Jiasong Feng
4 papers · 2025–2026 · 4 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 transformer
(3)
efficient computing
(2)
text-to-video generation
(2)
text-to-image generation
(2)
semantic correlation
(1)
diffusion model
(1)
parameter efficiency
(1)
control signal
(1)
temporal consistency
(1)
cross-attention mechanism
(1)
image-to-video generation
(1)
layout control
(1)
image generation
(1)
proxy token
(1)
video generation
(1)
video synthesis
(1)
knowledge distillation
(1)
Papers
RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers
AAAI 2026
FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance
IJCAI 2025
Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation
ICCV 2025
PT-T2I/V: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Image/Video-Task
ICLR 2025