Field notes
2,343 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.
262 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on artificial intelligence
262 notes, page 7 of 11
Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels
The research proposes JADR, a protocol for measuring the internal safety mechanisms of language models before their first response is generated. It uses Jacobian space to record top-k J-space tokens from prompts and…
Evidence-Backed Video Question Answering
The authors propose Evidence-Backed Video Question Answering (E-VQA), a new task that requires models to not only provide answers but also the specific spatial and temporal evidence from videos. They introduce…
LightMem-Ego: Your AI Memory for Everyday Life
The research paper introduces LightMem-Ego, a lightweight multimodal memory system designed for AI assistants on mobile and wearable devices. The system continuously captures and organizes egocentric visual and audio…
Metacognition in LLMs: Foundations, Progress, and Opportunities
This paper provides a comprehensive overview of metacognition in Large Language Models (LLMs), highlighting the importance of this aspect for effective learning, problem solving, and communication. It discusses recent…
VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
The paper introduces VoxENES 2026, a new benchmark for evaluating the performance of speech spoofing detectors against modern text-to-speech (TTS) and voice conversion (VC) systems. The benchmark contains 53,628 audio…
ArtMine: Discovering and Formalizing Artistic Processes
The paper introduces ArtMine, a framework for discovering and formalizing artistic processes from various historical sources. It uses an abductive agent to infer evidence-based production steps which are then optimized…
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
The text presents IdeaGene-Bench (IG-Bench), a new benchmark for evaluating AI systems' ability to follow the structure of scientific idea inheritance. IG-Bench is based on the IdeaGene framework, which represents each…
OpenCoF: Learning to Reason Through Video Generation
The paper introduces OpenCoF, a framework that includes a new dataset and a fine-tuned video model for improving Chain-of-Frame (CoF) reasoning in video generation. The authors argue that existing models lack specific…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper introduces ProjAgent, a system for generating code at the repository level that considers procedural similarity as a new method for retrieving appropriate functions. ProjAgent deconstructs target functions…
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
The paper proposes SMetric, a new scheduling method for Large Language Models (LLMs) in serving agents. The method aims to balance the session-centric workload of agents and increase Key-Value (KV$) reuse by…
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
The paper proposes a new LLM (Language Model) scheduling method called SMETRIC for serving agents. This method aims to balance the workload between instances by focusing on the first request of each agent session and…
The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality
The paper proposes a new dimension for analyzing disparities in AI usage called the 'Context Access Divide' (CAD). This divide is based on whether an AI system can autonomously access a user's stored knowledge or…
The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality
The text discusses a new concept called the 'Context Access Divide' in AI agents, which is a divide between users who can autonomously access their own knowledge corpus (Dynamic Context Retrieval) and those who need to…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
This research study introduces a new metric, called 'correctness agreement', to evaluate the impact of post-training quantization on large language models. The authors show that even when task performance seems…
Two Axes of LLM Abstention: Answer Correctness and Question Answerability
A study finds that large language models often struggle with two types of errors: answering questions incorrectly and attempting to answer unanswerable or misleading questions. The researchers propose a method to…
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
UltraX is a new framework designed to improve the quality of large-scale pre-training data for Large Language Models (LLMs). It addresses the limitations of existing methods by offering fine-grained instance-level…
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
The text describes a study that analyzed the use of an AI-based learning assistant (Syntea) among 77,543 students in distance education, looking at usage patterns across various demographic and structural factors. The…
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
The study presents a large-scale analysis of an AI-based learning assistant named Syntea, used by 77,543 students in distance studies. The research focuses on usage patterns across various demographic and structural…
Validity of LLMs as data annotators: AMALIA on authority
A study evaluates AMALIA, a Portuguese language model, in measuring moral values and authority. The model shows agreement with human coders but fails to perform well when the test is broken down into smaller parts…
Agentic Data Environments
The text discusses early work on Agentic Data Environments (ADE), a system that allows autonomous agents to operate safely and efficiently over a broader data environment. The goal is to increase the benefits of…
Beyond Attack-Success Rate: Action-Graded Severity Scale for Tool-Using AI Agents
The paper proposes an action-graded harm rubric for evaluating AI agents' behavior during cybersecurity attacks. This scale assesses the severity of an agent's actions based on factors like reversibility, scope…
CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis
The paper proposes CARLA-GS, a modular pipeline for synthesizing corner cases in autonomous driving simulations. The pipeline decouples visual representation, semantic reasoning, and physics-based execution while…
Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows
A study investigates whether Language Model (LLM) generated skills can improve the performance of AI in data science tasks compared to traditional methods. The study tests this across four stages of a data science…
Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety
The text introduces institutional red-teaming, a new evaluation methodology for testing the impact of deployment rules on multi-agent AI safety. The study uses IABench-CA, a consequence-allocation benchmark, to test…
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.
