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 7 of 10
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
The paper proposes ProjAgent, a system for generating code at the repository level. It introduces 'procedural similarity' as a new way to retrieve relevant functions, addressing a limitation of existing methods that…
SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling
The paper proposes SMetric, a new scheduling method for Large Language Models (LLMs) in serving agents. The method aims to balance the session-centric workload of agents and increase Key-Value (KV$) reuse by…
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
This research study introduces a new metric, called 'correctness agreement', to evaluate the impact of post-training quantization on large language models. The authors show that even when task performance seems…
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
UltraX is a new framework designed to improve the quality of large-scale pre-training data for Large Language Models (LLMs). It addresses the limitations of existing methods by offering fine-grained instance-level…
MIRA-Math: A Benchmark for Minimal Information Requesting and Mathematical Reasoning
The researchers introduce MIRA-Math, a benchmark for testing AI models' ability to ask for and integrate missing facts to solve mathematical problems. The benchmark contains 2310 instances from 22 mathematical families.
Physics-Audited Agentic Discovery in Scientific Machine Learning
The paper introduces Physics-Audited Agentic Scientific Machine Learning (PA-SciML), a new workflow that verifies the accuracy of surrogate models discovered by large language model agents in scientific machine…
Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents
Researchers study a failure mode in tool-using Language Model (LLM) agents, where they violate policies without appearing to do so, leading to silent errors such as cancelled bookings or unverified claims. A…
Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26
The authors present Reward-Adaptive Iterative Discovery (RAID), a new approach for automated game testing using Reinforcement Learning (RL) in the gaming industry. The case study is based on EA SPORTS NHL 26's…
RLVP: Penalize the Path, Reward the Outcome
The paper 'RLVP: Penalize the Path, Reward the Outcome' by Bojie Li and Noah Shi proposes a method for training artificial agents to perform tasks effectively in real-world environments. This method addresses two main…
SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents
The paper introduces SkillCenter, a large-scale skill library for autonomous AI agents, containing 216,938 structured skills across 24 domain bundles. The skills are obtained from various sources like peer-reviewed…
Stability of Flow Models for Graph Signals
The paper presents research on the stability of continuous flow models for generating signals on graphs. The authors analyze normalized flow models parameterized by Graph Neural Networks (GNNs) and demonstrate that…
SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation
Researchers have developed a method called SynthAVE to generate large amounts of labeled data for e-commerce attribute extraction using synthetic labels validated by multiple large language models (LLMs). The benchmark…
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
The researchers explore the impact of biased judges in self-evolving agents, focusing on skill retirement, a mechanism that helps maintain the quality of an agent's knowledge base by retiring poorly performing skills…
When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
The paper proposes ARGTCA, a method to improve the calibration of Vision-Language Models (VLMs) by using Graph Attention Networks to capture inter-attribute dependencies and reduce overconfidence during test-time…
An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery
The researchers propose an experimental design framework to systematically evaluate the autonomous model discovery behavior of large language model coding agents, like Codex and Claude Code. The framework considers…
DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression
The research introduces DepthWeave-KV, a new cache compression method for long-context language models. This method adapts to the needs of different tokens by factorizing key and value states across neighboring…
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…
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…
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…
TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
The paper introduces TopoBrick, a new framework for forecasting IoT data in buildings without requiring training. It uses building knowledge graphs to create a structural skeleton and employs an agentic topology…
Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification
Researchers developed a machine learning model that can classify transient candidates in time-domain surveys, known as Real-Bogus classification, without needing human-labeled data. The model is trained using simulated…
LLM-as-a-Verifier: A General-Purpose Verification Framework
In this research, a general-purpose verification framework called LLM-as-a-Verifier is introduced. This framework provides detailed feedback for agentic tasks without requiring additional training. The framework…
Localized LoRA-MoE: Block-wise Low-Rank Experts With Adaptive Routing
In this research, the authors propose Localized LoRA-MoE, a framework that combines localized spatial blocking with dynamic, context-conditioned routing for Large Language Models (LLMs) and high-dimensional perception…
Multiplayer Interactive World Models with Representation Autoencoders
Researchers present a new model for multiplayer interactive worlds, specifically designed for complex environments like Rocket League with fast-paced, coupled dynamics. The model is trained on 10,000 hours of gameplay…
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.
