Wenrui Dai

GranViT: A Fine-Grained Vision Model For Autoregressive Multimodal Large Language Models

ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning

OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation

Bootstrap Prompt Learning with Feature Adaptation for Vision-Language Efficient Tuning

On Disentangled Training for Nonlinear Transform in Learned Image Compression

Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation

LBI-FL: Low-Bit Integerized Federated Learning with Temporally Dynamic Bit-Width Allocation

FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates

FedSMU: Communication-Efficient and Generalization-Enhanced Federated Learning through Symbolic Model Updates

Noise Conditional Variational Score Distillation

ChebyNet: Boosting Neural Network Fitting and Efficiency through Chebyshev Polynomial Layer Connections