Papers by Guohui Zhang
MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues (2026.findings-acl)
Copied to clipboard
Yaning Pan, Qianqian Xie, Guohui Zhang, Zekun Moore Wang, Yongqian Wen, Yuanxing Zhang, Haoxuan Hu, Zhiyu Pan, Yibing Huang, Zhidong Gan, Yonghong Lin, An Ping, Shihao Li, Yanghai Wang, Tianhao Peng, Jiaheng Liu
| Challenge: | Existing evaluation benchmarks for Multimodal Large Language Models (MLLMs) focus on single-turn question answering, overlooking the complexity of multi-turn dialogues in real-world scenarios. |
| Approach: | They propose a video understanding benchmark for MLLMs in multi-turn dialogues that assesses six core competencies that focus on perceptivity and interactivity. |
| Outcome: | The MT-Video-Bench evaluates 1,000 multi-turn dialogues from diverse domains and reveals significant performance discrepancies and limitations in handling multi-turned video dialogues. |
Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented Dialogue (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent years has witnessed the remarkable success in end-to-end task-oriented dialog system, especially when incorporating external knowledge information. |
| Approach: | They propose a mechanism to model deterministic entity knowledge by using an intention reasoning network to obtain intention-aware representations of conceptual tokens. |
| Outcome: | The proposed mechanism captures concept shifts and generates accurate responses on two representative multi-domain dialog datasets. |