Vishnu Sarukkai — accepted AI-conference papers

2025

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

Vishnu Sarukkai, Zhiqiang Xie, Kayvon Fatahalian

NeurIPS 2025poster

Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering—custom prompts, curated examples, and specialized observation/action spaces. We investigate a different approach where agents automatically improve by lea…

Cited by 0 Source ↗Scholar ↗

2021

Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories

Fait Poms, Vishnu Sarukkai, Ravi Teja Mullapudi, Nimit S. Sohoni, William R. Mark, Deva Ramanan +1

ICCV 2021poster

For machine learning models trained with limited labeled training data, validation stands to become the main bottleneck to reducing overall annotation costs. We propose a statistical validation algorithm that accurately estimates the F-score of binary classifiers for rare categories, where finding r…

Cited by 9 PDF ↗Scholar ↗