Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
publications
Enhanced UNet++ Model for Brain Glioma MRI Image Segmentation
Published in 5th International Conference on Computer Science and Software Engineering (CSSE 2022), 2022
This work uses max- and min-filter-based data augmentation to improve UNet++ segmentation performance on the MICCAI BraTS 2020 brain glioma MRI dataset.
Recommended citation: Tuo Liang, Dongxu Yan, and Yanfeng Lu. "Enhanced UNet++ Model for Brain Glioma MRI Image Segmentation." Proceedings of the 5th International Conference on Computer Science and Software Engineering, pp. 568-573, 2022.
Download Paper
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
Published in Advances in Neural Information Processing Systems, Vol. 37 (NeurIPS 2024 Oral), 2024
We introduce the YesBut benchmark for evaluating how large vision-language models understand humorous contradictions in juxtaposed comic panels.
Recommended citation: Zhe Hu, Tuo Liang, Jing Li, Yiren Lu, Yunlai Zhou, Yiran Qiao, Jing Ma, and Yu Yin. "Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions." Advances in Neural Information Processing Systems 37 (2024): 47166-47188.
Download Paper
BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting
Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
BARD-GS reconstructs dynamic scenes from blurry observations using Gaussian splatting.
Recommended citation: Yiren Lu, Yunlai Zhou, Disheng Liu, Tuo Liang, and Yu Yin. "BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16532-16542, 2025.
Download Paper
Causal3D: A Comprehensive Benchmark for Causal Learning from Visual Data
Published in arXiv preprint, 2025
Causal3D is a benchmark for evaluating causal representation learning and reasoning from visual data.
Recommended citation: Disheng Liu, Yiran Qiao, Wuche Liu, Yiren Lu, Yunlai Zhou, Tuo Liang, Yu Yin, and Jing Ma. "Causal3D: A Comprehensive Benchmark for Causal Learning from Visual Data." arXiv:2503.04852, 2025.
Download Paper
Segment then Splat: A Unified Approach for 3D Open-Vocabulary Segmentation Based on Gaussian Splatting
Published in arXiv preprint, 2025
This preprint presents a unified Gaussian-splatting approach to open-vocabulary 3D segmentation.
Recommended citation: Yiren Lu, Yunlai Zhou, Yiran Qiao, Chaoda Song, Tuo Liang, Jing Ma, and Yu Yin. "Segment then Splat: A Unified Approach for 3D Open-Vocabulary Segmentation Based on Gaussian Splatting." arXiv:2503.22204, 2025.
Download Paper
When ‘YES’ Meets ‘BUT’: Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Published in arXiv preprint, 2025
We extend YesBut to 1,262 multilingual and multicultural comics and study comparative reasoning, visual perception, hallucination, and social-knowledge augmentation in large language and vision-language models.
Recommended citation: Tuo Liang, Zhe Hu, Jing Li, Hao Zhang, Yiren Lu, Yunlai Zhou, Yiran Qiao, Disheng Liu, Jeirui Peng, Jing Ma, and Yu Yin. "When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?" arXiv:2503.23137, 2025.
Download Paper
Juxtaposition as Joke: AI’s Struggle with Visual Contradiction
Published in Master's thesis, Case Western Reserve University, 2025
This thesis studies the challenges that artificial intelligence models face when interpreting visual contradiction and juxtaposition-based humor.
Recommended citation: Tuo Liang. "Juxtaposition as Joke: AI's Struggle with Visual Contradiction." Master's thesis, Case Western Reserve University, 2025.
Download Paper
ResSVD: Residual Compensated SVD for Large Language Model Compression
Published in arXiv preprint, 2025
ResSVD improves singular-value-decomposition-based large language model compression through residual compensation.
Recommended citation: Haolei Bai, Siyong Jian, Tuo Liang, Yu Yin, and Huan Wang. "ResSVD: Residual Compensated SVD for Large Language Model Compression." arXiv:2505.20112, 2025.
Download Paper
Nebula: Do We Evaluate Vision-Language-Action Agents Correctly?
Published in arXiv preprint, 2025
Nebula examines evaluation methodology for vision-language-action agents.
Recommended citation: Jierui Peng, Yanyan Zhang, Yicheng Duan, Tuo Liang, Vipin Chaudhary, and Yu Yin. "Nebula: Do We Evaluate Vision-Language-Action Agents Correctly?" arXiv:2510.16263, 2025.
Download Paper
Deconstructing Spatial Intelligence in Vision-Language Models
Published in TechRxiv preprint, 2025
This work analyzes the component capabilities and limitations underlying spatial intelligence in vision-language models.
Recommended citation: Disheng Liu, Tuo Liang, Zhe Hu, Jierui Peng, Yiren Lu, Yi Xu, Yun Fu, and Yu Yin. "Deconstructing Spatial Intelligence in Vision-Language Models." TechRxiv, 2025.
Download Paper
Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting
Published in Advances in Neural Information Processing Systems, Vol. 38 (NeurIPS 2025), 2026
The proceedings version of Segment then Splat provides unified open-vocabulary 3D segmentation through Gaussian splatting.
Recommended citation: Yiren Lu, Yunlai Zhou, Yiran Qiao, Chaoda Song, Tuo Liang, Jing Ma, Huan Wang, and Yu Yin. "Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting." Advances in Neural Information Processing Systems 38: 165975-165994, 2026.
Download Paper
HugRAG: Hierarchical Causal Knowledge Graph Design for RAG
Published in International Conference on Machine Learning (ICML), 2026
HugRAG designs hierarchical causal knowledge graphs to improve retrieval-augmented generation.
Recommended citation: Nengbo Wang, Tuo Liang, Vikash Singh, Chaoda Song, Van Yang, Yu Yin, Jing Ma, Jagdip Singh, and Vipin Chaudhary. "HugRAG: Hierarchical Causal Knowledge Graph Design for RAG." International Conference on Machine Learning (ICML), 2026.
Download Paper
Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing
Published in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 40, No. 19, 2026
This work evaluates large language models for discovering unexpected but useful knowledge-graph connections in drug repurposing.
Recommended citation: Mengying Wang, Chenhui Ma, Ao Jiao, Tuo Liang, Pengjun Lu, Shrinidhi Hegde, Yu Yin, Evren Gurkan-Cavusoglu, and Yinghui Wu. "Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing." Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 19 (2026): 15860-15867.
Download Paper
When ‘YES’ Meets ‘BUT’: Can AI Comprehend Contradictory Humor in Comics?
Published in IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026
This peer-reviewed journal version studies comparative reasoning and contradictory humor comprehension in comics.
Recommended citation: Tuo Liang, Zhe Hu, Jing Li, Hao Zhang, Yiren Lu, Yunlai Zhou, Yiran Qiao, Disheng Liu, Jierui Peng, Jing Ma, and Yu Yin. "When 'YES' Meets 'BUT': Can AI Comprehend Contradictory Humor in Comics?" IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026.
Download Paper
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Published in arXiv preprint, 2026
This survey reviews methods, datasets, evaluation protocols, and open challenges in computational humor with multimodal large language models.
Recommended citation: Tuo Liang, Zhe Hu, Disheng Liu, Jing Li, and Yu Yin. "Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges." arXiv:2607.19011, 2026.
Download Paper