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 40 of 59
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
The text discusses the increasing trend of AI systems improving themselves through various methods such as revising outputs, adapting their own harnesses, and conducting AI research itself. The authors surveyed 1250…
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
The researchers present Reward-Adaptive Iterative Discovery (RAID), a new approach for automated game testing in the gaming industry, specifically focusing on the ice hockey game EA SPORTS NHL 26. The goal is to reduce…
RLVP: Penalize the Path, Reward the Outcome
The paper 'RLVP: Penalize the Path, Reward the Outcome' by Bojie Li and Noah Shi proposes a method for training artificial agents to perform tasks effectively in real-world environments. This method addresses two main…
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF
The paper proposes two methods for improving the efficiency of Reinforcement Learning from Human Feedback (RLHF) when applied to diffusion models, which are often inefficient due to high feedback requirements. The…
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
The paper introduces Single-rollout Asynchronous Optimization (SAO), a new approach to reinforcement learning (RL) aimed at post-training large language models (LLMs). SAO addresses stability and off-policy challenges…
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
Researchers have created SkillCenter, a large-scale library of structured skills for autonomous AI agents. The library contains over 216,000 skills across 24 domains, obtained from various sources like peer-reviewed…
SpaCellAgent: A Self-Evolving LLM-Based Multi-Agent Framework for Trajectory Analysis
Researchers propose SpaCellAgent, an autonomous multi-agent framework that automates spatiotemporal analysis in single-cell transcriptomics. It improves efficiency by over 40% while maintaining expert-level…
Stability of Flow Models for Graph Signals
The paper presents research on the stability of continuous flow models for generating signals on graphs. The authors analyze normalized flow models parameterized by Graph Neural Networks (GNNs) and demonstrate that…
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
Researchers have developed a method called SynthAVE to generate large amounts of labeled data for e-commerce attribute extraction using synthetic labels validated by multiple large language models (LLMs). The benchmark…
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
The researchers explore the impact of biased judges in self-evolving agents, focusing on skill retirement, a mechanism that helps maintain the quality of an agent's knowledge base by retiring poorly performing skills…
Towards Agentic AI Governance: A Preliminary Assessment
This paper reviews emerging literature on agentic AI governance, a new field that deals with autonomous AI systems capable of planning and executing tasks. The authors analyze the unique features of agentic AI that…
Vision Foundation Models in Radiology: A Scoping Review of Data, Methodology, Evaluation and Clinical Translation
The text discusses a scoping review of vision foundation models (VFMs) used in radiology. The study found that while these models are becoming common in radiological imaging, their development and evaluation methods…
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
The paper proposes ARGTCA, a method to improve the calibration of Vision-Language Models (VLMs) by using Graph Attention Networks to capture inter-attribute dependencies and reduce overconfidence during test-time…
A Definition and Roadmap for World Models
The provided text discusses the concept of 'world models', which are internal simulators used in AI to understand the structure and dynamics of an environment. The authors propose a definition for world models, outline…
A Physics-Informed Neural Network Framework for Elastodynamic Wave Propagation in Bimaterial Systems
A new study presents a Physics-Informed Neural Network (PINN) framework to model the transient elastodynamic wave propagation in bimaterial systems, specifically focusing on a steel-aluminum specimen. The PINN…
A toy framework for single and multi-agent human-AI curiosity ecosystems
The paper presents a basic framework to understand curiosity from the perspective of an ecosystem. It discusses how an individual agent's curiosity is influenced by factors like immediate uncertainty reduction, costs…
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
The researchers propose an experimental design framework to systematically evaluate the autonomous model discovery behavior of large language model coding agents, like Codex and Claude Code. The framework considers…
Analysis-by-Proxy: Localization Signals in VLMs Operating as Condition Encoders
Researchers investigate why Vision-Language Models (VLMs) struggle to maintain localization accuracy during image editing, even though they have strong localization capabilities on their own. The study suggests that…
Bridging Physical Reasoning and Task Generalization via Visual Action Outcome Reasoning Alignment
Researchers have developed a new method called VAORA (Visual Action Outcome Reasoning Alignment) to improve the performance of vision-language models in interactive physical reasoning, especially in unseen tasks and…
Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory
The paper proposes a system called Danus that aims to help mathematical reasoning agents tackle complex, research-level problems by coordinating them effectively and managing their shared memory through a global fact…
Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities
The researchers introduce DataGovBench, a new benchmark for evaluating large language models (LLMs) in practical scenarios of real-world data analysis. The benchmark tests the models' ability to answer complex…
Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale
The paper introduces TOFFEE, a system designed to generate high-quality data agent trajectories using Monte Carlo Tree Search (MCTS) with adaptive model selection and cross-task prefix reuse. This is aimed at…
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression
The research introduces DepthWeave-KV, a new cache compression method for long-context language models. This method adapts to the needs of different tokens by factorizing key and value states across neighboring…
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Researchers propose a method to predict early on if large language models (LLMs) are likely to fail at solving multi-step tasks and abort the process before consuming too much compute. This method uses probes on hidden…
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.
