Irene Pi — accepted AI-conference papers

2026

Building a Precise Video Language with Human-AI Oversight

Zhiqiu Lin, Siyuan Cen, Chancharik Mitra, Isaac Li, Yuhan Huang, Yu Tong Tiffany Ling +6

CVPR 2026

Video-language models (VLMs) learn to reason about the dynamic visual world through natural language. We introduce a suite of open datasets, benchmarks, and recipes for scalable oversight that enable precise video captioning. First, we define a structured specification for describing subjects, scene

Cited by 0 Source ↗code ↗Scholar ↗

2025

AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark

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

NeurIPS 2025poster

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 datasets that rely on crowdsourced prompts, AgMMU is distilled from 116,231 authentic dialogues between everyday growers…

Cited by 0 Source ↗Scholar ↗