Author

Ziyue Wang

Observed name: Wang, Ziyue

Institutions: Microsoft (United States), Nanyang Technological University, Peking University, Wuhan University, ByteDance (China), Tsinghua University

Observed institutions: Microsoft (United States), National University of Singapore, Nanyang Technological University, Peking University, Wuhan University, ByteDance (China), Tsinghua University

OpenAlex ID: A5125487948

TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

2026 · Yao, Linli, Wei, Yuancheng, et al. · arXiv (Cornell University) · 14

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution

2026 · Wang, Ziyue, Jin, Sheng, et al. · arXiv (Cornell University) · 13

PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization

2026 · Jiang, Songhan, Liu, Fengchun, et al. · arXiv (Cornell University) · 11

Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation

2026 · Cai, Yishuo, Liu, Jiahui, et al. · arXiv (Cornell University) · 7

EvoVid: Temporal-Centric Self-Evolution for Video Large Language Models

2026 · Huang, Shiqi, Wang, Ziyue, et al. · arXiv (Cornell University) · 7

Video-OPSD: Exploiting Privileged Visual Evidence for On-Policy Self-Distillation in Video Large Language Models

2026 · Wang, Ziyue, Huang, Shiqi, et al. · arXiv (Cornell University) · 5

PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology

2025 · Liu, Fengchun, Jiang, Songhan, et al. · arXiv (Cornell University) · 3

BASIS: Evaluating Belief-Aware Solutions in Interactive Settings beyond Instructions

2026 · Ruan, Minyuan, Wang, Ziyue, et al. · arXiv (Cornell University) · 1

Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors

2026 · Luo, Fuwen, Wan, Zihao, et al. · arXiv (Cornell University) · 1

SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

2026 · Ma, Caoyuan, Gu, Tian, et al. · arXiv (Cornell University)

Multimodal Reasoning with Explicit Reasoning Patterns and Rewards

2026 · Han Qiu, Sheng Jin, et al.

Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue

2026 · Kaiming Liu, Fuwen Luo, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 12

Citation count: 62

H-index: 5

I10-index: 3