Author

Jiwon Jeon

Observed name: Jeon, Jiwon

Institutions: Microsoft (United States), Korea Advanced Institute of Science and Technology

Observed institutions: Microsoft (United States), Korea Advanced Institute of Science and Technology

OpenAlex ID: A5128070461

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

2026 · Kim, Jeonghye, Luo, Xufang, et al. · arXiv (Cornell University) · 103

Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR

2026 · Kim, Jeonghye, Jeon, Jiwon, et al. · arXiv (Cornell University) · 19

Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback

2026 · Byeon, Woohyeon, Jeon, Jiwon, et al. · arXiv (Cornell University) · 1

STAIRS-Former: Spatio-Temporal Attention with Interleaved Recursive Structure Transformer for Offline Multi-task Multi-agent Reinforcement Learning

2026 · Jeon, Jiwon, Cho, Myungsik, et al. · arXiv (Cornell University) · 1

AGiR: Mitigating Gift Over-Reliance in Mixed-Motive Games

2026 · Byeon, Woohyeon, Kim, Seongmin, et al. · arXiv (Cornell University)

Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction

2026 · Jeon, Jiwon, Cho, Myungsik, et al. · arXiv (Cornell University)

Works count: 6

Citation count: 124

H-index: 2

I10-index: 2