activity
20242026
collaborators

9 papers

cs.CV2026

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

Zheyu Zhang, Ziqi Pang, Shixing Chen +3

Long video understanding is inherently challenging for vision-language models (VLMs) because of the extensive number of frames. With each video frame typically expanding into tens…

cs.CV2025

AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark

Aruna Gauba, Irene Pi, Yunze Man +3

We present AgMMU, a challenging real-world benchmark for evaluating and advancing vision-language models (VLMs) in the knowledge-intensive domain of agriculture. Unlike prior datas…

cs.CV2025

RandAR: Decoder-only Autoregressive Visual Generation in Random Orders

Ziqi Pang, Tianyuan Zhang, Fujun Luan +5

We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a p…

cs.CV2025

MR. Video: "MapReduce" is the Principle for Long Video Understanding

Ziqi Pang, Yu-Xiong Wang

We propose MR. Video, an agentic long video understanding framework that demonstrates the simple yet effective MapReduce principle for processing long videos: (1) Map: independentl…

cs.CV2025

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception

Ziqi Pang, Xin Xu, Yu-Xiong Wang

With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. Ho…

cs.CV2025

GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation

Lang Lin, Xueyang Yu, Ziqi Pang +1

This paper proposes a novel framework utilizing multi-modal large language models (MLLMs) for referring video object segmentation (RefVOS). Previous MLLM-based methods commonly str…