Weinan Jia
4 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
Top co-authors
Research topics
Keywords
diffusion model
(2)
image generation
(2)
image synthesis
(1)
image reconstruction
(1)
generative model
(1)
cross-modal alignment
(1)
noise prediction
(1)
visual tokenizer
(1)
diffusion transformer
(1)
position embedding
(1)
hierarchical encoder
(1)
dynamic compression
(1)
language model embedding
(1)
subject fidelity
(1)
attribute leakage
(1)
multi-subject generation
(1)
multi-shot video generation
(1)
reference character
(1)
cross-shot consistency
(1)
transformer architecture
(1)
Papers
FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
AAAI 2026
Prompt Yourself: Awakening Textual Semantics in 1D Visual Tokenizers
CVPR 2026
Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation
CVPR 2026
D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation
CVPR 2025