Wu Chengjing
4 papers · 2026–2026 · 1 venue · 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.
Venues
Top co-authors
Research topics
Keywords
in-context learning
(1)
object removal
(1)
diffusion model
(1)
temporal consistency
(1)
open vocabulary
(1)
hierarchical feature
(1)
human preference
(1)
vision language
(1)
scene text editing
(1)
video-to-video translation
(1)
semantic flow
(1)
stochastic bridge
(1)
self-prompting
(1)
qwen3-vl
(1)
flux-fill
(1)
style-consistent
(1)
multiscale features
(1)
self-attention diffusion transformer
(1)
adaptive mask modulation
(1)
bidirectional semantic flow
(1)
Papers
FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
ICML 2026
Learning Stochastic Bridges for Video Object Removal via Video-to-Video Translation
ICML 2026
MiVE: Multiscale Vision-language features for reference-guided video Editing
ICML 2026
Self-Prompting Diffusion Transformer for Open-Vocabulary Scene Text Editing via In-Context Learning
ICML 2026