Linrui Ma
Author directory2026
VGI-Bench: Probing Visual Intelligence in Video Generation Models
Xuan He | Cong Wei | Yuhao Cheng | Linrui Ma | Yuxuan Zhang | Zuojun Li | Yuhao Wen | Jize Jiang | Zeyi Liu | Yuren Hao | Songcheng Cai | Keming Wu | Penghui Du | Kai Zou | Rui Yang | Chenkai Sun | Ke Yang | Ping Nie | Kelsey R Allen | Chenglong Wang | Michel Galley | Jianfeng Gao | ChengXiang Zhai
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Xuan He | Cong Wei | Yuhao Cheng | Linrui Ma | Yuxuan Zhang | Zuojun Li | Yuhao Wen | Jize Jiang | Zeyi Liu | Yuren Hao | Songcheng Cai | Keming Wu | Penghui Du | Kai Zou | Rui Yang | Chenkai Sun | Ke Yang | Ping Nie | Kelsey R Allen | Chenglong Wang | Michel Galley | Jianfeng Gao | ChengXiang Zhai
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
Recent studies suggest that video generative models can exhibit certain forms of zero-shot visual reasoning through generated frames. Yet reliable evaluation remains challenging: benchmarks should adopt inputs aligned with the visual priors of current video models, require valid evolving processes rather than only plausible final states, and calibrate task difficulty to remain challenging yet partly feasible. To this end, we introduce VGI-Bench, containing 27 tasks and 810 instances, organized by a two-level taxonomy of domains and skill tags for evaluating the visual reasoning capabilities of video generative models. Our evaluations show that current generative systems can solve a subset of visually grounded reasoning tasks, but remain far from reliable, with even the strongest model, Seedance 2.0, achieving only 51.0% under our evaluation criteria. Our findings further reveal the input sensitivity, skill-bounded transfer from synthetic fine-tuning, and limited denoising-time self-correction, where later steps mainly refine early hypotheses rather than correct reasoning errors. We hope VGI-Bench will help stimulate the development of next-generation video generative models. Data and code are available at [our project page](https://hexuan21.github.io/VGI-Bench/).
MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers
Linrui Ma | Chun Hei Lo | Xinyu Wang | Peng Lu | Xihao Yuan | Hanting Chen | Kai Han | Xinghao Chen | Chengjun Zhan | Hanlin xu | Yichun Yin | Lifeng Shang | Feng Wen | Boxing Chen | Yufei Cui
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Linrui Ma | Chun Hei Lo | Xinyu Wang | Peng Lu | Xihao Yuan | Hanting Chen | Kai Han | Xinghao Chen | Chengjun Zhan | Hanlin xu | Yichun Yin | Lifeng Shang | Feng Wen | Boxing Chen | Yufei Cui
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
The quadratic computational cost of traditional attention mechanisms poses a major bottleneck to the scalability and practical deployment of large language models (LLMs), particularly in long-context scenarios. To improve efficiency, existing approaches often enforce rigid structural constraints such as local attention windows. However, these strategies typically lead to substantial performance degradation on tasks requiring precise long-range recall. In this work, we propose MATCH, a scalable and efficient framework that augments sparsified attention mechanisms with dynamically integrated in-context information through an efficient retrieval system. Empirical results show that MATCH significantly improves the performance of sparse-attention models on both synthetic and real-world natural-language tasks. These findings highlight the versatility of MATCH as a general approach for enhancing in-context retrieval capabilities while maintaining the efficiency benefits of sparse attention architectures.
Search
Co-authors
- Kelsey R Allen 1
- Songcheng Cai 1
- Boxing Chen 1
- Hanting Chen 1
- Xinghao Chen 1
- Yuhao Cheng 1
- Yufei Cui 1
- Penghui Du 1
- Michel Galley 1
- Jianfeng Gao 1
- Kai Han 1
- Yuren Hao 1
- Xuan He 1
- Jize Jiang 1
- Zuojun Li 1
- Zeyi Liu 1
- Chun Hei Lo 1
- Peng Lu 1
- Ping Nie 1
- Lifeng Shang 1
- Chenkai Sun 1
- Chenglong Wang 1
- Xinyu Wang 1
- Cong Wei 1
- Feng Wen 1
- Yuhao Wen 1
- Keming Wu 1
- Ke Yang 1
- Rui Yang 1
- Yichun Yin 1
- Xihao Yuan 1
- ChengXiang Zhai 1
- Chengjun Zhan 1
- Yuxuan Zhang 1
- Kai Zou 1
- Hanlin xu 1