Author

Ke Hao

Observed name: Hao, Ke

Institutions: Shanghai Jiao Tong University, China Telecom (China), China Telecom

Observed institutions: Hunan Normal University, Shanghai Jiao Tong University, China Telecom (China), China Telecom

OpenAlex ID: A5125589705

StyleSRN: Scene Text Image Super-Resolution with Text Style Embedding

2025 · Shengrong Yuan, Runmin Wang, et al. · IEEE/CVF International Conference on Computer Vision (ICCV) · 2

Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models

2026 · Hao, Ke, Liang, Yuanzhi, et al. · arXiv (Cornell University)

Separating Capability from Confidence: Grounded Dual-State Calibration for GRPO-Trained Medical Vision-Language Models

2026 · Xie, Yangyang, Hao, Ke, et al. · arXiv (Cornell University)

Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training

2026 · Li, Rui, Liang, Yuanzhi, et al. · arXiv (Cornell University)

Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video

2026 · Chen, Tingxi, Hao, Ke, et al. · arXiv (Cornell University)

Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation

2026 · Li, Rui, Hao, Ke, et al. · arXiv (Cornell University)

TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation

2026 · Liang, Yuanzhi, Wu, Xuan'er, et al. · arXiv (Cornell University)

Works count: 7

Citation count: 2

H-index: 1

I10-index: