α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Yulin Wang
Yulin Wang
1
Affiliations
Affiliations
Department of Automation, Tsinghua University
24
papers
1,335
total citations
papers (24)
Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
NEURIPS 2021
arXiv
237
citations
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
CVPR 2021
arXiv
193
citations
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
NEURIPS 2020
arXiv
167
citations
Transferable Semantic Augmentation for Domain Adaptation
CVPR 2021
arXiv
141
citations
Adaptive Rotated Convolution for Rotated Object Detection
ICCV 2023
arXiv
133
citations
Adaptive Focus for Efficient Video Recognition
ICCV 2021
arXiv
112
citations
CondenseNet V2: Sparse Feature Reactivation for Deep Networks
CVPR 2021
arXiv
71
citations
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
CVPR 2022
arXiv
63
citations
Dynamic Perceiver for Efficient Visual Recognition
ICCV 2023
arXiv
40
citations
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones
ICCV 2023
arXiv
35
citations
Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
CVPR 2024
arXiv
28
citations
XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?
CVPR 2025
arXiv
26
citations
AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition
ECCV 2022
arXiv
20
citations
AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation
ECCV 2024
arXiv
16
citations
Deep Incubation: Training Large Models by Divide-and-Conquering
ICCV 2023
arXiv
13
citations
GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
NEURIPS 2025
arXiv
12
citations
RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
NEURIPS 2025
arXiv
10
citations
LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
ICCV 2025
arXiv
7
citations
EchoWorld: Learning Motion-Aware World Models for Echocardiography Probe Guidance
CVPR 2025
arXiv
6
citations
CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
CVPR 2025
arXiv
4
citations
IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
ICCV 2025
arXiv
1
citations
HccePose (BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation
ICCV 2025
arXiv
0
citations
Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm
ICCV 2023
0
citations
Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment
CVPR 2025
arXiv
0
citations
