Jianhui Wei — accepted AI-conference papers

2026

UniVBench: Towards Unified Evaluation for Video Foundation Models

Jianhui Wei, Xiaotian Zhang, Yichen Li, Yuan Wang, Yan Zhang, Ziyi Chen +3

CVPR 2026

Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation benchmarks remain fragmented and limited in scope, as they each

Cited by 0 Source ↗code ↗Scholar ↗

2025

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability

Zikai Xiao, Fei Huang, Jianhong Tu, Jianhui Wei, Wen Ma, Yuxuan Zhou +4

EMNLP 2025

Generating long, informative, and factual outputs remains a major challenge for Large Language Models (LLMs). Existing benchmarks for long-form generation typically assess real-world queries with hard-to-verify metrics or use synthetic setups that ease evaluation but overlook real-world intricacies.

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗