Field notes
2,348 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.
2,348 notes and 295 topics.
- Question answered
- Source note
- Topic
- Shared notes
All notes, newest first
2,348 notes, page 21 of 98
CEAA: A Cognitive Embodied Agents Architecture for Interactive Computing Systems
The authors propose a modular cognitive architecture to develop Intelligent Virtual Agents (IVAs) that can operate in real-time interactive virtual environments. This architecture aims to bridge the gap between…
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Researchers propose ColluSkill, a framework for multi-skill attacks that can bypass individual skill checks in LLM-based agent systems. These attacks are composed of locally plausible behaviors that collectively form…
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Researchers propose ColluSkill, a framework for creating multi-step attacks on LLM-based agent systems. These agents have vulnerabilities in their skill systems that current defenses don't fully address, particularly…
Defining Decentralization: An Ontological Perspective
This research paper addresses the lack of a universal definition for decentralization in computer science and its related fields like security, AI, cloud infrastructure, IoT, etc. The authors propose a graph-based…
Defining Decentralization: An Ontological Perspective
The authors address the lack of a universally accepted definition of decentralization in computer science, particularly in emerging fields like decentralized AI and machine learning. They propose a graph-based ontology…
DSLE: A Learning Environment for Dark Souls Boss Encounters
The authors introduce the Dark Souls Learning Environment (DSLE), a platform for training AI agents to play boss encounters in the video game 'Dark Souls: Remastered'. The DSLE is designed as a benchmark for…
DSLE: A Learning Environment for Dark Souls Boss Encounters
Researchers have created a learning environment for AI agents called DSLE, which is based on the game Dark Souls: Remastered. The environment includes 22 boss encounters that can be used as benchmarks. The researchers…
ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization
The paper presents ElasticBack, a stealthy conditional backdoor that can compromise LLM agents by planting a rule and trigger in skills. The backdoor only activates when both the rule and the trigger appear together…
From Semantic Grounding to Decision Optimization: A Unified Framework for Long-Horizon UAV Vision-Language Navigation
The authors propose a unified framework to improve UAV vision-language navigation (UAV-VLN). This framework addresses three main issues: weak grounding of instruction-relevant landmarks, insufficient exploitation of…
From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch
The paper presents a new evaluation framework called 'Grip on LLMs' specifically designed for Dutch governmental use of large language models (LLMs). The framework is created in collaboration with domain experts and…
From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch
Researchers present a new evaluation framework called 'Grip on LLMs' for Dutch governmental use of large language models. The framework focuses on six dimensions: factuality, honesty, social bias, energy consumption…
Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching
Researchers propose a new framework for grounding user instructions in graphical user interfaces (GUI). The framework uses a frozen multimodal large language model (MLLM) to parse instructions and a dedicated grounding…
How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans
This research investigates how large language models (LLMs) evaluate social attraction by comparing their judgments to human's from theory-grounded persona ratings. The study found that while some LLMs tended to give…
Illusion or Integrity? Geometrical Consistency Metric for AIGC Video Quality Evaluation
The paper presents a new benchmark, called GeoCon-Bench, to evaluate the quality of AI-generated videos by measuring their compliance with physical principles and geometric consistency across frames. The benchmark…
KGCaRe: Explainable Complex Conditional Question Answering using Automatic Knowledge Graph Construction and Context Retrieval with LLMs
The study proposes a new method called KGCaRe for answering complex conditional questions using large language models (LLMs) and retrieval-augmented generation (RAG). This approach combines neural retrieval with…
MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation
Researchers present MedPixel, a unified medical pixel-language model that bridges the gap between clinical language and visual reasoning in medical image understanding. The model is trained using MedPLG-440K, a large…
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
Researchers present TIDE, a new method to address a failure mode in on-policy distillation (OPD) called degenerate agreement. This issue arises when students exploit repetitive loops to achieve high token agreement…
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
The text introduces the Model Discovery Agent (MDA), a system designed to efficiently discover mechanistic, causal models from minimal interventions using a large language model (LLM) and Bayesian methods. The MDA…
Modern Backbones Improve Multi-task DETR for Mammography Classification and Lesion Localization
The study evaluates a multi-task DETR framework that simultaneously predicts the malignancy of mammogram images and locates lesions, using modern backbones such as ConvNeXtV2 and DINOv3. The results show that these…
Multi-Agent AI Safety as an Institutional Design Problem
The paper discusses AI safety as an institutional design problem in multi-agent systems. The research focuses on understanding which parts of an AI institution ensure safety and how they do it. The study involves a…
Multi-Agent AI Safety as an Institutional Design Problem
In this research paper, Abdullah X discusses the role of institutions in ensuring safety for AI agents within multi-agent systems. The study includes a 5280-episode study suite with various experiments testing…
Multi-Agent AI Safety as an Institutional Design Problem
The paper discusses an experiment on multi-agent AI safety as an institutional design problem. The research focuses on understanding which parts of an AI institution ensure safety and how they do it. The study includes…
Multimodal Model Diffing for Feature Discovery and Control
Researchers introduce a framework called MMDiff to help identify, control, and audit the internal features of Multimodal Large Language Models (MLLMs). The framework is designed to isolate which features are altered by…
Multimodal Model Diffing for Feature Discovery and Control
Researchers developed a framework called MMDiff to help understand, control, and audit the behavior of Multimodal Large Language Models (MLLMs). The framework identifies features that are altered by multimodal…
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.
