Scholar
Fan Yin
Google Scholar ID: klShdV0AAAAJ
Research Scientist at Google Deepmind
Citations & Impact
Citations
1,522
H-index
13
i10-index
14
Publications
20
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- [{'PaperTitle': 'OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles', 'Conference': 'NeurIPS 2025'}, {'PaperTitle': 'Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation', 'Conference': 'ACL 2025'}, {'PaperTitle': 'BingoGuard: LLM Content Moderation Tools with Risk Levels', 'Conference': 'ICLR 2025'}, {'PaperTitle': 'Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation', 'Conference': 'EMNLP 2024'}, {'PaperTitle': 'Enhancing Large Vision Language Models with Self-Training on Image Comprehension', 'Conference': 'NeurIPS 2024'}, {'PaperTitle': 'Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension', 'Conference': 'ICML 2024'}, {'PaperTitle': 'Prompt-Driven LLM Safeguarding via Directed Representation Optimization', 'Conference': 'ICML 2024'}, {'PaperTitle': 'Red Teaming Language Model Detectors with Language Models', 'Conference': 'TACL'}, {'PaperTitle': 'Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks', 'Conference': 'EMNLP 2023'}, {'PaperTitle': 'Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation', 'Conference': 'EMNLP 2023'}, {'PaperTitle': 'Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning', 'Conference': 'ACL 2023'}, {'PaperTitle': 'Efficient Shapley Values Estimation by Amortization for Text Classification', 'Conference': 'ACL 2023'}, {'PaperTitle': 'CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning', 'Conference': 'ICCV 2023, Oral', 'Award': 'Best Paper Award at Trustworthy and Reliable Large-Scale ML@ICLR 2023'}, {'PaperTitle': 'ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation', 'Conference': ''}]
Research Experience
- [{'Time': 'July 2025 -- Present', 'Company': 'Google Deepmind', 'Position': 'Research Scientist', 'Project': 'Gemini post-training'}, {'Time': 'October 2024 -- April 2025', 'Company': 'Google LLC', 'Position': 'Student Researcher', 'Hosts': 'Hamid Palangi'}, {'Time': 'June 2024 -- September 2024', 'Company': 'Salesforce, Palo Alto', 'Position': 'Research Intern', 'Hosts': 'Philippe Laban, Becky Xiangyu Peng, Yilun Zhou, Jason Wu'}, {'Time': 'June 2023 -- September 2023', 'Company': 'Amazon AWS, Santa Clara', 'Position': 'Applied Scientist Intern', 'Hosts': 'He He'}, {'Time': 'June 2022 -- September 2022', 'Company': 'Salesforce Research, Palo Alto', 'Position': 'Research Intern', 'Hosts': 'Jesse Vig, Philippe Laban, Jason Wu'}]
Background
- Research Interests: Making NLP systems more reliable and robust
Miscellany
- Contact: Email / LinkedIn / Github / CV / Google Scholar
