Reinforcement Learning

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
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
A physics-grounded 3D motion reward for improving human motion realism in video generation
Yidong Huang, Zun Wang, Han Lin, Dong-Ki Kim, Shayegan Omidshafiei, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal
Preprint Cite
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
OneLife learns symbolic programmatic world models from a single episode of unguided exploration in stochastic environments
Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal
Preprint Cite Project
One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration
Fine-grained Image Captioning with CLIP Reward
Findings of NAACL 2022
Jaemin Cho, Seunghyun Yoon, Ajinkya Kale, Franck Dernoncourt, Trung Bui, Mohit Bansal
Preprint Cite Code
Fine-grained Image Captioning with CLIP Reward