Keyang Xuan — accepted AI-conference papers

2025

ResearchTown: Simulator of Human Research Community

Haofei Yu, Zhaochen Hong, Zirui Cheng, Kunlun Zhu, Keyang Xuan, Jinwei Yao +2

ICML 2025poster

Large Language Models (LLMs) have demonstrated remarkable potential in scientific domains, yet a fundamental question remains unanswered: Can we simulate human research communities with LLMs? Addressing this question can deepen our understanding of the processes behind idea brainstorming and inspire…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2025

TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Models

Jaewoo Lee, Keyang Xuan, Chanakya Ekbote, Sandeep Polisetty, Yi R. Fung, Paul Pu Liang

ACL 2025finding

Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in unimodal models, its application to MLLMs often yields limi…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗