Scholar
Lixiang Ru
Google Scholar ID: y7wegKQAAAAJ
Ant Group
Citations & Impact
Citations
1,361
H-index
11
i10-index
11
Publications
20
Co-authors
12
list available
Publications
Resume (English only)
Academic Achievements
- [{'Title': 'ARGenSeg: Image Segmentation with Autoregressive Image Generation Model', 'Conference/Journal': 'NeurIPS, 2025'}, {'Title': 'M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning', 'Conference/Journal': 'arXiv, 2025'}, {'Title': 'Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction', 'Conference/Journal': 'arXiv, 2025'}, {'Title': 'A Semantic-Enhanced Multi-Modal Remote Sensing Foundation Model for Earth Observation', 'Conference/Journal': 'Nature Machine Intelligence (NMI), 2025'}, {'Title': 'SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing', 'Conference/Journal': 'ICCV, 2025'}, {'Title': 'SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery', 'Conference/Journal': 'CVPR, 2024'}, {'Title': 'Parameter-Efficient Complementary Expert Learning for Long-Tailed Visual Recognition', 'Conference/Journal': 'ACM Multimedia 2024 (ACM MM), 2024'}, {'Title': 'Token Contrast for Weakly-Supervised Semantic Segmentation', 'Conference/Journal': 'CVPR, 2023'}, {'Title': 'Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers', 'Conference/Journal': 'CVPR, 2022'}, {'Title': 'Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling', 'Conference/Journal': 'IJCV, 2022'}, {'Title': 'Learning Visual Words for Weakly-Supervised Semantic Segmentation', 'Conference/Journal': 'IJCAI, 2021'}, {'Title': 'Multi-Temporal Scene Classification and Scene Change Detection with Correlation based Fusion', 'Conference/Journal': 'Incomplete information provided'}]
Background
- Currently a Computer Vision Researcher focusing on Multi-modal Model and Visual Understanding at Ant Group. Research interests include Multi-Modal Learning and Reasoning, Visual Understanding, and Remote Sensing.
