Large Language Models

Astra in Robot Control (Ditto-bench)
Exploring Astra’s capabilities, agent design, and future possibilities in robot control
Lin Long, Jaemin Cho
Cite Code Blog
MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
A 4,016-question benchmark evaluating MLLMs on creative intent across audiovisual arts
Yuxuan Fan, Gyusik Seo, Jing Hao, Jaemin Cho, Mohit Bansal, Jaehong Yoon
Preprint Cite Code Project
GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime Optimization
LLMs as selective surrogates that forecast GPU kernel performance to accelerate kernel search
Zaid Khan, Justin Chih-Yao Chen, Jaemin Cho, Elias Stengel-Eskin, Mohit Bansal
Preprint Cite
An Assessment of Reported Biases and Harms of Large Language Models
Analysis of how biases and harms are reported and understood in recent LLM papers - ICA 2024 (Top Paper Award)
Heesoo Jang, Jaemin Cho
PDF Cite