I will be graduating in 2026 and am actively seeking full-time positions in industry.

Research Interests

  • Efficiency and Budget Aware Agents: How to design agentic frameworks that are efficient and adaptive under budget constraints (such as thinking budget, tool call budget, or interaction turn budget). For math problems, this means reducing thinking tokens and preventing overthinking. For deep research, it means teaching models to use tool call budgets wisely. For AI assistants with ambiguous user queries, it means asking the right questions and knowing when to stop.

  • Alignment and Safety: Building human-centered models that improve people’s lives rather than replace humans. As AI researchers, if we create these systems, we bear responsibility for ensuring they are beneficial. This requires both careful evaluation and effective intervention: understanding model behavior through rigorously designed experiments, and steering models toward desired behaviors through post-training methods and high-quality data curation.

I stopped writing academic papers and the Publications page is no longer updating. To know more about my current research and interests, check the Research Blog instead.

Experience

Meta
FAIR Alignment
Dec 2025 – May 2026
Adobe
Adobe Research
May 2025 – Aug 2025

Education

Cornell
Ph.D. in Computer Science
2023 – 2026 (expected)
Stanford
Visiting Student in Computer Science
2025
UESTC
B.S. in Information and Computing Sciences
2018 – 2022

📫 Contact

Email: jinyansu6[@]gmail.com