Aoxue Li

11

Papers

27

Total Citations

Papers (11)

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

NeurIPS 2025arXiv

Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

Boosting Few-Shot Learning With Adaptive Margin Loss

Transformation Invariant Few-Shot Object Detection

Semi-Supervised Object Detection via Multi-Instance Alignment With Global Class Prototypes

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-Real Novel View Synthesis via Contrastive Learning

Few-Shot Learning With Global Class Representations

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

Dense Relation Distillation With Context-Aware Aggregation for Few-Shot Object Detection

Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy

CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds