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 38 of 59
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
The text presents IdeaGene-Bench (IG-Bench), a new benchmark for evaluating AI systems' ability to follow the structure of scientific idea inheritance. IG-Bench is based on the IdeaGene framework, which represents each…
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
The paper proposes a method for machine learning that aims to align autonomous agents' behavior with human intent in diverse operational contexts by using a hierarchical machine teaching algorithm for reward learning…
OmniFood-Bench: Evaluating VLMs for Nutrient Reasoning and Personalized Health Advice
A new benchmark, OmniFood-Bench, is introduced to evaluate the performance of Large Vision-Language Models (VLMs) in nutrient reasoning and personalized health advice for dietary management. The benchmark assesses VLMs…
OpenCoF: Learning to Reason Through Video Generation
The paper introduces OpenCoF, a framework that includes a new dataset and a fine-tuned video model for improving Chain-of-Frame (CoF) reasoning in video generation. The authors argue that existing models lack specific…
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
The research proposes a lightweight plug-in called BioModule that can be added to any 3D pose estimator to predict biomechanical attributes from standard 17-joint 3D skeletons. It's trained and evaluated on an aligned…
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper presents ProjAgent, a system for generating code at the repository level that uses 'procedural similarity' as a new signal in the retrieval process. This system decomposes the target function into…
Psychological Competence as a Missing Dimension in AI Evaluation
The paper discusses the need to consider psychological competence as an important aspect in evaluating AI systems that interact directly with humans, particularly in roles like advisors, coaches, tutors, and…
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Researchers propose a proactive memory agent for long-horizon tasks, where decision-relevant information can get buried as trajectories grow. The memory agent updates a structured bank from the recent trajectory and…
Self-Adaptive Anomaly Detection with Reinforcement Learning and Human Feedback in Connected Vehicles
The paper proposes an online anomaly detection framework for autonomous cyber-physical systems (CPS), specifically connected vehicles, that combines three coordinated mechanisms: a deep Q-network with self-attention to…
SLORR: Simple and Efficient In-Training Low-Rank Regularization
The paper introduces SLORR, a simple and efficient in-training low-rank regularization framework for neural networks. It aims to improve compressibility without significant accuracy loss, while avoiding the limitations…
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
The paper proposes a new method for scheduling Language Model (LLM) requests called SMetric, which aims to improve the performance of serving agents in terms of tokens per second (TPS). The current methods prioritize…
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
The authors propose SolarChain-Eval, a benchmark for evaluating the trustworthiness of autonomous agents in decentralized energy markets. It assesses market utility, physical safety, slippage, action smoothness…
Swapping Faces, Saving Features: A Dual-Purpose Pipeline for Pedestrian Privacy in ITS
The paper focuses on creating a five-stage pipeline for protecting pedestrians' privacy in AI models used by autonomous vehicles (AVs) while maintaining the image attributes needed to train the models. The proposed…
The complexities of patient-centred conversational artificial intelligence
Researchers analyzed 2,053 conversations between patients and AI chatbots powered by large language models (LLMs) for symptom assessment. They found that communication patterns and emotional expressions vary widely…
The Context Access Divide: Interaction-Level Architecture as a Complementary Dimension of Agentic Inequality
The text introduces a new concept called the 'Context Access Divide' (CAD). This divide refers to the qualitative difference in AI utility experienced by two users who have similar access to AI agents, but one system…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
The authors of this paper introduce a new method to evaluate the effects of post-training quantization on large language models, as this technique is commonly used to deploy models in resource-limited settings. The…
Towards Precision Therapy in Hepatocellular Carcinoma: A Clinical-Reasoning LLM for Risk Stratification and Treatment Guidance
A large language model named HCC-STAR has been developed to provide personalized treatment recommendations, risk scores, and survival estimates for patients with Hepatocellular Carcinoma (HCC). The model reads through…
TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories
Researchers introduce TRACE, a watermark system for large language model (LLM) agents that can maintain its integrity even when resellers rebrand or substitute cheaper models. TRACE consists of two channels: a…
Two Axes of LLM Abstention: Answer Correctness and Question Answerability
A study finds that large language models often struggle with two types of errors: answering questions incorrectly and attempting to answer unanswerable or misleading questions. The researchers propose a method to…
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
UltraX is a new framework designed to improve the quality of large-scale pre-training data for Large Language Models (LLMs). It addresses the limitations of existing methods by offering fine-grained instance-level…
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
This study presents a large-scale analysis of an AI-based learning assistant called Syntea, used by 77,543 students in distance learning. The analysis examines usage patterns based on demographic and structural…
Validity of LLMs as data annotators: AMALIA on authority
A study tests the validity of a large language model (LLM), AMALIA, in measuring moral foundation concepts for European Portuguese. The study finds that while AMALIA agrees with human coders on these concepts, it does…
VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval
The text presents a new framework called VocaDet for open-vocabulary object detection and segmentation. This framework learns object concepts directly from user-provided positive and negative sample collections without…
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…
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.
