Failed to load scholar profile
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published 'Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentation' at CoRL 2025, analyzing shortcut learning as a barrier to generalization in robot policies
- Published 'Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers' at ICLR 2025 (Spotlight), introducing a flow-based diffusion Transformer for text-to-multimodal generation
- Published 'A Closer Look at Few-shot Classification Again' at ICML 2023, empirically demonstrating the disentanglement of training and adaptation in few-shot classification
- Published 'Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid' at NeurIPS 2022 (Spotlight), revealing and correcting centroid-induced bias in few-shot tasks
- Published 'Channel Importance Matters in Few-Shot Image Classification' at ICML 2022, identifying and analyzing channel bias in few-shot learning
- Published 'Rectifying the Shortcut Learning of Background for Few-Shot Learning' at NeurIPS 2021, identifying background as a non-generalizable shortcut and proposing the COSOC framework
- Published 'Boosting Few-Shot Classification with View-Learnable Contrastive Learning' at ICME 2021, applying learnable-view contrastive learning to few-shot classification
- Published 'DETA: Denoised Task Adaptation for Few-shot Learning' at ICCV 2023, proposing a framework to handle data/label noise in few-shot transfer
- Published 'Less is More: On the Feature Redundancy of Pretrained Models When Transferring to Few-shot Tasks' on arXiv 2023, uncovering extreme feature redundancy in pretrained models during few-shot transfer
Co-authors: 0 (list not available)