Ziqi Pang

PhD student, UIUC

3 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

2 papers

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

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

#4703 · Zheyu Aqa Zhang, Ziqi Pang, Shixing Chen, Xiang Hao, Vimal Bhat, Yu-Xiong Wang

Enhancing long video understanding via extreme compression by reducing each selected frame to a single token.

AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark

#2406 · Aruna Gauba, Irene Pi, Yunze Man, Ziqi Pang, Vikram S. Adve, Yu-Xiong Wang

AgMMU is a challenging real‑world benchmark for evaluating and advancing vision-language models (VLMs) in the knowledge‑intensive domain of agriculture.

Poster Session 5

1 paper

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

MR. Video: MapReduce as an Effective Principle for Long Video Understanding

#4612 · Ziqi Pang, Yu-Xiong Wang