Jiyang Liu

5 papers · 2025–2026 · 2 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 ⭐ Rising Star (5)

Venues

ICCV (3) CVPR (2)

Top co-authors

Yitong Wang (5) Junjia Huang (4) Guanbin Li (3) Pengxiang Yan (3) Zhao Wang (3) bin xia (2) Liang Lin (2) Xiangtai Li (1) Jiashi Feng (1) Binbin Yang (1)

Research topics

Computer Vision (5) Generation (5) Deep Learning (4) Processing (4) Models (3) Architectures (1) Learning Types (1)

Keywords

image editing (2) text-to-image generation (2) image fusion (1) preference optimization (1) diffusion model (1) vision-language model (1) video editing (1) text-guided editing (1) cross-attention mechanism (1) data synthesis (1) diffusion transformer (1) text-guided image editing (1) multimodal diffusion transformer (1) text-driven generation (1) attention manipulation (1) feature replacement (1) character consistency (1) image layer decomposition (1) text-driven editing (1) multimodal instruction (1)

Papers

DreamOmni2: Multimodal Instruction-based Generation and Editing CVPR 2026 DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior CVPR 2026 DreamFuse: Adaptive Image Fusion with Diffusion Transformer ICCV 2025 DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Model ICCV 2025 QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing ICCV 2025