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 41 of 59
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail
Researchers present DT-Guard, a content safety guardrail model for large language models in open-world applications. The model uses a Reasoning-Active Training, Reasoning-Free Inference paradigm and aims to improve…
EcoVision: AI-Powered Drone Imaging for Salt Marsh Vegetation Monitoring and Dominance Mapping
A new AI-powered drone imaging system called EcoVision has been developed for monitoring and mapping the dominance of two types of halophytic grasses in salt marshes. The system uses high-resolution RGB images from…
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs
The researchers evaluate the performance of uncertainty estimation methods across 22 languages in high-, mid-, and low-resource settings using two human-curated question and answer datasets. They compare open and…
Finding H. pylori in the Fine Print: Evidence-Linked Multi-Agent Case Finding from Gastric Biopsy Reports
Researchers evaluated a system called nMAS for extracting information from gastric biopsy reports to identify Helicobacter pylori infection. The system achieved high accuracy in classifying samples, and could…
FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference
The paper introduces FreqDepthKV, an inference-time cache compression method for long-context LLM (Large Language Model) inference that reduces memory and bandwidth costs while maintaining task accuracy on various…
From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution
The paper proposes a theoretical framework to integrate higher-order cognitive architectures into a native meta-architecture for large language models (LLMs). This is achieved by introducing three mechanisms…
From Voting to Agent Collaboration: Answer-Type-Aware LLM Pipelines for BioASQ 14b
A study presents a framework for improving the accuracy and reliability of biomedical question answering by using a large language model (LLM) that adapts its inference strategies based on the type of question (yes/no…
Harnessing Code Agents for Automatic Software Verification
A new method using a general language model code agent and a verification harness proves all targeted lemmas in Iris, Rust's standard libraries, and unfinished Lean 4 port of Iris, achieving full coverage without any…
Improving LLM-Generated Process Model Quality Through Reinforcement Learning: The Role of Reward Function Design
Researchers have improved the quality of process models generated by large language models (LLMs) using reinforcement learning (RL). They found that designing the reward function is crucial for optimizing beyond the…
Industry Classification of GitHub Repositories Using the North American Industry Classification System (NAICS)
Researchers have developed NAICS-GH, a corpus of 6,588 GitHub repositories labeled with industry sectors according to the North American Industry Classification System (NAICS). The labels are generated using a pipeline…
Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents
The paper presents Information Gain-based Rollout Policy Optimization (IGRPO), a new framework for improving large language model agents in long-horizon search tasks. IGRPO aims to allocate rollout budget more…
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
This research investigates the performance of large language models (LLMs) in collaborative decision-making tasks where information is not fully available to all agents. The study introduces a benchmark for such tasks…
LongCrafter: Towards Diverse Long-Context Understanding via Evidence-Graph-Guided Instruction Synthesis
LongCrafter is a framework designed to enhance the understanding capabilities of large language models by synthesizing long-context supervised fine-tuning data. It addresses three limitations of existing methods…
Multi-Agent Deep Reinforcement Learning for Multi Objective Battery Management in Dairy Farms
The paper proposes a multi-objective optimization control system for battery management in dairy farms using differential evolution and multi-agent deep reinforcement learning. The system aims to improve profits from…
Rethinking Indic AI from a Lens of Cultural Heritage Preservation
The paper 'Rethinking Indic AI from a Lens of Cultural Heritage Preservation' discusses how Artificial Intelligence (AI) impacts India's linguistic and cultural foundations, focusing on the challenges and opportunities…
RMISC: A Large-scale Real-world Multivariate Corpus for Time Series Foundation Models
The paper presents RMISC, a large-scale, high-quality, open-access corpus of real-world multivariate time series data. The researchers pretrain four advanced Time Series Foundation Models (TSFMs) on univariate…
RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
The authors propose a framework called RSF-GLLM to improve Multi-hop Question Answering over Knowledge Graphs. The framework decouples differentiable graph reasoning from answer generation, allowing the system to learn…
RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications
The paper introduces RuBench 1.0, a new benchmark for coding agents that uses tasks specified in Russian rather than English. The benchmark is designed to measure the performance of coding agents when they are given…
Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows
Researchers introduce a new benchmark called Spider 2.0-AIFunc to test the ability of language models to generate AI-native SQL queries on large cloud data platforms. The benchmark includes 465 verified instances…
Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval
The authors propose a method called SkillReranker to improve the ability of agent systems to complete complex tasks by accurately selecting skills from large libraries. The method involves semantic decomposition of…
The Large Cancer Assistant (LCA): A Model-Agnostic Orchestration Framework for Scalable Clinical Decision Support in Oncology
The Large Cancer Assistant (LCA) is a proposed framework designed to improve the scalability of clinical decision support systems in oncology. It aims to address the rigidity of current multimodal deep learning models…
TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
The paper introduces TopoBrick, a framework for zero-shot forecasting of Internet-of-Things (IoT) data in buildings, which does not require training and takes into account the physical topology, spatial hierarchy, and…
UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation
Researchers have introduced UI2App, a new benchmark focused on evaluating the ability of large language models to recover application behavior from screenshots alone, without any textual or behavioral guidance. The…
VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection
The paper introduces VendorBench-100, a benchmark for evaluating deepfake image detection models across three paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. The…
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.
