Field notes
1,406 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.
1,406 notes and 240 topics.
- Question answered
- Source note
- Topic
- Shared notes
All notes, newest first
1,406 notes, page 33 of 59
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Researchers have developed teLLMe, a system that helps traffic agencies analyze large volumes of video-derived data for studying safety and congestion by answering causal questions about urban driving, such as 'How…
The Industrialization of Research ; On AI-Driven Science and Its Consequences
The text discusses the transformation of scientific research due to artificial intelligence (AI), likening it to the industrialization of research. The author raises several concerns about this shift, including the…
Towards Hierarchical Structure Understanding of Newspaper Images
The paper presents two approaches for understanding the complex and nested hierarchical structures in newspaper images. The first approach is a modular pipeline that combines existing open-source models to detect…
When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration
This research investigates how people's understanding of their own authorship changes when using AI, particularly Generative AI. The study uses the CoAuthor dataset and finds that frequent users tend to overestimate…
A Self-Evolving Agent for Longitudinal Personal Health Management
The authors developed an open-source agent architecture called HealthClaw for personal health management. It learns and adapts to changes in a person's routines, preferences, measurements, and risks over time. The…
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
The text is about AgentCompass, an open-source evaluation infrastructure designed to evaluate Large Language Models (LLMs) as they evolve into autonomous agents. The infrastructure aims to address the current…
AI-accelerated End-to-End Framework for Rapid Professional Upskilling
The paper presents an end-to-end AI-accelerated framework designed to improve professional upskilling programs' efficiency by focusing on five stages: knowledge acquisition, content development, content review and…
AI-Augmented Human Resource Management? Insights from German companies
This study investigates how AI is being integrated into Human Resource Management (HRM) in German companies and whether it enhances or 'augments' HRM. The research findings, based on interviews, group discussions, and…
AIMO Interpretability Challenge
The text proposes the AIMO Interpretability Challenge, a competition aimed at distinguishing robust from spurious reasoning in advanced mathematical language models. The challenge will provide participants with new…
Automatic Ordinary Differential Equations Discovery For Biological Systems Using Large Language Model Powered Agentic System
The MEDA system is an automated framework using Large Language Models (LLMs) and Symbolic Regression (SR) to discover Ordinary Differential Equations (ODEs) for biological systems. It retrieves background knowledge…
CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI Systems
The paper introduces Canonical Action Verification and Attestation (CAVA), a system designed to convert diverse agent activities into standardized action objects, addressing the challenge of governing heterogeneous AI…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Researchers propose a new method called Deep Interaction to correct errors made by large language models (LLMs) during complex, multi-step tasks. The method allows for direct editing of the original response, improving…
Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0
The research evaluates if improvements from agent-optimization methods can stack up over time in a continual learning setting. Three optimizer-driven methods (GEPA, Meta Harness, and RELAI's Verifiable Continual…
Early Adoption of Agentic Coding Tools by GitHub Projects
This research investigates the adoption and management of agentic coding tools in software development on GitHub. The study analyzes 25,264 agentic pull requests from 2,361 popular repositories to understand (1) how…
Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
The paper introduces Earthquaker-AI, a hybrid educational framework that combines conversational AI with Lego robotics to teach primary school students about earthquake preparedness. The system uses Lego WeDo2 for…
Experience Memory Graph: One-Shot Error Correction for Agents
The researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. EMG reformulates failure recovery…
Explaining Reinforcement Learning Agents via Inductive Logic Programming
This research aims to improve Reinforcement Learning (RL) policies by making them more transparent and interpretable. It proposes objective and planning-oriented metrics for policy explainability in RL settings using…
Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code
Researchers introduce 'generative compilation', an approach that allows compilers to provide feedback on partial programs during the generation of AI-generated code in languages with rich static semantics like Rust…
Groc-PO: Grounded Context Preference Optimization for Truthful Multimodal LLMs
Researchers propose a new method called Grounded Context Preference Optimization (Groc-PO) to improve the truthfulness and utility of Multimodal Large Language Models (MLLMs). Current MLLMs often make errors due to…
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
This research paper discusses the importance of user-level permissions for AI agents to protect users from risks such as data leaks and unauthorized actions. The authors survey 21 proposals for agent permissions…
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
Researchers propose a new method for feature selection in renewable energy prediction pipelines, called Cluster-based Sequential Feature Selection (CSFS). This method aims to address the gap in limited or unsystematic…
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
The paper proposes a new framework called Memory as a Controlled Process (MemCon) for large language model (LLM) agents that use external memory systems. MemCon learns an online policy to adaptively decide when, what…
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
The paper introduces a multi-expert system for Optical Character Recognition (OCR) of historical Manchu texts which have various writing styles and limited labeled data. The system uses a router that classifies pages…
Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings
The text presents a new theory for partially correlated verifier cascades in LLM harnesses (a system used to verify candidate answers). The theory provides insights into the growth and decay of failure rates, the…
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.
