Xubing Ye

Xubing Ye (叶栩冰)

Hi! I'm Xubing Ye. I'm currently an algorithm engineer at ByteDance Seed. Before that, I obtained my master's degree from SIGS at Tsinghua University in 2026, supervised by Prof. Yansong Tang. I obtained my bachelor's degree from Tongji University in 2023.

My current research focuses on data-centric engineering for agentic LLMs and MLLMs.

Email: yxb_tongji@163.com / Github / Scholar

Recent Works

* Indicates Equal Contribution

	SeedRealtime: An Audio-Visual Full-Duplex LLM ByteDance Seed Team Tech Blog, 2026 [Tech Blog] A native audio-visual full-duplex LLM enabling real-time interactions that can watch, listen, and speak.
	MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling MiroMind Team Tech Report, 2026 [arXiv] [Code] [HF] An open-source deep research agent advancing model, context, and interactive scaling.
	VoCo-LLaMA: Towards Vision Compression with Large Language Models Xubing Ye, Yukang Gan, Xiaoke Huang, Yixiao Ge, Yansong Tang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [arXiv] [Code] Compresses hundreds of video tokens into one via attention distillation for efficient long-video understanding.
	ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models Xubing Ye, Yukang Gan, Yixiao Ge, Xiao-ping Zhang, Yansong Tang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 [arXiv] Adaptively prunes visual tokens inside LLM decoder layers with minimal performance loss.
	Language-Aware Vision Transformer for Referring Segmentation Xubing Ye, Zhao Yang, Jiaqi Wang, Yansong Tang, Kai Chen, Hengshuang Zhao, Philip H.S. Torr IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, IF=20.8), 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, 2022 [IEEE] [Conference Version] [Code] A universal referring image and video segmentation framework with language-aware visual encoding.