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 53 of 59
Einstein World Models
The text discusses a proposed system called Einstein World Models (EWMs) which aim to enhance the reasoning abilities of Language Model (LLM) by incorporating visual-temporal rollouts within the reasoning process…
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
Researchers introduce a new method called PEEU to improve the task planning capabilities of small, open-source multimodal web agents that assist humans in operating repetitive graphical user interface (GUI) tasks…
From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan
This research study explores the Wild West of AI-generated explicit content known as AI nudification on the anonymous online community 4chan. The authors identify over 24,000 such items and find that non-celebrity…
Heavy-Ball Q-Learning with Residual Weighting Correction
The paper presents a corrected version of Heavy-Ball Q-Learning for reinforcement learning, which is guaranteed to converge faster than standard Q-Learning under certain conditions. The analysis uses a switched linear…
How to evaluate clustering with ground truth?
The text discusses the use of external validation indexes for evaluating clustering algorithms when ground truth is available. It focuses on set-matching-based measures and recommends the Centroid Index (CI) as a…
In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics
The paper proposes a new method called In-Context Model Predictive Generation (ICMPG) for generating human motions based on textual descriptions in digital applications. The method combines language model planning with…
Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation
The study shows that Language Models (LLMs) fine-tuned for security classification may overlook vulnerabilities introduced during fine-tuning itself. These models can learn token-level indicator semantics that preserve…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
The paper introduces a new method called Joint Learning of Experiential Rules and Policies (JERP) for large language model agents operating in multi-step interactive environments. The main challenge addressed is…
Language-Based Digital Twins for Elderly Cognitive Assistance
Researchers propose using large language models (LLMs) to create digital twins that mimic the conversational behavior of elderly individuals, potentially aiding in early detection of Mild Cognitive Impairment (MCI)…
Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)
The text describes a prize-winning system for bimanual garment folding from the LeHome Challenge 2026. The system used a reinforcement learning loop to improve a vision-language-action (VLA) policy, placing first in…
Look-Before-Move: Narrative-Grounded World Visual Attention in Dynamic 3D Story Worlds
Researchers have developed a new camera planning framework called Look-Before-Move for embodied AI operating in dynamic 3D environments. The goal is to enable the camera to actively decide what to observe, not just…
NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Models
Researchers have created a new benchmark called NuclearQAv2 to evaluate the performance of large language models (LLMs) in the domain of nuclear engineering. This benchmark consists of about 1,240 question-answer pairs…
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
The paper introduces OpenRCA 2.0, a new benchmark for root cause analysis (RCA) that includes step-wise causal annotations for large language models (LLMs). The benchmark aims to test the capabilities of LLMs in…
Parametric Open Source Games
The authors introduce a new concept called parametric open-source games, which are continuous versions of game equilibria where players choose parameter vectors to determine their actions in an underlying finite game…
Prompt Injection in Automated Résumé Screening with Large Language Models: Single and Multi-Injection Settings
The study explores the impact of prompt injection, a self-promotional text strategy used by job applicants to manipulate automated hiring systems, on Large Language Models (LLMs) in résumé screening. The research shows…
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasoning Models
The paper introduces a new method called Reasoning-guided progressive Open Relation Extraction (ReaORE) to improve the extraction of unseen relations between entities in text for real-world applications. Current…
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Researchers propose a method for improving the safety of autoregressive image generation models, which generate images by sequentially predicting discretized visual tokens derived from a codebook. The proposed method…
Semantic Early-Stopping for Iterative LLM Agent Loops
The research proposes a method for stopping large language model loops (like drafting and revising) early, based on when consecutive drafts no longer change in meaning and the answer's quality stops improving. This…
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
The paper introduces ShareLock, a stealthy multi-tool threshold poisoning framework designed to exploit the interaction between Large Language Models (LLMs) and external tools through the Model Context Protocol (MCP)…
Simulation-based inference for rapid Bayesian parameter estimation in epidemiological models: a comparison with MCMC
A study compares two methods for estimating parameters in epidemiological models: Markov chain Monte Carlo (MCMC) and Simulation-based Inference (SBI). The authors use SBI with neural posterior estimation to analyze…
State Representation Matters in Deep Reinforcement Learning: Application to Energy Trading
Researchers studied how the representation of a state given to a reinforcement learning (RL) agent impacts energy trading decisions. They used a fixed Double DQN agent in a pumped-storage arbitrage environment and…
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
The Spec Growth Engine is a proposed framework to address two challenges in AI coding agents: context explosion and silent spec-code drift. It does this by creating a machine-readable spec graph, scoping agent context…
Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text
Researchers have developed a new method called GAversary, which uses a Genetic Algorithm (GA) and GloVe embeddings to generate adversarial attacks on natural language models. These attacks can significantly reduce the…
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
The study investigates the use of multi-model language models to improve accuracy over single-models. It is found that the improvement is limited by a factor called 'beta', which represents the rate at which all models…
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.
