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 6 of 10
teLLMe Why (Ain't Nothing but a Jam): Exploratory Causal Analysis of Urban Driving Data
Researchers developed teLLMe, a system that allows traffic agencies to analyze urban driving data using causal analysis methods. The system helps answer questions about the impact of various factors on traffic density…
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…
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…
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…
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
The research investigates the effectiveness of Reinforcement learning with verifiable rewards and Group Relative Policy Optimization (GRPO) on a small language and vision-language model web agent at scales ranging from…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
Researchers present Pythia, a multi-agent system that automatically generates and optimizes extraction prompts for clinical concepts without manual engineering or fine-tuning. They compare Pythia with a curated lexicon…
A Multi-Agent System for Autonomous, Fine-Tuning-Free Clinical Symptom Detection: Development and Validation Study
A new system called Pythia was developed, which automatically generates and optimizes extraction prompts for clinical concepts without the need for manual prompt engineering or fine-tuning. The researchers compared…
Audio-Native Speech Recognition with a Frozen Discrete-Diffusion Language Model
Researchers train a discrete diffusion language model to transcribe speech instead of using autoregressive decoders that emit one token at a time. The model is based on a mixture-of-experts called DiffusionGemma, and…
Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
In this research, Mehmet Iscan introduces a method called PoPE (Popperian Placebo-controlled Evaluation) to test the effectiveness of Frozen small code LLMs in self-repair when faced with errors. The study compares…
Tracing Agentic Failure from the Flow of Success
The paper proposes a new method called OAT (One-Class Attribution for Tracing) for identifying errors in language models without relying on expensive or difficult-to-collect data. This method is faster and more…
UR-VC: Unsupervised Robotic Value Correction for Time-Derived Progress Proxies
Researchers introduce an offline method called Unsupervised Robotic Value Correction (UR-VC) to correct time-derived progress labels used by modern robot learning systems. The method is based on a regularity in…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
The authors present a method for creating and refining evaluation metrics for self-improving language models (LLMs). The proposed method, called Double Ratchet, evolves metrics by combining small drawback detectors in…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
The paper presents a method for creating and improving self-evolving agent systems, which are capable of developing, modifying, and discarding their own skills. The authors claim that in many real-world applications, a…
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
Researchers present AHA, an automated red-teaming approach for production language models like Claude Code and Codex. AHA discovers reusable vulnerability knowledge about other agents by proposing a vulnerability…
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
A new method using reinforcement learning (RL) has been proposed to improve the accuracy of decoding continuous three-dimensional motor imagery signals from non-invasive EEG data for brain-computer interfaces (BCIs)…
Metacognition in LLMs: Foundations, Progress, and Opportunities
This research paper provides a comprehensive overview of the current state of metacognition in Large Language Models (LLMs). The authors discuss recent advancements, methods, and benchmarks for measuring and evaluating…
MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
Researchers introduce MM-ToolSandBox, a new evaluation framework for visual tool-calling agents. This framework supports over 500 tools across 16 application domains and can handle multi-image, multi-turn tasks with…
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
The authors of the paper 'Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph', published in 2026, discuss a new approach to utilizing the internal k-nearest-neighbor (kNN) graph constructed…
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
The paper proposes a method for machine learning that aims to align autonomous agents' behavior with human intent in diverse operational contexts by using a hierarchical machine teaching algorithm for reward learning…
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…
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
A new method called BioModule is proposed for predicting biomechanical attributes from standard 3D skeletons recovered from human motion, without requiring modifications to the upstream pose model. The method is…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper proposes ProjAgent, a new system for generating code at the repository level by introducing 'procedural similarity' as a retrieval signal. This method decomposes the target function into steps and retrieves…
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…
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.
