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.
5 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on training methods
5 notes
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Researchers introduce a new method called Top-K prompting to train language models for single-step retrosynthesis, a crucial component of computer-aided synthesis planning. They use an ultra-large dataset of verified…
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
The paper introduces Visual Skill Cards (VSCs), a memory representation that helps computer agents make decisions by binding reusable procedures with applicability cues, visual evidence, and verification signals. The…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Researchers have proposed a new method called Answer-Backtracked Credit Assignment (ABC) to train long-horizon search agents more effectively. This method converts sparse trajectory-level outcomes into dense step-level…
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Researchers propose a method called Answer-Backtracked Credit Assignment (ABC) to train long-horizon search agents more effectively. This method converts sparse trajectory-level outcomes into dense step-level…
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
The authors propose a new training paradigm called PATS for reinforcement learning agents that learn long-term tasks. PATS converts rollout groups from the latest policy into evidence cards and adjusts the context used…
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.
