Field notes
2,348 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.
2,348 notes and 295 topics.
- Question answered
- Source note
- Topic
- Shared notes
All notes, newest first
2,348 notes, page 11 of 98
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
The paper introduces Eureka, a Meta-Agent architecture that can complete long-horizon tasks by forming specialized Macro-Agents through receding-horizon planning and architecture promotion. The agents can evolve to…
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
The paper introduces Eureka, a meta-agent system designed for scientific discovery tasks. Eureka forms specialized agents through planning, promotion, and minimal-sufficient compilation, adapting to recurring…
Finetuning Strategies for Querying Sounds by Vocal Imitation
The authors describe their winning strategy for a sound effect querying competition in 2025, which involved two fine-tuning strategies: contrastive learning with a frozen pretrained CED encoder and joint…
From Threat Intelligence to Detection: Knowledge-driven Enrichment and Template-based Rule Grounding for Automated Sigma Rule Generation
The paper presents AUTOSIGMA, a system that automates the transformation of unstructured cyber threat intelligence (CTI) reports into relevant Sigma rules for threat detection. Instead of solely relying on language…
Graphical Design of Interpretable Architectures
The text discusses a new graphical notation for designing interpretable AI architectures, which addresses the limitations of existing representations. The proposed notation provides a global view of an architecture and…
Grouping the Stochastic Machine: Precision, Not Capability, as the Frontier Metric for AI Systems
The author argues that precision, rather than capability, should be the focus when comparing and measuring AI systems. Precision refers to how consistently an AI system performs the same task, while capability is where…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
The paper presents a new paradigm for continual learning called Harness Continual Learning (HCL). In this approach, an agent can adapt through a harness of prompts, memories, tools, skills, and routing rules. The…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
The paper 'Harness Continual Learning: Continual Adaptation Beyond Model Parameters' introduces a new approach to continual learning, focusing on the evolution of an agent's harness (which includes prompts, memories…
Identifying Implicit Premises for Logical Reconstruction of Argument Graphs
The authors propose a neuro-symbolic pipeline to generate implicit premises from natural language text, which can be translated into logical formulae to show the logical relationships between statements (entailment…
Interpretable AI predicts a 2026 summer dry anomaly in central China
Researchers have developed an AI model that predicts a dry anomaly in central China during the summer of 2026. This prediction is based on atmospheric circulation patterns, particularly a persistent cyclonic…
Metrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
Researchers developed a method called EvalCEGAR to automatically create an evaluation metric for AI agents in tasks like report generation, where traditional metrics are difficult to develop. The method involves…
MLREF: Efficient Module Reuse for Reward Design in Reinforcement Learning via Large Language Models
The research proposes a new framework called Module Level Reward Evolution Framework (MLREF) to address the issue of unreliable reward function preservation and reuse in reinforcement learning. MLREF uses a module…
ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery
The paper introduces ORBITER, a system designed to make decisions for last-mile delivery by couriers. It models the courier service through decision points and uses language models (LLMs) to reason about individual…
PGFS++: Molecular Property Improvement under Synthesis and Diversity Constraints
Researchers present PGFS++, an advancement of a previous method called PGFS for improving molecular properties like drug-likeness or binding affinity. The new method addresses limitations in PGFS by using trainable…
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors present a method to split large machine learning models into smaller parts called pipeline shards, which can then be run on multiple Integrated AI Processors (AIPCs) over an ordinary network. They show that…
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors propose a method to utilize multiple Intel AI PCs with integrated GPUs and NPUs, even when they have insufficient memory for large models like a 70B-parameter LLM. The method involves breaking the model…
Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets
The authors present a method to distribute Large Language Model (LLM) inference across multiple Intel AI PCs using pre-compiled pipeline shards. This allows for efficient use of idle AI PCs with integrated GPUs and…
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
The authors propose a system called rEDMRec that improves recommendation quality by compressing the reasoning of a large language model (LLM) into a compact, editable memory. This memory is maintained by an LLM memory…
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
The paper proposes a new approach for recommendation systems, called rEDMRec, which distills the reasoning of large language models into an editable memory that can be used to rank candidate items without regenerating…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The authors propose a new risk measure called the Wasserstein entropic value-at-risk (WEVAR). This measure is designed to address the limitations of the traditional entropic value-at-risk, particularly in terms of…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The paper proposes a new risk measure called Wasserstein Entropic Value-at-Risk (WEVaR) for an agent learning its environment. The WEVaR is designed to account for the reachable catastrophes that the current entropic…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The authors propose a new risk measure called Wasserstein Entropic Value-at-Risk (WEVaR). This measure is designed to help an agent navigate uncertain environments by being cautious when it's unsure and bold when it's…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The study explores the ability of large language models (LLMs) to extract contextualized information from research articles efficiently. The authors present four workflows that demonstrate LLMs can perform well in data…
Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
The paper investigates the performance of large language models (LLMs) in extracting contextualized information from research articles, finding that while LLMs can perform well with expert-curated prompts, they may…
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.
