collaborators

5 papers

cs.CL2025

Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly

Wenya Xie, Shaochen, Zhong +4

Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. We show that a significant portion of these tokens are useless self-repetitions - what we ca…

cs.CL2025

Sensitivity Meets Sparsity: The Impact of Extremely Sparse Parameter Patterns on Theory-of-Mind of Large Language Models

Yuheng Wu, Wentao Guo, Zirui Liu +3

This paper investigates the emergence of Theory-of-Mind (ToM) capabilities in large language models (LLMs) from a mechanistic perspective, focusing on the role of extremely sparse…

cs.LG2024

Gradient Rewiring for Editable Graph Neural Network Training

Zhimeng Jiang, Zirui Liu, Xiaotian Han +6

Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks…

cs.AI2024

Weighted Diversified Sampling for Efficient Data-Driven Single-Cell Gene-Gene Interaction Discovery

Yifan Wu, Yuntao Yang, Zirui Liu +6

Gene-gene interactions play a crucial role in the manifestation of complex human diseases. Uncovering significant gene-gene interactions is a challenging task. Here, we present an…

cs.CR2024

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion

Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang +8

Ensuring the security of released large language models (LLMs) poses a significant dilemma, as existing mechanisms either compromise ownership rights or raise data privacy concerns…