← Seungyeon Jwa
News
Sep 2026
We released EvoDuet, which co-evolves web search queries and solutions for LLM-driven scientific discovery. Another collaboration at Minnesota NLP Group.
Jun 2026
We released RTSGameBench, a benchmark for strategic reasoning in vision-language models.
Jan 2026
Our paper on test-time learning for LLM evaluators, LWE, was accepted to EACL 2026 as Oral.
Jan 2026
I joined NAVER Cloud as an AI Resident on the Foundation Research Team, working on AudioLLM benchmarking and synthetic data generation (Jan–Mar 2026).
Mar 2025
I wrapped up three years at NCSOFT (currently NC AI) and joined SNUMPR as a research intern to begin graduate studies.