Xiaoxuan He

4

Papers

252

Total Citations

Papers (4)

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Unified Medical Image Pre-training in Language-Guided Common Semantic Space

Robustness-Guided Image Synthesis for Data-Free Quantization

Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-Tailed Learning