Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Wang Yang

Wang Yang

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×2Vision×1Crypto×1

Frequent co-authors

Chuang Ma1×
Qianying Liu1×
Tomoyuki Obuchi1×
Fei Cheng1×
Sudong Cai1×
Shuyuan Zheng1×

Research Timeline

2026
MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment

MOSAIC is a multi-objective framework that efficiently allocates a fixed supervised fine-tuning budget by turning failure profiles into actionable data mixtures, significantly improving model alignment across multiple safety and capability metrics.

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from the language processing side rather than poor visual attention.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.CVRecentJun 1, 2026

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning

Chuang Ma, Qianying Liu, Tomoyuki Obuchi, Fei Cheng +5 more

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…

View →
cs.CRcs.CLRecentMar 19, 2026

MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment

Yipu Dou, Wang Yang

MOSAIC is a multi-objective framework that efficiently allocates a fixed supervised fine-tuning budget by turning failure profiles into actionable data mixtures, significantly improving model alignmen…

View →