Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- [ArXiv'25] Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities
- [ACL'25] SkillVerse - Assessing and Enhancing LLMs with Tree Evaluation
- [ArXiv'24] Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- [NAACL'24] CodecLM: Aligning Language Models with Tailored Synthetic Data
- [ArXiv'23] Gemini: a family of highly capable multimodal models
- [ACL'23] QueryForm: A Simple Zero-shot Form Entity Query Framework
- [ECCV'22] DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning
- [ECCV'22] Learning Instance-Specific Adaptation for Cross-Domain Segmentation
- [CVPR'22] Learning to Prompt for Continual Learning
- [AAAI'22] Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
- [AAAI'22] Learning from Weakly-labeled Web Videos via Exploring Sub-Concepts
- [NeurIPS'21] Improved Transformer for High-Resolution GANs
- [ICCV'21] Learning Fast Sample Re-weighting Without Reward Data
- [ICLR'21] PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
- [AAAI'21] Improved Consistency Regularization for GANs
- [NeurIPS'20] FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
- [ECCV'20] Consistency-Based Semi-Supervised Active Learning: Towards Minimizing Labeling Cost
- [CVPR'20] Distilling Effective Supervision from Severe Label Noise
- [ICLR'20] Consistency Regularization for Generative Adversarial Networks
- [ICLR'20] Distance-Based Learning from Errors for Confidence Calibration
- [Before 2020] Pathologist-level interpretable whole-slide cancer diagnosis with deep learning
Research Experience
- Worked at Siemens Research
- Worked at Facebook AI Research (FAIR)
- Currently working on research and development for Gemini at Google
Education
Completed PhD since 2019.
Background
Research interests: Computer vision and deep learning, especially their applications in medical imaging and healthcare. Currently doing research and development for Gemini at Google.