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.
14 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on ml
14 notes
An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
The study presents a three-step approach for integrating data collection, processing, and predictive modeling in travel behavior research using conversational surveys, machine learning, and large language models…
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…
Multimodal Model Diffing for Feature Discovery and Control
Researchers developed a framework called MMDiff to help understand, control, and audit the behavior of Multimodal Large Language Models (MLLMs). The framework identifies features that are altered by multimodal…
ORCA-bench: How Ready Are Language Model Agents for Oncall?
The paper introduces ORCA-bench, a benchmark for testing the performance of large language models in oncall root cause analysis (RCA). The benchmark includes a live microservice system with six days of metrics, logs…
MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models
Researchers introduce MADA-RL, a framework that improves reasoning performance in compact models (up to 4 billion parameters) while reducing training cost. This is achieved by specializing the models into generator and…
Concept-Guided Spatial Regularization for World Models in Atari Pong
Researchers evaluated five world model agents in Atari Pong and found failures in visual and dynamical aspects of the generated trajectories by these agents. They propose a method called Concept-Guided Spatial…
Reachability-Aware Pretraining for Efficient Target-Oriented Path Exploration in Temporal Knowledge Graph Reasoning
The authors propose a new method called RAPTOR for improving the efficiency of target-oriented path exploration in temporal knowledge graphs (TKG). The method injects a reachability-aware inductive bias to the agent…
Experience Memory Graph: One-Shot Error Correction for Agents
Researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. Instead of using prompt-based…
Experience Memory Graph: One-Shot Error Correction for Agents
The researchers propose a new framework called Experience Memory Graph (EMG) to help large language model agents recover from failures more effectively in complex, long-horizon tasks. EMG reformulates failure recovery…
TREK: Distill to Explore, Reinforce to Refine
The paper proposes a method called TREK (Teacher-Routed Exploration via Forward KL) to improve Group Relative Policy Optimization (GRPO). TREK uses distillation for exploration support expansion and can work with…
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Researchers propose Task-Agnostic Pretraining (TAP), a two-stage framework to train Vision-Language-Action (VLA) models. TAP first learns transferable motor priors from unlabeled interaction data using self-supervised…
Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
The paper 'Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents' discusses the concept of always-on agents, which are systems that have a durable state accumulated from past interactions…
UNKNOWN
The text does not provide a summary.
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
The paper introduces OpenRCA 2.0, a new benchmark for root cause analysis (RCA) of Large Language Models (LLMs). The new dataset, OpenRCA 2.0, includes 500 instances and is the first cross-system RCA benchmark with…
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.
