by Longxu Dou Papers
3 papers found
NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
Xiangyan Liu, Jinjie Ni, Zijian Wu et al.
NeurIPS 2025poster
RegMix: Data Mixture as Regression for Language Model Pre-training
Qian Liu, Xiaosen Zheng, Niklas Muennighoff et al.
ICLR 2025posterarXiv:2407.01492
99
citations
Unnatural Languages Are Not Bugs but Features for LLMs
Keyu Duan, Yiran Zhao, Zhili Feng et al.
ICML 2025poster