Scholar
Yuanxing Zhang
Google Scholar ID: COdftTMAAAAJ
Kuaishou Technology
Recommender System
Large Language Model
Video Understanding
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1,084
H-index
18
i10-index
27
Publications
20
Co-authors
10
list available
Contact
No contact links provided.
Publications
78 items
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models
2026
Cited
0
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models
2026
Cited
0
Human-Centric Image Captioning with Subject-Centered Spatial Understanding
2026
Cited
0
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
2026
Cited
0
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
2026
Cited
0
CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video Generation
2026
Cited
0
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
2026
Cited
0
Flux-OPD: On-Policy Distillation with Evolving Contexts
2026
Cited
0
Load more
Resume (English only)
Co-authors
10 total
Kaigui Bian
Associate Professor, School of CS, Peking University
Lingyang Song
Peking University & Peng Cheng Laboratory, China
Pengyu Zhao
Peking University
Co-author 4
Jiaheng Liu (刘佳恒)
NJU & M-A-P
Yushuo Guan
Peking University
Co-author 7
Co-author 8
