Scholar
Tao Li
Google Scholar ID: C1-ACVEAAAAJ
Google DeepMind
Citations & Impact
Citations
3,565
H-index
16
i10-index
19
Publications
20
Co-authors
10
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications include 'Devil’s Advocate: Anticipatory Reflection for LLM Agents' (EMNLP Findings 2024), 'A Zero-Shot Language Agent for Computer Control with Structured Reflection' (EMNLP Findings 2023, oral at NILLI), 'MUG: Interactive Multimodal Grounding on User Interfaces' (EACL Findings 2024), 'Learning Semantic Role Labeling from Compatible Label Sequences' (EMNLP Findings 2023), 'Structured Tuning for Semantic Role Labeling' (ACL 2020), 'A Logic-Driven Framework for Consistency of Neural Models' (EMNLP 2019), 'Augmenting Neural Networks with First-order Logic' (ACL 2019, oral), 'Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compression' (EMNLP Findings 2024), 'OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings' (EMNLP 2021), 'UnQovering Stereotyping Biases via Underspecified Questions' (EMNLP Findings 2020), 'On Measuring and Mitigating Biased Inferences of Word Embeddings' (AAAI 2020, oral). Projects include Gemini 2.5 and more.
Research Experience
- Current: Research Engineer at Google DeepMind (May 2022 - Present). Former: Research Engineer at Google Research (Jan 2022 - May 2024), Research Intern at AllenAI Aristo (Jan 2020 - May 2020), Applied Scientist Intern at Amazon A9 (May 2019 - Aug 2019), Research Intern at Philips Research (May 2018 - Aug 2018).
Education
- PhD in Computing from the Kahlert School of Computing, University of Utah, under the supervision of Prof. Vivek Srikumar.
Background
- Research Interests: Gemini Multimodal Generation and Gemini Thinking. Previously interned at AI2 Aristo, Amazon A9, and Philips Research.
Miscellany
- Personal interests and hobbies information not provided.
