Yibing Song
- Papers
- 19
Cite
Notes
Only stored in your browser.
Authored papers
19DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation
arXiv 2025
WorldVLA: Towards Autoregressive Action World Model
arXiv 2025
AvatarArtist: Open-Domain 4D Avatarization
CVPR 2025 1
LLaVA-CoT: Let Vision Language Models Reason Step-by-Step
arXiv 2024
ATPrompt: Textual Prompt Learning with Embedded Attributes
ICCV 2025
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
arXiv 2024
Efficient Video Action Detection with Token Dropout and Context Refinement
ICCV 2023 1
InstructDET: Diversifying Referring Object Detection with Generalized Instructions
arXiv 2023
Improved Test-Time Adaptation for Domain Generalization
CVPR 2023 1
Domain Generalization via Rationale Invariance
ICCV 2023 1
Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation
ICCV 2023 1
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
videomae-masked-autoencoders-are-data
DiffusionDet: Diffusion Model for Object Detection
ICCV 2023 1
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
arXiv 2022
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
arXiv 2022
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
CVPR 2022 1
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
arXiv 2022
PD-GAN: Probabilistic Diverse GAN for Image Inpainting
CVPR 2021 1
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
ECCV 2020 8
Affiliations
Frequent co-authors
10from 19 papers