "Portal"…
qwen-code v0.21.12 release (and related preview/nightly builds)
Alibaba's Qwen team shipped a stable release (v0.21.12) of qwen-code, its coding-agent CLI/desktop tool, along with preview and nightly builds in the same window, adding features like drag-and-drop workspace file…
Custom reward functions for multi-turn reinforcement learning with Amazon Nova Forge
AWS engineers describe how to design reward functions for training AI models on multi-turn tasks (e.g., a coding assistant that should ask clarifying questions before writing code) using Amazon Nova Forge, and how to…
Using AI_Functions in Your Data Warehouse: Top Use Cases
Databricks describes how its "AI Functions" let users run AI inference (document parsing, extraction, classification, translation, custom prompting) directly from SQL inside the data warehouse, without moving data to…
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
Researchers have developed a new framework called AutoDesign to improve the process of transforming multimodal sources into structured media outputs, such as converting academic papers into posters. The system uses a…
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
Researchers have developed OmniScientist, an AI system that can conduct multidisciplinary research from raw data across various modalities (text, images, signals, etc.). The system operates in a deterministic pipeline…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
