Guojie Zhu

Huawei Inc

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)Speech & Audio (1)

Frequent co-authors

Yijing Chen (1)Wenhui Tan (1)Xiaoyi Yu (1)Yuyue Wang (1)

Papers (1)

Jun 23, 2026

2w ago·also Huawei

AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression

AVOC achieves a remarkable 4.9-point accuracy boost over the next best model in long-form audio-video comprehension, redefining efficiency in multimodal understanding.

Yijing Chen, Wenhui Tan, Xiaoyi Yu +6

Multimodal Models Speech & Audio

Search

Guojie Zhu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)