Bingxin Xu

About Me

My Photo

Hi everyone! I'm Bingxin Xu, first-year Ph.D. student in Computer Science at University of Southern California, advised by Prof. Emilio Ferrara.

My research focuses on Efficient and Trustworthy AI, especially for large language model (LLM), multi-modal large language models (MLLM) and vision-language-action models (VLA).

Before joining USC, I worked as research assistant under the mentorship of Prof. Yan Yan from Illinois Institute of Technology. Previously, I received my M.S. in Data Science and B.S. in Computer Science from Illinois Institute of Technology.

Publications

Google Scholar: Bingxin Xu

PruMerge 2024

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models

Bingxin Xu*,Yuzhang Shang*, Mu Cai*, Yong Jae Lee, Yan Yan

International Conference on Computer Vision (ICCV), 2025

freePruner 2024

freePruner: A Training-free Approach for Large Multimodal Model Acceleration

Bingxin Xu, Yuzhang Shang, Yunhao Ge, Qian Lou, Yan Yan

arXiv Nov.2024

Paper
ButterflyQuant 2025

ButterflyQuant: Ultra-low-bit LLM Quantization through Learnable Orthogonal Butterfly Transforms

Bingxin Xu, Zhen Dong, Oussama Elachqar, Yuzhang Shang

arXiv Sep.2025

Paper
VideoLLM 2024

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Bingxin Xu*, Yuzhang Shang*, Weitai Kang, Mu Cai, Yuheng Li, Zehao Wen, Zhen Dong, Kurt Keutzer, Yong Jae Lee, Yan Yan

arXiv Sep.2024

Paper
ECAR 2024

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling

Zhihang Yuan, Yuzhang Shang, Hanling Zhang, Tongcheng Fang, Rui Xie, Bingxin Xu, Yan Yan, Shengen Yan, Guohao Dai, Yu Wang

arXiv Dec.2024

Paper
ICCV 2023

Causality Guided Data-free Network Quantization

Yuzhang Shang, Bingxin Xu, Gaowen Liu, Ramana Rao Kompella, Yan Yan

International Conference on Computer Vision (ICCV), 2023

Contact

Email: bingxin.xu.ai@gmail.com