Cite
Notes
Only stored in your browser.
Attribution
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
arXiv 2025
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
arXiv 2024
from 2 papers
Chao Du
Chaoqun He
Jie Liu
Jinyi Hu
Junhao Shen
Lei Qi
Maosong Sun
professor
Min Lin
Shengding Hu
researcher
Tianyu Pang