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.
235 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on machine learning
235 notes, page 1 of 10
WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
WikiSkill is a framework that helps AI agents evolve their skills by creating a persistent knowledge base (wiki) to store and consolidate their experiences. This framework outperforms other skill-evolution methods…
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
This research proposes a three-step workflow integrating chatbot-administered surveys, data processing, and behavioral prediction for travel behavior modeling and weather-sensitive demand forecasting. The study uses…
Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning
This research focuses on predicting rug pulls, a form of fraud in memecoins traded on the Solana blockchain, using machine learning models. The study assembles a dataset of over 6 million tokens traded over 7 months…
Electronic Navigational Chart Change Classification
The authors propose an automated method to classify changes in Electronic Navigational Charts (ENCs), which are used in maritime navigation systems. The proposed approach involves encoding complex vector data changes…
EnvHarness: Awakening Static Worlds for Agent Learning
The paper proposes a new system called Environment Harness (EnvHarness) to improve static environments used in learning by AI agents. The system can adapt the behavior of these environments without modifying their…
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
The paper presents MaliciousSkillBench, a comprehensive benchmark for detecting malicious Agent Skills in large language models (LLMs). The benchmark consolidates various sources of malicious artifacts and reduces them…
MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
Researchers have introduced a new benchmark called MemTrapBench to test the performance of large language models (LLMs) in terms of cognitive traps caused by their memory components. The study identifies two types of…
Repo0: Design-Driven Zero-to-All Code Generation
The paper introduces Repo0, a framework for zero-to-all code generation that maintains an explicit architectural state using a Dual-Directed Acyclic Graph (Dual-DAG). It iteratively evolves component boundaries guided…
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
The paper presents Task-CoEvolve, a new approach to optimize language model agent harnesses efficiently by adaptively selecting validation tasks. It addresses the challenge of using fixed validation sets by co-evolving…
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
Researchers have developed a method called Task-CoEvolve to improve the efficiency of harness optimization for large language models (LLMs). This method co-evolves validation tasks with the harness by focusing on tasks…
Beyond the Transcript: Detecting Covert Co ordination in Latent Multi-Agent Communication
Researchers have developed Verifiable Latent Alignments (VLA), a framework for monitoring and controlling communication between language-model agents that occurs through hidden states not visible in public transcripts…
Finetuning Strategies for Querying Sounds by Vocal Imitation
The authors describe their winning strategy for a sound effect querying competition in 2025, which involved two fine-tuning strategies: contrastive learning with a frozen pretrained CED encoder and joint…
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
The author argues that precision, rather than capability, should be the focus when comparing and measuring AI systems. Precision refers to how consistently an AI system performs the same task, while capability is where…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
The paper presents a new paradigm for continual learning called Harness Continual Learning (HCL). In this approach, an agent can adapt through a harness of prompts, memories, tools, skills, and routing rules. The…
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Researchers developed a method called EvalCEGAR to automatically create an evaluation metric for AI agents in tasks like report generation, where traditional metrics are difficult to develop. The method involves…
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors propose a method to utilize multiple Intel AI PCs with integrated GPUs and NPUs, even when they have insufficient memory for large models like a 70B-parameter LLM. The method involves breaking the model…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The paper investigates the performance of large language models (LLMs) in extracting contextualized information from research articles, finding that while LLMs can perform well with expert-curated prompts, they may…
Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models
The paper presents EvoResearcher, a training-free protocol for adding cost-bounded self-reflection to large language models (LLMs). The protocol is designed to work with a single frozen LLM backbone and aims to improve…
AutoSR: Automatic Symbolic Regression by Searching Research States
The authors introduce AutoSR, a fully automated system that searches for persistent scientific investigations instead of isolated equations in symbolic regression. Unlike traditional methods, AutoSR preserves the…
Orbit-Planner: Towards Latent World Models for On-Orbit Obstacle Avoidance of Satellite Agents
The paper presents Orbit-Planner, a system designed to help satellite agents navigate in space by predicting collision risks with limited onboard observations. It introduces a two-stage latent world model for on-orbit…
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
A new benchmark called Diagram-MMU has been created to test the ability of Multimodal Large Language Models (MLLMs) in parsing and understanding scientific diagrams. The benchmark includes 3,700 curated diagrams and…
Redistribution-based Cost Inference Improves Sparse Safe Offline RL
A new framework called Redistribution-based Cost Inference (RCI) is proposed to convert sparse stop-feedback in safe offline reinforcement learning into dense per-step costs. This conversion helps train a constrained…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
Researchers have created a benchmark dataset called VICBench for evaluating code vulnerability detection tools. The dataset contains 100 verified vulnerabilities across 88 projects in Python, Java, and C++, covering 48…
GitSkills: A Dataset of Agent Skills on GitHub
The paper introduces GitSkills, a dataset of 3,797,117 SKILL.md files collected from public GitHub repositories in July 2026. The dataset retains every file occurrence with its repository, path, and content hash. It…
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.
