Jie Shao

20

Papers

124

Total Citations

Papers (20)

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation

Graphic Design with Large Multimodal Model

AdaDiff: Adaptive Step Selection for Fast Diffusion Models

EWMoE: An Effective Model for Global Weather Forecasting with Mixture-of-Experts

Rectify the Regression Bias in Long-Tailed Object Detection

Abstract and Explore: A Novel Behavioral Metric with Cyclic Dynamics in Reinforcement Learning

Multiple Granularity Descriptors for Fine-Grained Categorization

Contrast and Order Representations for Video Self-Supervised Learning

Mining Contextual Information Beyond Image for Semantic Segmentation

COOKIE: Contrastive Cross-Modal Knowledge Sharing Pre-Training for Vision-Language Representation

Quantization without Tears

BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers

Training-Free Class Purification for Open-Vocabulary Semantic Segmentation

Memory-Efficient Generative Models via Product Quantization

Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data

Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and Skills

Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation

Improving Generalization in Reinforcement Learning with Mixture Regularization

Is normalization indispensable for training deep neural network?