6 papers
On the Limitations of Rank-One Model Editing in Answering Multi-hop Questions
Zhiyuan He, Binghan Chen, Tianxiang Xiong +3
Recent advances in Knowledge Editing (KE), particularly Rank-One Model Editing (ROME), show superior efficiency over fine-tuning and in-context learning for updating single-hop fac…
When Do Symbolic Solvers Enhance Reasoning in Large Language Models?
Zhiyuan He, Dingmin Wang
Large Reasoning Models (LRMs) achieve strong performance on complex reasoning tasks by generating long Chains of Thought (CoTs). However, this paradigm might incur substantial toke…
Exploring Depth Generalization in Large Language Models for Solving Recursive Logic Tasks
Zhiyuan He
Large language models have demonstrated remarkable capabilities across many tasks, yet face significant challenges when dealing with recursive reasoning problems, those requiring t…
Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning
Yang Li, Zhiyuan He, Yuxuan Huang +5
Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In cont…
Orlando's flask: detection of a lost-and-found valley on the Moon
Vito Squicciarini, Irina Mirova, Francis D. Anderson +2
High angular resolution holds the key to extending our knowledge in several domains of astronomical research. In addition to the development of new instruments, advancements in pos…
Gradient Boosting Machine: A Survey
Zhiyuan He, Danchen Lin, Thomas Lau +1
In this survey, we discuss several different types of gradient boosting algorithms and illustrate their mathematical frameworks in detail: 1. introduction of gradient boosting lead…