Scholar
Anikait Singh
Google Scholar ID: lPaISmIAAAAJ
Stanford University
Citations & Impact
Citations
4,102
H-index
13
i10-index
16
Publications
20
Co-authors
59
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 'Learning to Discover Abstractions for LLM Reasoning' (ICML 2025), 'Few-Shot Preference Optimization of Synthetic Preferences Elicits Effective Personalization to Real Users' (ICML 2025), 'Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs' (CoLM 2025), 'Improving Test-Time Search in LLMs with Backtracking Against In-Context Value Verifiers' (ICLR 2025); Awards: Runner-Up Best Paper at ICLR 2025 for 'Improving Test-Time Search in LLMs with Backtracking Against In-Context Value Verifiers'.
Research Experience
- Research Scientist Intern at Microsoft Research NYC; Student Researcher at Google DeepMind Robotics and Toyota Research Institute.
Education
- Ph.D. student at Stanford AI, advised by Chelsea Finn and Aviral Kumar; Previously, a student at UC Berkeley, advised by Sergey Levine.
Background
- Research Interests: Understanding and tackling the core bottlenecks in scaling reinforcement learning to foundation models. Research Areas: The intersection of data and algorithms, including designing simple, scalable, and predictable learning objectives; systematically curating data distributions to teach models dynamic, adaptive behaviors.
