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 54 of 59
Where Do CoT Training Gains Land in LLM based Agents?
The study investigates how Chain-of-thought (CoT) training in language model agents affects their performance. The authors find that while CoT improves overall, it doesn't significantly widen the advantage of CoT…
Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs
Researchers have found that two open-source language models, Apertus-8B-Instruct-2509 and Gemma-4-E4B-it, have internal representations (emotion vectors) that can encode emotions such as valence and arousal. The…
A cross-process welding penetration status prediction algorithm based on unsupervised domain adaptation in laser and TIG welding
Researchers have developed a new approach to improve the performance of deep learning models in predicting weld penetration status, especially when transferring between welding processes with distinct physical…
A welding penetration prediction model for laser welding process based on self-supervised learning using physics-informed neural networks
A new algorithm named SimPhysNet has been introduced to predict laser welding penetration with high accuracy using only a limited number of labelled images. The algorithm uses self-supervised learning and…
Agentic evolution of physically constrained foundation models
Researchers present a multi-agent discovery engine that is grounded in physics and can autonomously architect hardware-compliant computing systems. The engine evolved two hardware-aware compression methodologies…
Agentic System as Compressor: Quantifying System Intelligence in Bits
The authors propose a method to measure the intelligence of an agentic system by quantifying its ability to compress a target object under a fixed task distribution, interface, and compute budget. This is done using…
AI-Assisted Computational Reproducibility on the FABRIC Testbed
This paper discusses how the FABRIC testbed, along with an AI coding assistant named LoomAI, can help simplify reproducing published experiments across various domains. The authors present three case studies and…
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
Researchers have identified the issue of AI agents being used for user surveillance, which is a concern as these agents can access personal data without user control. They introduce SurveilBench, a dataset to evaluate…
Autodata: An agentic data scientist to create high quality synthetic data
The authors introduce Autodata, an AI agent that acts as a data scientist to create high-quality synthetic training and evaluation data. They discuss how to train this data scientist agent to improve its data creation…
AutoRelAnnotator: Calibrated Model Cascades for Cost-Efficient Relevance Evaluation in Sponsored Search
Researchers propose a method to generate high-quality relevance annotations at a lower cost without the need for human labeling. This is important for training data preparation, NDCG evaluation, and root cause analysis…
Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem
The study analyzes the ERC-8004 protocol, a trust layer for AI agent economies. The authors find that most registrations are placeholders, the reputation system is flawed and can be easily manipulated, and a…
Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation
This research compares the effectiveness of encoder classifiers (using models like ModernBERT and Ettin) against LLM-based judges in identifying harmful outputs from large language models (LLMs). The study evaluates…
Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface
The paper introduces an Explainable Control Framework (XCF) for understanding complex controllers' behavior in various scenarios. It offers three main contributions: the XCF, a model-agnostic explanation method called…
Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis
The researchers have developed a new method for diagnosing depression using deep learning models and facial videos. Their approach provides interpretable explanations for the model's decisions, which can help health…
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
The paper introduces FORCE, a framework designed to improve the efficiency of reinforcement learning fine-tuning for Vision-Language-Action (VLA) models. The framework consists of three stages: Value-Calibrated…
GUI agent: Guided Exploration of User-Sensitive Screens
This research presents a new agent called Guided Exploration of User-Sensitive Screens (GUI agent) designed to automate tasks within an open Graphical User Interface (GUI) environment. The GUI agent is intended to…
Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study
The authors propose an empirical study to evaluate the effectiveness and potential risks of using Large Language Models (LLMs) for vulnerability patching in software development. They plan to conduct a controlled…
Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization
The paper introduces HiReLC, a hierarchical reinforcement learning framework that automates the joint quantization and structured pruning of deep neural networks. It operates at two levels: low-level agents (LLAs)…
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization
The paper introduces a framework for comparing different variants of RAG (Rich Automated Generation) scenarios, including GraphRAG and Agentic RAG, in semi-structured knowledge bases. The framework includes nine…
MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources
Researchers propose MiniOpt, a reinforcement learning framework that helps large language models solve various optimization problems with limited resources. It breaks down optimization reasoning into structured…
Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment
The authors propose a method for investigating if AI models are acting with 'malign intent' when exhibiting concerning behavior. The method involves analyzing the chain of thought (CoT) of the AI and making adjustments…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
Researchers propose a method called Multi-Agent Goal Recognition with Branch-and-Bound (MAGR-BB) to infer the goals of multiple agents in real applications like drone surveillance and collaborative robotics, where only…
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Researchers present a new method called 'progress advantage' for evaluating Language Learning Models (LLMs) without the need for dedicated reward model training. This method is based on reinforcement learning (RL)…
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
The paper discusses a method called On-policy Self-Distillation, which uses a single model as both teacher and student to achieve high accuracy in pass@1. However, it is found that this method can lead to a decrease in…
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.
