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 44 of 59
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
A new evaluation setting called Autonomous Policy Evolution (APE) is introduced in a benchmark named EvoPolicyGym, which is used to test how autonomous agents iteratively improve their policy systems within a fixed…
Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
The text discusses a new method for identifying multi-dimensional refusal subspaces in Large Language Models (LLMs), which are used for safety and interpretability. The proposed method adapts the Recursive Feature…
Grounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physics
The paper presents an autonomous research pipeline that can conduct end-to-end research from a corpus of 11,083 recent condensed matter physics papers to a publication-grade manuscript. The agent is capable of…
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
The authors propose a hardware-enforced semantic coordination architecture for safety-critical real-time autonomous systems. This new approach aims to address limitations of software-mediated coordination by…
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
A study using real-money prediction markets found that the effectiveness of human-AI collaboration in forecasting depends on specific forms of human capital (like perspective-taking, intellectual humility, and…
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
The researchers introduce a new testbed called LACUNA for evaluating the precision of post hoc removal methods (unlearning) for LLMs. The testbed focuses on injecting personal identifiable information into specific…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Researchers propose Task-Agnostic Pretraining (TAP) as a solution to the scarcity of expert demonstrations in Vision-Language-Action (VLA) models. TAP aims to separate learning physical competence and semantic…
Neuron-Aware Active Few-Shot Learning for LLMs
The paper introduces a new method called NeuFS for Active Few-Shot Learning (AFSL) in Language Models (LLMs). Instead of relying on output-level signals to identify valuable unlabeled samples, it focuses on the…
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Researchers have developed a new method called Neuron On-Policy Self-Distillation (Neuron-OPSD) for training large language models without the need for real-world interaction feedback or human-labeled supervision…
Online Safety Monitoring for LLMs
The researchers propose a straightforward method for monitoring Large Language Models (LLMs) in real-time to ensure safety during deployment. This method involves setting a threshold for a verifier signal from an…
Overview of Risk Assessment and Management for Intelligent Systems under the AI Act and Beyond
This paper provides an overview of methods for assessing and managing risks associated with intelligent systems, as required by emerging regulatory frameworks. It reviews various types of AI-related risks, existing…
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
The authors propose a new programming paradigm called fuzzy-function programming, which compiles natural language specifications into compact, locally executable neural artifacts using a 4B compiler trained on a large…
QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition
The paper proposes QFedAgent, a new approach for multi-agent activity recognition in federated learning. It uses a hybrid quantum-classical framework and a variational quantum circuit fusion module that models…
Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study
A study found that the level of reasoning effort in agentic code generation, rather than the availability of additional capabilities like testing tools and design prompts, significantly affects the reliability of…
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
Researchers introduce DramaSR-532K, a large-scale benchmark for speaker recognition in long-form TV dramas. They also propose DramaSR-LRM, a robust approach that uses a large reasoning model to improve speaker…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Researchers have proposed a new method called Recursive Evidence Replay (RECONTEXT) to improve the ability of large language models to understand and reason over long contexts. This method doesn't require training…
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
The paper presents SkillFuzz, a method for discovering unintended objectives (implicit intents) in Large Language Model (LLM)-based agents that use reusable skills from open skill marketplaces. SkillFuzz works by…
Steerability via constraints: a substrate for scalable oversight of coding agents
The author proposes a method for improving the scalability of oversight on coding agents by implementing constraints such as access control, network policies, and strict coding conventions enforced by tooling. This…
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
Researchers have developed TestEvo-Bench, a live benchmark for testing software tests and code co-evolution. The benchmark includes two tracks: test generation and test update, where an agent should either write new…
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
Researchers have developed a new method called SPG-Layout for creating realistic indoor scenes in complex, non-rectangular (non-Manhattan) environments using large language models. This method improves upon existing…
The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry
A study analyzes the geometry of Large Language Model (LLM) personas using psychometric questionnaires and SPD manifolds. The research finds that LLM personas have two components: aggregated features (Big Five scores)…
The Eticas AI Risk Taxonomy: Open Infrastructure for Operationalizing AI Audits
The Eticas AI Risk Taxonomy v2.0.0 is an open-source framework for operationalizing AI audits. It provides a standardized method for evaluating AI systems across various high-stakes domains, focusing on turning risks…
UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development
The researchers proposed UA-ChatDev, an uncertainty-aware multi-agent software development framework to improve the reliability of autonomous multi-agent software development. The framework uses a lightweight…
Understanding Agent-Based Patching of Compiler Missed Optimizations
The paper presents a study on the effectiveness of AI agents in addressing missed optimizations in compilers. The authors found that while coding agents can often optimize given examples, the generated patches…
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.
