Xiao Luo

18

Papers

72

Total Citations

Papers (18)

LION: Implicit Vision Prompt Tuning

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Fine-grained Prototypical Voting with Heterogeneous Mixup for Semi-supervised 2D-3D Cross-modal Retrieval

Test-time Adaptation on Graphs via Adaptive Subgraph-based Selection and Regularized Prototypes

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

Hypergraph-enhanced Dual Semi-supervised Graph Classification

PGODE: Towards High-quality System Dynamics Modeling

Prototypical Mixing and Retrieval-Based Refinement for Label Noise-Resistant Image Retrieval

InAction: Interpretable Action Decision Making for Autonomous Driving

Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs

Attention Bootstrapping for Multi-Modal Test-Time Adaptation

Prometheus: Out-of-distribution Fluid Dynamics Modeling with Disentangled Graph ODE

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval