Woosung (Reiss) Koh
Woosung (Reiss) Koh

Research Intern

Trillion Labs

About Me

👋 Hi! I am interested in expanding what is possible for humanity. To this end, I primarily work on Foundation Models and Agents. Currently, I am primarily working on a generative world model for VLM agent training. Previously, I have worked on pre-training, post-training, reasoning, self-evolution, agents, and scalable feedback/evaluation, and inference-time scaling. I am perfectly bilingual in English and Korean. If you have similar interests, let’s connect.

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

  • Graduate Student

    KAIST AI

  • Bachelor's Degree

    Yonsei University

  • Diploma Programme

    International Baccalaureate

Publications

*Equal contribution

[P1] Woosung Koh, Juyoung Suk, Sungjun Han, Se-Young Yun, Jay Shin (2025). Predicting LLM Reasoning Performance with Small Proxy Model. Pre-print.
PDF
[C3] Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee, Hyeongjin Kim, Ah Yeon Kim, Joonkee Kim, Junghyun Lee, Taehyeon Kim, Se-Young Yun (2025). AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners. NeurIPS 2025.
PDF Code
[C2] Woosung Koh*, Jang Han Yoon*, MinHyung Lee, Youngjin Song, Jaegwan Cho, Jaehyun Kang, Taehyeon Kim, Se-Young Yun, Youngjae Yu, Bongshin Lee (2024). C2^2: Scalable Auto-Feedback for LLM-based Chart Generation. NAACL 2025 Main (Oral, Long) (7.7% of Submissions).
PDF Code Project Video
[C1] Woosung Koh, Wonbeen Oh, Siyeol Kim, Suhin Shin, Hyeongjin Kim, Jaein Jang, Junghyun Lee, Se-Young Yun (2024). FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RL. ICLR 2025.
PDF Code Project
[W2] Insu Choi*, Woosung Koh*, Gimin Kang, Yuntae Jang, Woo Chang Kim (2024). Encoding Temporal Statistical-space Priors via Augmented Representation. IJCAI 2024 STRL Workshop (Oral).
PDF
See all publications