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 52 of 59
UNKNOWN
The text provided does not contain any research findings or summary.
UNKNOWN
The provided text does not contain any information to create a brief summary.
UNKNOWN
The text provided does not contain any information for a summary.
UNKNOWN
The text provided does not contain sufficient information for a summary.
UNKNOWN
The provided text does not contain any information to generate a brief summary.
UNKNOWN
The text does not provide a summary.
A Deterministic Control Plane for LLM Coding Agents
The research proposes a control plane for LLM coding agents, which currently have unmanaged configuration layers. The control plane aims to fill gaps identified in a study of 10,008 public GitHub repositories, such as…
A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models
A new pipeline for creating synthetic clinical notes is introduced to help develop AI systems in healthcare without compromising privacy. The pipeline generates structured, semi-structured, and unstructured clinical…
A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO
Researchers introduce a new mechanism called the 'process harness' to upgrade legacy workflow systems into Agentic Business Process Management (Agentic BPM) without replacing the existing engine. The process harness…
Adaptive Utility driven Resource Orchestration for Resilient AI (AURORA-AI)
A new AI resource management framework called AURORA-AI has been proposed by the authors to improve the performance of modern AI systems under non-stationary conditions. It unifies various control methods and…
Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy
Researchers have developed a new framework called OmniAct for building embodied agents that can operate in unstructured environments. This framework aims to address the challenges of managing both cyber and physical…
AI Healthcare Chatbots as Information Infrastructure: A Large-Scale Study of User-Reported Breakdowns
This study analyzes over 15,000 user reviews of AI healthcare chatbot apps to identify common issues reported by users. The research found three main breakdowns: access barriers and service unreliability, user…
Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions
The authors propose using Large Language Models (LLMs) to help assess threats during foreign peacekeeping missions, specifically referencing their work with the EU Monitoring Mission in Georgia. They combine an…
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
Researchers have developed a new method called BINEVAL to evaluate the output of large language models (LLMs). Instead of relying on human judgment or lexical metrics, which can be expensive and unreliable, BINEVAL…
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions
Researchers investigated how different contexts or framings can affect the responses of large language models (LLMs) used in mental health support tools. They found that framing does systematically alter interpretive…
Automating Potential-based Reward Shaping with Vision Language Model Guidance
Researchers have developed a new method for reinforcement learning agents using vision language models (VLMs). The approach called VLM-guided PBRS learns a potential function from VLM feedback to address the challenge…
Autoregressive Boltzmann Generators
A new method called Autoregressive Boltzmann Generators (ArBG) is proposed to efficiently sample molecular systems at thermodynamic equilibrium. This method overcomes limitations of previous methods by using an…
Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts
The authors present a framework for analyzing dialogue in collaborative problem-solving contexts, particularly focusing on human-AI and multi-agent collaboration. The framework addresses limitations in current…
CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention
The paper introduces CARVE (Content-Aware Recurrent with Value Efficiency), a recurrent model that addresses three issues in the leading delta-rule architecture (GDN-2). The primary problem is memory-blind gating…
Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities
The paper introduces Chai, an AI-based system that discovers and validates cryptographic misuse vulnerabilities using naturally occurring signals. Instead of auditing one codebase for many flaws, Chai catalogs flaws at…
Confidence-Aware Tool Orchestration for Robust Video Understanding
The paper presents a new framework called Robust-TO for video understanding that addresses the issue of 'Blind Trust Problem' in current language models. These models assume every input frame is equally reliable, but…
Diagnosing Task Insensitivity in Language Agents
Researchers identify an issue with large language models where they are unable to adapt to new tasks effectively due to their task insensitivity. The authors propose a lightweight solution called Task-Perturbed NLL…
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
Researchers have developed a new framework called E-TTS for robotic manipulation tasks. This framework combines reasoning and action scaling to address two challenges: the lack of study on the scaling mechanism for…
Efficient foundation decoders for fault-tolerant quantum computing
The paper introduces Neural Transfer Unification (NTU), a framework for creating efficient foundation decoders that can handle various code distances in fault-tolerant quantum computing. The NTU-Transformer, an…
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.
