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 36 of 59
A Minimalist Retargeting-Guided Reinforcement Learning Recipe for Dexterous Manipulation
Researchers introduce REGRIND, a method that enables robots to learn dexterous manipulation policies from a single human demonstration. The method retargets hand-object motion to a robot reference and trains an RL…
A Multimodal Dataset for Large Language Model Applications in the Energy Domain
The paper introduces a new open-access dataset called mAIEnergy which is a multimodal corpus designed to support Large Language Model (LLM) applications in the energy sector. It contains various types of data including…
Active Offline-to-Online Reinforcement Learning
Researchers propose an active policy selection method for fine-tuning in offline-to-online reinforcement learning (O2O-RL) settings, where the goal is to allocate a limited online interaction budget effectively among…
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
Researchers have developed a new method called AHA for automated red-teaming of production language models like Claude Code and Codex. This method uses one agentic research environment to discover reusable…
Agentic Routing: The Harness-Native Data Flywheel
The authors propose a new method for routing large language model agents called Harness-Native agentic routing. This method selects either a single best-fit model or multiple complementary models based on the full…
Agentic Skill Optimization over Lie Algebroids
The text introduces LASKO, a new framework for optimizing skills in agentic systems. LASKO models skills as structured artifacts and edit policies as sections of a Lie algebroid. The framework achieves significant…
An Explainable Agentic System for Detection of Conversational Scams with Summary-Based Memory
The paper presents an 'explainable agentic system' for detecting conversational scams over multiple messages, which existing systems often fail to do effectively. The new system achieves high accuracy in both…
Auditing the Risk Claims of Distributional Reinforcement Learning
In a study titled 'Auditing the Risk Claims of Distributional Reinforcement Learning', Hari Prasad investigates whether the risk claims made by distributional reinforcement learning agents are accurate. The study finds…
AutoMatBench: An Automatic Optimization Toolkit for the Acceleration of Material Properties Prediction Benchmarking
The paper presents AutoMatBench, an automatic optimization toolkit that addresses the limitations of MatBench, a widely used material property prediction benchmarking tool. MatBench lacks the ability to reflect the…
BackgroundMellow: A Multi-Modal Cohesive Framework for Narrative-Driven Rich Cinematic Soundscape Generation
The paper presents BackgroundMellow, a new framework for generating synchronized and immersive audio for long-form narratives. The framework treats sound generation as an orchestration problem and uses a…
Evaluating RE Practices for Explainability: Synthesizing Insights from Daimler Truck into an Explainable RE Framework Proposal
This research paper reports early findings from an ongoing study investigating how requirements engineering (RE) practices support explainability in AI-based systems, particularly in the industrial context of Daimler…
Evidence-Backed Video Question Answering
The authors propose Evidence-Backed Video Question Answering (E-VQA), a new task that requires models to not only provide answers but also the specific spatial and temporal evidence from videos. They introduce…
Extending LLM Context via Associative Recurrent Memory
In this research, the authors propose a new method called Associative Recurrent Memory Transformer (ARMT) to extend the context length of large language models (LLMs). This is crucial for many real-world applications…
From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
The paper proposes a roadmap for developing artificial general intelligence that can reason and act in the physical world. The authors identify three gaps in current progress: inconsistencies in model roles…
HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference
The paper proposes HCRMap, a framework for managing hot expert replicas in 3.5D Mixture-of-Experts (MoE) inference systems. The aim is to dynamically place and reuse hot experts across different memory tiers to…
Heuristic Learning for Active Flow Control Using Coding Agents
A new method for active flow control is proposed in this research paper. Instead of optimizing neural network parameters, the authors use coding agents to search directly for explicit executable feedback laws. The…
Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias
A research study presents an approach to understanding and mitigating bias in large language models (LLMs) used as judges, focusing on the hidden state of these models rather than just their input-output level. The…
Introducing Human-Centeredness in AI-Assisted Lexicography
This research introduces a framework for using AI in lexicography that prioritizes human involvement and understanding. The framework addresses concerns about the impact on lexicographers' roles and linguistic…
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks
The authors present a theoretical framework explaining the development of inductive reasoning abilities in Transformer language models. This framework applies to a wide range of inductive tasks and provides insights…
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
Researchers proposed a new method for improving the accuracy of decoding continuous three-dimensional motor imagery signals using non-invasive EEG-based BCIs. They introduced a two-stage decoding framework that applies…
LightMem-Ego: Your AI Memory for Everyday Life
The research paper introduces LightMem-Ego, a lightweight multimodal memory system designed for AI assistants on mobile and wearable devices. The system continuously captures and organizes egocentric visual and audio…
LoRA-Based Cascaded Multimodal Fusion for Action Recognition in Medical Training Environments
The paper introduces a new framework for recognizing actions and activities in medical training environments using a cascaded Low-Rank Adaptation (LoRA)-based multimodal fusion approach. This method allows for the…
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
The paper presents MAGIC, a system that generates connected multi-scene game worlds using large language models. The system overcomes three challenges in single-scene methods: cross-scene consistency, in-scene…
Metacognition in LLMs: Foundations, Progress, and Opportunities
This paper provides a comprehensive overview of metacognition in Large Language Models (LLMs), highlighting the importance of this aspect for effective learning, problem solving, and communication. It discusses recent…
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.
