Minki Kang

Nardien

·

Nardien

AI & ML interests

None yet

Recent Activity

upvoted a paper about 7 hours ago

Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents

upvoted a paper 8 days ago

Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay

upvoted a paper 14 days ago

Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data

View all activity

Organizations

Papers 6

arxiv:2605.28774

arxiv:2505.17612

arxiv:2504.04718

arxiv:2411.00686

models 0

None public yet

datasets 0

None public yet