Shoufa Chen
14 papers · 2021–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Renaissance Researcher (5) π Interdisciplinary Bridge π Conference Polyglot (5) π Academic Marathon (5) πΊοΈ Taxonomy Completionist (22)
π
Cross-Pollinator
(15)
π
Conference Polyglot
(5)
π
Grand Slam
π
Triple Crown
π₯
Mega-Team
(22)
π€
Dynamic Duo
(11)
π₯
Unstoppable
(5)
π
Century Club
(13)
Conferences
ICCV (4)
ICLR (4)
CVPR (2)
ICML (2)
AAAI (1)
NIPS (1)
Top co-authors
Keywords
text-to-video generation
(3)
object detection
(2)
diffusion transformer
(2)
diffusion model
(2)
video generation
(2)
text-to-image generation
(2)
flow matching
(2)
action recognition
(1)
multi-task learning
(1)
contrastive learning
(1)
video recognition
(1)
preference alignment
(1)
prompt engineering
(1)
generative model
(1)
vision transformer
(1)
action classification
(1)
state representation
(1)
transfer learning
(1)
parameter-efficient transfer learning
(1)
image generation
(1)
Papers
FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation
AAAI 2026
ControlAR: Controllable Image Generation with Autoregressive Models
ICLR 2025
Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM
ICCV 2025
Goku: Flow Based Video Generative Foundation Models
CVPR 2025
FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
ICLR 2024
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
ICML 2024
GenTron: Diffusion Transformers for Image and Video Generation
CVPR 2024
Going Denser with Open-Vocabulary Part Segmentation
ICCV 2023
Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning
ICLR 2023
DiffusionDet: Diffusion Model for Object Detection
ICCV 2023
CycleMLP: A MLP-like Architecture for Dense Prediction
ICLR 2022
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
NIPS 2022
CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer
ICML 2022
Watch Only Once: An End-to-End Video Action Detection Framework
ICCV 2021