From the 1 of 4 linked papers with an AI index.
4 papers
Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning
Haodong Zhu, Yangyang Ren, Yanjing Li +4
The paper introduces Kalman-Guided Prompt Selection (KGPS), a method that treats prompt difficulty as a dynamic state estimated with a Kalman filter to adaptively choose prompts du…
Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
Haodong Zhu, Yangyang Ren, Yanjing Li +6
Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs due to its extensive group-based sampling requirement. While r…
CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
Yangzhe Peng, Kaiyuan Gao, Liang He +4
Molecular docking plays a crucial role in predicting the binding mode of ligands to target proteins, and covalent interactions, which involve the formation of a covalent bond betwe…
Nature Language Model: Deciphering the Language of Nature for Scientific Discovery
Yingce Xia, Peiran Jin, Shufang Xie +43
Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspire…