alphaFeedback
MW

Mingyang Wu

cs.CVcs.AIcs.CLcs.RO

On Valency

published · living versions
W_xe6vjvab·v1 · currentpublished
AVTime: Reinforcing Dense Audio-Visual Captions with Bidirectional Alignment
with Kaituo Feng, Bohao Li, Kaixiong Gong, Zihao Yin +1
1 version

Preprints & journals

10 papers in the corpus · 2025–2026
AVTime: Reinforcing Dense Audio-Visual Captions with Bidirectional Alignment2610.26046v1 · Mingyang Wu, Kaituo Feng, Bohao Li et al.2026 · 0 citationsarXivon Valency
AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward2608.06930v1 · Mingyang Wu, Kaituo Feng, Bohao Li et al.2026 · 0 citationsarXiv
Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation2607.26694v3 · Xiangbo Gao, Siyuan Yang, Ping He et al.2026 · 0 citationsarXiv
4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation2605.24762v1 · Zihao Zhu, Kuan-Ru Huang, Zhaoming Xu et al.2026 · 0 citationsarXiv
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects2604.16272v2 · Xiangbo Gao, Sicong Jiang, Bangya Liu et al.2026 · 0 citationsarXiv
The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics2603.14375v2 · Xiangbo Gao, Mingyang Wu, Siyuan Yang et al.2026 · 0 citationsarXiv
ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation2602.10113v1 · Mingyang Wu, Ashirbad Mishra, Soumik Dey et al.2026 · 0 citationsarXiv
FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation2510.21744v1 · Yanjia Huang, Shuo Liu, Sheng Liu et al.2025 · 0 citationsarXiv
Career total: 10 works. 10 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.