Yiweng Xie — accepted AI-conference papers

2026

FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding

Yiweng Xie, Bo He, Junke Wang, Xiangyu Zheng, Ziyi Ye, Zuxuan Wu

CVPR 2026

This paper presents FluxMem, a training-free framework for efficient streaming video understanding. FluxMem adaptively compresses redundant visual memory through a hierarchical, two-stage design: (1) a Temporal Adjacency Selection (TAS) module removes redundant visual tokens across adjacent frames,

Cited by 0 Source ↗code ↗Scholar ↗

2025

INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning

Wujian Peng, Lingchen Meng, Yitong Chen, Yiweng Xie, Yang Liu, Tao Gui +4

NeurIPS 2025poster

Large Multimodal Models (LMMs) have made significant breakthroughs with the advancement of instruction tuning. However, while existing models can understand images and videos at a holistic level, they still struggle with instance-level understanding that requires a more fine-grained comprehension an…

Cited by 0 Source ↗Scholar ↗