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.
235 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on machine learning
235 notes, page 2 of 10
Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction
The paper introduces Hypothesis Frontier, a framework that uses a combination of language models (LLMs) and symbolic processing to solve first-order concept synthesis problems. The system iteratively generates and…
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
Researchers introduce Visual Skill Cards (VSCs), a new method for improving the decision-making abilities of computer agents in GUI environments. VSCs are memory representations that bind reusable procedures with…
SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
SkillZip is an evaluation-free method that helps compress skills by identifying their shortest faithful structural explanations, making it easier to reuse common action sequences without needing to repeat them. This…
Two-stage Odd Residual Flows for Mean-Preserving Probabilistic Time Series Forecasting
Researchers propose a new method called Two-stage Odd Residual Flows (TORF) for probabilistic time series forecasting. The method aims to address the trade-off between distributional flexibility and accurate mean…
V-FiLLM: Verified Financial LLM Reasoning Benchmark
Researchers have created a new framework called V-FiLLM to evaluate the abilities of Language Models (LLMs) in financial reasoning using structured data. The framework generates questions from executable computation…
Whisper-Aware LLM: Self-Supervised Uncertainty Learning for Robust Whispered Speech Recognition
The Whisper-Aware LLM is a new framework designed to improve the performance of ASR (Automatic Speech Recognition) systems for whispered speech. The model learns to perceive and react to the uncertainty associated with…
Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding
The paper discusses the growth of Agentic coding README files like CLAUDE.md in real repositories and attributes this to imperfect recall. The authors refer to this phenomenon as 'catastrophic remembering'. They find…
Agentic Auto-Research is Fuzz Testing
The authors argue that current methods for autonomous research agents are inefficient due to the slow validation process of generated experiments. They propose to adapt fuzzer techniques, which use feedback from…
NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation
The study introduces a new method called NeuroRefiner for accurately segmenting neurons in 3D fluorescence microscopy images. The method overcomes challenges posed by the sparse and elongated morphology of neurons…
Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach
Researchers propose a new method for fine-tuning large language models in a federated learning paradigm using Low-rank adaptation (LoRA). They investigate two strategies, Share-A/Local-B and Share-B/Local-A, and reveal…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
A research paper proposes a new method for document search called Reliable Embedding-free Agentic Document-search (READ), which is designed to overcome limitations in current methods for long documents, particularly…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The authors propose a new method for document search called READ (Reliable Embedding-free Agentic Document-search). This method uses an interpretable agent that performs three operations: normalized lexical search…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The paper proposes a new approach for document search called 'READ (Reliable Embedding-free Agentic Document-search)', which aims to address the issues with current black-box retrieval designs in handling long…
Beyond Top-K: Replacing Black-Box Retrieval with Interpretable Agentic Operations
The authors propose a new method for document search called Reliable Embedding-free Agentic Document-search (READ). In contrast to the common design of retrieval-augmented generation, READ uses an agent that reads the…
Challenges in Evaluating Explanation Methods for Static and Evolving Data
The paper discusses the limitations in evaluating Explainable Artificial Intelligence (XAI) systems, specifically focusing on the DetoxAI image recognition system. It highlights the need for better evaluation methods…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The study compares two systems for deciding which skills to load from a large skill library by an agent. The first system is a hybrid ranker that combines lexical and dense-embedding retrieval, while the second system…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The study compares two systems for deciding which skills to load from large skill libraries in AI agents. The first system is a hybrid ranker that combines lexical and dense-embedding retrieval for sparse, on-demand…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The research compares two systems for deciding which skills to load from a large skill library when creating agents. One system combines lexical and dense-embedding retrieval, while the other uses a typed knowledge…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
Researchers compared two methods for deciding which skills to load from large skill libraries in AI agents: a hybrid ranker combining lexical and dense-embedding retrieval, and a typed knowledge graph encoding workflow…
Contextual Information Policy Optimization for Search Agents
The text introduces a new method called Contextual Information Policy Optimization (CIPO), which aims to improve the reliability of search agents by ensuring they use retrieved evidence effectively during multi-step…
Contextual Information Policy Optimization for Search Agents
The researchers propose a new reinforcement learning framework called Contextual Information Policy Optimization (CIPO) to improve the reliability of search agents for knowledge-intensive tasks. CIPO encourages the use…
Does FLAIR super-resolution erase or hallucinate small white-matter lesions?
The study investigates whether using super-resolution (SR) techniques on Fluid-attenuated Inversion Recovery (FLAIR) scans affects the detection of small white-matter lesions. The research finds that SR tends to erase…
FinEvo-Bench: A Longitudinal Benchmark for Self-Evolving Agents in Professional Financial Workflows
The research introduces a new benchmark called FinEvo-Bench for evaluating the performance of self-evolving agents in professional financial workflows. The benchmark consists of 120 real-case-grounded tasks across six…
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Researchers have introduced HarnessOpt-Bench, a benchmark to measure the performance of Large Language Models (LLMs) in optimizing their own harnesses (the prompts, tools, etc. surrounding them). The research shows…
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.
