ZY
Zuhao Yang
cs.CVcs.CLcs.AIcs.LGcs.MM
On Valency
published · living versionsW_bwftpw98·v1 · currentpublished
GroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research
with Xiyuan Liang, Yu Wang, Ziting Wang, Duo Li +5
1 version
Preprints & journals
22 papers in the corpus · 2023–2026GroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research2610.25493v1 · Xiyuan Liang, Yu Wang, Zuhao Yang et al.2026 · 0 citationsarXivon Valency
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding2610.18829v1 · Xuyang Liu, Shihao Wang, Xinyu Wei et al.2026 · 0 citationsarXiv
What Really Works for Universal Multimodal Embeddings? A Controlled Study of Contrastive Training Strategies2610.15035v1 · Duo Li, Haojun Pan, Zuhao Yang et al.2026 · 0 citationsarXiv
OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning2610.12458v1 · Zhongyu Yang, Jiale Tao, Ruitao Chen et al.2026 · 0 citationsarXiv
StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding2608.16320v1 · Keming Wu, Baoyi Wang, Kaichen Zhang et al.2026 · 0 citationsarXiv
Kimi K3: Open Frontier Intelligence2607.24653v2 · Kimi Team: Tongtong Bai, Yifan Bai, Yiping Bao et al.2026 · 0 citationsarXiv
PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models2607.24957v1 · Zichao Lin, Yifeng Xie, Bowen Qu et al.2026 · 0 citationsarXiv
Demonstrating TOFFEE: A Learned System for Synthesizing Data Agent Trajectories at Scale2607.06233v3 · Ziting Wang, Yin Li, Zuhao Yang et al.2026 · 0 citationsarXiv
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning2605.20342v2 · Zuhao Yang, Kaichen Zhang, Sudong Wang et al.2026 · 0 citationsarXiv
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors2605.10434v1 · Keming Wu, Yijing Cui, Wenhan Xue et al.2026 · 0 citationsarXiv
Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL2604.28123v3 · Sudong Wang, Weiquan Huang, Xiaomin Yu et al.2026 · 0 citationsarXiv
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling2604.28185v2 · Keming Wu, Zuhao Yang, Kaichen Zhang et al.2026 · 0 citationsarXiv
SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration2604.05079v1 · Zhongyu Yang, Zuhao Yang, Shuo Zhan et al.2026 · 0 citationsarXiv
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling2511.20785v3 · Zuhao Yang, Sudong Wang, Kaichen Zhang et al.2025 · 0 citationsarXiv
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe2511.16334v4 · Kaichen Zhang, Keming Wu, Zuhao Yang et al.2025 · 0 citationsarXiv
A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models2511.15098v2 · Duo Li, Zuhao Yang, Xiaoqin Zhang et al.2025 · 0 citationsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026, pp. 2823-2833
Versatile Transition Generation with Image-to-Video Diffusion2508.01698v1 · Zuhao Yang, Jiahui Zhang, Yingchen Yu et al.2025 · 0 citationsarXiv
TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding2508.01699v1 · Zuhao Yang, Yingchen Yu, Yunqing Zhao et al.2025 · 3 citationsarXiv
ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance2505.18757v3 · Duo Li, Zuhao Yang, Xiaoqin Zhang et al.2025 · 2 citationsarXiv
AI-Generated Images as Data Source: The Dawn of Synthetic Era2310.01830v3 · Zuhao Yang, Fangneng Zhan, Kunhao Liu et al.2023 · 7 citationsarXiv
FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy2305.10307v4 · Zuhao Yang, Yingfang Yuan, Yang Xu et al.2023 · 3 citationsarXiv
PaCaNet: A Study on CycleGAN with Transfer Learning for Diversifying Fused Chinese Painting and Calligraphy2301.13082v5 · Zuhao Yang, Huajun Bai, Zhang Luo et al.2023 · 3 citationsarXiv
Career total: 28 works. 22 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.