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.
9 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on machine learning models
9 notes
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…
A First Look at Coding Agents' Compliance with AI Contribution Rules in Open-Source Communities
Researchers studied whether AI agents comply with contribution rules in open-source communities. They found that the AI agents do not proactively retrieve the rules but improve with reminders, quotes, or feedback…
Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation
A study using OpenAI's gpt-5.6-sol model found that the model gave different advice when presented with a dangerous objective directly compared to when other agents transformed and relayed the direction. When shown an…
PhaseAware: Interpretable Human-in-the-Loop Rehabilitation Scoring with Boundary Monitoring
The study introduces PhaseAware, a framework designed for continuous evaluation of rehabilitation quality during physical therapy sessions. It combines temporal data with phase-specific and body part descriptors to…
CommuniWave:A Machine Learning Model for Quantifying the Degree of Temporary Informal Behavior in Urban Communities
Researchers have developed a machine learning model named CommuniWave. This model aims to help urban managers and designers by efficiently detecting and quantifying temporary informal behaviors in urban communities…
TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories
The paper introduces TRACE, a new agent watermark system designed to withstand manipulation by resellers who may alter or replace an original agent. The system works by embedding two channels into the agent's behavior…
WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving
Researchers propose WCog-VLA, a dual-level model for autonomous driving, which combines semantic world forecasting and generative world evolution to bridge the gap between reactive and proactive driving. The semantic…
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Researchers collect and release a dataset of approximately 4,300 coding-agent sessions from their own use of Claude Code and Codex. The data shows that coding-agent workloads feature long autonomous loops, long…
Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning
The research introduces a method called Planning Experience Exploration and Utilization (PEEU) to improve the task planning capabilities of smaller open-source Multi-Language Model Learning Machines (MLLMs). These…
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.
