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 55 of 59
Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz
This research paper presents a Multi-Agent System (MAS) architecture with Hybrid Retrieval Augmented Generation (HybridRAG) for partially automating IT-Grundschutz certification, a German standard for IT security. The…
Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models
A study finds that using low-bit quantization to reduce the cost of large language models can lead to longer chains of thought, which offsets the expected per-token speedup in reasoning tasks. The study introduces a…
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment
Researchers have proposed a framework called SARA (Semantically Anchored Routing Alignment) to improve the performance of multilingual language models in low-resource languages. The framework aligns the routing…
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
The researchers propose a method called Semantic Consistency Policy Optimization (SCPO) to address a problem in reinforcement learning of LLM agents. The issue is that these agents are trained for long-term, sparse…
SpeechEQ: Benchmarking Emotional Intelligence Quotient in Socially Aware Voice Conversational Models
The paper introduces SpeechEQ, a framework designed to evaluate the sociolinguistic reasoning of Speech-Language Models (SLMs) in multi-turn dialogues. The framework includes a dataset and evaluation protocol for…
Staying In Character: Perspective-Bounded Memory For Book-Based Role-Playing Agents
Researchers propose a three-layer memory architecture named REVERIEMEM for book-based role-playing agents to address the issues of Factual Overreach and Stylistic Monotony in current LLM role-playing systems. The…
The impact of artificial intelligence on enterprise software user roles
This research study explores how Artificial Intelligence (AI) is impacting the roles of users in enterprise software development, specifically focusing on SAP's Business Technology Platform (BTP). The study involves…
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
The authors present the Unfireable Safety Kernel, a Rust implementation that serves as an execution-time AI alignment layer for escapable AI systems. This system aims to provide authorization mechanisms for controlling…
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Researchers have developed a benchmark called Argus to test the reliability of computer-use agents that convert vision-language model predictions into executable clicks. The study compares 27 methods across four…
Variable Bound Tightening for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games
A new method is presented for solving exact Nash equilibria in multiplayer imperfect-information games, which improves upon previous algorithms by using finite bounds on slack and multiplier variables in the nonlinear…
Weave of Formal Thought
The paper introduces Weave of Formal Thought (WoFT), a new paradigm for large language models that combines syntactic validation with learned structural representations. The proposed approach includes a formal engine…
WinDOM: Self-Family Distillation for Small-Model GUI Grounding
Researchers present WinDOM, a large dataset of bounding box training data for small GUI-grounding agents, which can be used for on-device deployment, accessibility tooling, and low-cost iteration. They also introduce…
Shared Infrastructure, Isolated Tenants: Pool Model Multi-Tenancy with Amazon Bedrock AgentCore
AWS demonstrates production-ready multi-tenant AI agent patterns using Bedrock AgentCore, illustrated through a healthcare use case serving multiple clinics and hospitals. The post covers pool model multi-tenancy with…
A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial
Researchers have developed a specialized language model called RaDaR (Rare Disease navigatoR) to assist in the diagnosis of rare diseases. The model, which has 32 billion parameters, was trained on both publicly…
Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
Researchers examined the accuracy of Large Language Model (LLM)-based dialogue assistants in handling Non-Functional Requirements (NFRs) related to Health Insurance Portability and Accountability Act (HIPAA) regulatory…
AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
The paper introduces AdversaBench, a red-teaming pipeline for evaluating large language models. The pipeline generates hard inputs using five structured operators and confirms failures through a three-judge panel with…
AI-PAVE-Br: Leveraging Large Language Models for Enhanced Product Attribute Value Extraction through a Golden Set Approach
The paper presents AI-PAVEBr, a system that uses large language models to extract product attribute values from Brazilian e-commerce catalogs. It also introduces the Golden Set, a new dataset in Portuguese for product…
Q&A: What Are the Latest Activity Patterns in AI?
What are the latest themes/activity patterns in AI? TL;DR from vault.
ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
The paper introduces a new method called ASALT for multi-agent reinforcement learning (MARL). This method is designed to handle situations where the state-space dimensionalities between source and target domains don't…
Bayesian control for coding agents
The paper proposes a Bayesian controller for coding agents that make decisions based on a belief over candidate correctness, rather than fixed rules. This method is found to be most useful when verification is costly…
Beyond U-Net: A Latent-Representation-Aligned Skip-Free Backbone for Flow-Matching Speech Enhancement
The authors propose a new method for speech enhancement using flow-matching, which is more efficient than generative models with iterative sampling processes that limit real-time deployment. Their approach involves a…
BluTrain: A C++/CUDA Framework for AI Systems
BluTrain is a C++/CUDA training framework for AI systems that provides better throughput and memory efficiency compared to industry-standard baselines like PyTorch in training a 124M-parameter GPT-2 model.
Can Scale Save Us From Plasticity Loss in Large Language Models?
Researchers study plasticity loss in GPT-style transformer models trained on a multilingual continual learning problem. They find evidence of plasticity loss across different sizes of models and under stationary…
Decentralised AI Training and Inference with BlockTrain
The paper introduces Spheroid BlockTrain, a decentralized AI training protocol that partitions a model into independent blocks, each optimized on a local objective derived from the same global target. The protocol is…
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.
