Tao Dai

Assistant Professor@Department of Software Engineering, Shenzhen University·中国·OpenReview

研究方向

point cloud analysis · time series forecasting · knowledge distillation · parameter-efficient fine-tuning · image super-resolution · image restoration · image denoising · CT reconstruction

Tao Dai

RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization

SparseEval: Efficient Evaluation of Large Language Models by Sparse Optimization

IDFSR: Personalized Face Super-Resolution with Identity Decoupling and Fitting

EG3AD: An Efficient Geometry-Aware Encoding Framework for Reconstruction-Based Multi-Class Point Cloud Anomaly Detection

Why does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs

TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting

3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors

IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models

TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting

IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models

3D-GP-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors

Block-to-Scene Pre-training for Point Cloud Hybrid-Domain Masked Autoencoders

Towards Scalable Semantic Representation for Recommendation

MambaVC: Exploring Selective State Spaces for Learned Visual Compression

Multimodal LLM-guided Query Optimization for Visual-Language Retrieval

TimeBridge: Non-Stationarity Matters for Long-term Time Series Forecasting

RouGE: Learning Gated Experts for Segment Anything in the Wild