Woosung (Reiss) Koh
Woosung (Reiss) Koh

Research Intern

About Me

👋 Hi! I am interested in pushing the boundary of Foundation Models and Agents. I am perfectly bilingual in English and Korean. I love research, and thinking about ways to maximize downstream impact. Feel free to check out my publications below.

Interests
  • Foundation Models
  • Efficient Learning and Models
  • Reasoning and Agents
Education
  • Graduate Student

    KAIST AI

  • Bachelor's Degree

    Yonsei University

  • Diploma Programme

    International Baccalaureate

Publications

*Equal contribution

(2025). Predicting LLM Reasoning Performance with Small Proxy Model. Pre-print.
(2025). AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners. NeurIPS 2025.
(2024). C2^2: Scalable Auto-Feedback for LLM-based Chart Generation. NAACL 2025 Main (Oral, Long) (7.7% of Submissions).
(2024). FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL. ICLR 2025.
(2024). Encoding Temporal Statistical-space Priors via Augmented Representation. IJCAI 2024 STRL Workshop (Oral).