Field notes
2,343 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.
262 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on artificial intelligence
262 notes, page 3 of 11
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
Researchers have developed a system called TYTAN that can automatically construct an analytic semantic schema from a relational database, helping to reduce the need for manual knowledge acquisition and potentially…
Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data
TYTAN is a system that automatically constructs an analytic semantic schema from a relational database, with user-provided descriptions when available. It uses symbolic analysis and LLM-based semantic inference for…
What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)
The study compares two access modalities of a large language model (LLM), ChatGPT's chat UI and OpenAI's API, with and without web search enabled. The research shows that the accuracy of responses varies between the…
A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI
A study reviews 58 AI audits that focus on system integration, finding that while few measures address integration-specific risks and significant gaps remain in traditional audit expectations, integration can be…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
Researchers have developed a new framework called A-SR for symbolic regression. This framework uses a self-evolving agentic system that shifts control from expression edits to role-conditioned evidence views. It…
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
A research paper introduces a new framework called A-SR for symbolic regression. A-SR is designed to discover closed-form equations from data and uses a self-evolving agentic system that coordinates formula discovery…
CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs
The paper introduces CoPlan, a new AI system designed to aid in care planning. CoPlan allows various stakeholders like clinicians, patients, and caregivers to collaborate on complex decisions by generating potential…
Item Response Theory for AI Safety
The paper presents a study using Item Response Theory (IRT) to analyze the safety of language models. The authors find that three factors - refusal strictness, truthfulness, and contextual harm - explain most of the…
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
The research presents a new approach called OctoLong for creating longer contexts for language models. It uses an AST parser, a language server backend, and a package manager to retrieve code references from various…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
The paper introduces a new method called On-Policy Self-Distillation with Visual Modality Balance (OPD-V) to improve the visual reasoning of multimodal large language models. The authors argue that previous methods…
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
The text discusses a new benchmark called RepoProbe for evaluating the ability of Large Language Models (LLMs) to understand repository-scale code. The benchmark uses open-ended questions from GitHub Discussions and…
When Shared Rollouts Fail in Defensive Driving Evaluation: A NAVSIM Score Basis Audit
The study identifies a risk in NAVSIM v2.2 original scene single-stage scoring where reference-conditioned forgiveness can propagate shared reference failures into compliance credit, potentially leading to incorrect…
AI and Authenticity in Islamic Research: A Critical Evaluation of Generative AI Reliability, Hallucination, and Source Fidelity in Quranic, Hadith, and Fiqh Knowledge
This research evaluates six popular AI systems' ability to provide reliable, authentic Islamic knowledge. The study found that while these AI systems can be useful for introductory learning, they should not be treated…
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications
The paper introduces AISPA, a framework for auditing system prompts in AI systems to ensure user protection. The study analyzes 3,249 instructions from 88 commercial AI products and finds significant variation in…
AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis
AskChem is a system designed to make it easier for scientists and AI agents to find specific findings in chemistry literature by converting papers into atomic, typed claims that are grounded by their source DOI and a…
EgoGenesis: Egocentric World-Action Modeling with Online Anchored Projective Memory and Action-3D RoPE
The authors present a method called EgoGenesis for creating synthetic manipulation videos for embodied AI using egocentric video. The method uses a pretrained video generation prior and introduces two geometry-aware…
InfoOps Bench: A live information operations safety benchmark
The paper introduces an AI benchmark that measures the safety of language models against being manipulated for state-backed information operations. The benchmark uses data from a live monitoring pipeline tracking…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
The paper introduces MANTA, a framework for Multi-Agent Network Topology Adaptation that allows communication structures in large language model-based multi-agent systems to evolve during inference time. This…
ORCA-bench: How Ready Are Language Model Agents for Oncall?
Researchers introduce ORCA-bench, a new benchmark that tests the ability of large language models to perform root cause analysis (RCA) in a production-like setting. The benchmark includes a microservice system with six…
WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning
Researchers introduce WIDE, a dynamic token-level pruning framework for improving the efficiency of large language models (LLMs). The framework allows each token to select attention and FFN channel groups dynamically…
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Researchers have introduced a new framework for ontology matching called AgentMap. This framework can simultaneously discover both equivalent and subsuming mappings in ontologies, which existing systems cannot do. The…
Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility
Researchers have developed a new method for controlling large language models during scientific discovery tasks. The method, called CostAda, takes into account the costs associated with each action in addition to the…
Do Latent Channels Actually Communicate? A Causal Audit of Latent Multi-Agent LLM
Researchers have developed a method to evaluate if latent channels in large language models effectively communicate task-relevant information in multi-agent systems. The study applies this method to Qwen3 and Qwen3-8B…
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
MemSecBench is a new benchmark for testing the lifecycle security of agent memory systems. The benchmark contains 310 cases drawn from various contexts, and it follows a controlled protocol to test the persistence…
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.
