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 17 of 98
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
A multimodal benchmark and training setup for agents that generate and evaluate business ideas using visual evidence.
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
Researchers have developed a system called Mechanist that uses AI to autonomously discover the mechanisms underlying AI intelligence. The system is built on an interpretability-focused knowledge graph of around 13,000…
Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence
The study introduces Mechanist, an AI system designed to autonomously discover the mechanisms behind AI intelligence. It uses a knowledge graph of approximately 13,000 papers integrated with a multidisciplinary…
NetlistBench: Evaluating LLM Reliability in SPICE Netlist Recognition and Manipulation
Researchers present NetlistBench, a new benchmark for evaluating the reliability of Large Language Models (LLMs) in SPICE netlist recognition and manipulation tasks. The study finds that while LLMs perform well on…
No One to Blame: A Framework of Constitutive AI Unaccountability
The paper 'No One to Blame: A Framework of Constitutive AI Unaccountability' argues that certain configurations of actors, systems, and institutions make AI accountability unachievable, no matter the effort put into…
No One to Blame: A Framework of Constitutive AI Unaccountability
Researchers have proposed a new framework called 'constitutive AI unaccountability' to address challenges in traditional accountability mechanisms with the increasing deployment of autonomous AI systems. This framework…
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
The paper discusses a common issue in multi-agent reinforcement learning for human-AI interaction: using a single large language model (LLM) to simulate user behavior often results in the LLM focusing on specific…
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
The paper discusses a common issue in multi-agent reinforcement learning (MARL) for human-AI interaction: relying on a single large language model to simulate user behavior often leads to poor generalization due to…
Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations
The research presents a new framework called Preference Tree Optimization (PTO) for enhancing dialogue systems in specialized domains with limited data. It focuses on Motivational Interviewing (MI), a counseling…
Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations
Researchers propose Preference Tree Optimization (PTO), a framework that enhances dialogue systems in specialized domains like Motivational Interviewing by using preference data generated through Look-Ahead Simulations…
Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
The research focuses on optimizing the use of GPUs in LLM-agent services by identifying a boundary for concurrent work (ready cohort) and investigating the impact of keeping GPU-computed decisions on device instead of…
Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control
The paper discusses a method for determining when it's beneficial to execute small deterministic transitions between model and tool calls on GPUs, and presents a dynamic program that computes the optimal amount of work…
RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
A new benchmark called RealisticTritonBench was introduced to test the ability of large language models (LLMs) to generate GPU kernels for real-world AI frameworks. This benchmark addresses limitations in previous…
RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks
Researchers have introduced a new benchmark called RealisticTritonBench to improve the evaluation of large language models (LLMs) in generating GPU kernels for AI frameworks using Triton. The new benchmark derives…
Redistribution-based Cost Inference Improves Sparse Safe Offline RL
A new framework called Redistribution-based Cost Inference (RCI) is proposed to convert sparse stop-feedback in safe offline reinforcement learning into dense per-step costs. This conversion helps train a constrained…
Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection
The paper presents a framework called BENCH2ROBUST, which converts reliable tool-use benchmarks into controlled stochastic environments with failure scenarios. The authors test two interventions to improve the…
Retry, Switch, or Abstain? Learning Strategy-Aware Tool-Use Policies via Controlled Error Injection
Researchers present BENCH2ROBUST, a framework for converting reliable tool-use benchmarks into stochastic environments with controlled solvability. This allows study of agent's response to tool failures, which can be…
Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages
The paper discusses how AI tools for education and language support can disadvantage speakers of underrepresented languages before training, using Bengali as a case study. The authors identify four main issues: a web…
Structural Silence: When AI Infrastructure Fails Speakers of Underrepresented Languages
The authors discuss how the underlying infrastructure of AI tools designed for education and language support can disadvantage speakers of underrepresented languages, using Bengali as an example. They highlight four…
VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
The researchers introduce VAKRA, a benchmark for evaluating the ability of agents to reason across structured APIs and document collections in enterprise settings. The benchmark includes over 8,000 executable APIs…
VAKRA: Evaluating Multi-Hop Reasoning Across APIs and Retrieval Under Tool-Use Policies
The study introduces VAKRA, a benchmark for evaluating the ability of agents to reason across APIs and document collections in enterprise settings. The benchmark includes over 8000 executable APIs across 62 domains…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
The paper introduces VICBench, a new benchmark dataset for evaluating code vulnerability detection tools. VICBench contains 100 verified vulnerability-inducing commits (VICs) across 88 projects in Python, Java, and…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
Researchers have created a benchmark dataset called VICBench for evaluating code vulnerability detection tools. The dataset contains 100 verified vulnerabilities across 88 projects in Python, Java, and C++, covering 48…
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
The paper introduces VICBench, a multi-language benchmark for code vulnerability detection. It was created by human experts and an agentic workflow, featuring 100 verified vulnerabilities across 88 projects in Python…
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.
