conftrace_

Zhanhao Liang

4 papers · 2024–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

CVPR (2) ECCV (1) ICCV (1)

Top co-authors

YUHUI YUAN (3) Ji Li (3) Liang Zheng (2) Mingxi Cheng (1) Tiankai Hang (1) Yinuo Wang (1) Jie Wu (1) WEICONG LIANG (1) Gao Huang (1) Zeyu Liu (1)

Research topics

Deep Learning (3) Models (3) Computer Vision (2) Generation (2) Learning Types · Deep Learning (2) Machine Learning (1) Architectures (1) Learning Types · Machine Learning (1) Optimization & Theory (1)

Keywords

diffusion model (2) text-to-image generation (2) flow matching (1) human preference (1) diffusion transformer (1) reward signal (1) layout control (1) aesthetic improvement (1) image aesthetics (1) image generation (1) aesthetic preference (1) direct preference optimization (1)

Papers

LeapAlign: Post-training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories CVPR 2026 Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization CVPR 2025 Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics ICCV 2025 Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering ECCV 2024