4 papers
Trust the uncertain teacher: distilling dark knowledge via calibrated uncertainty
Jeonghyun Kim, SooKyung Kim, Richeng Xuan +1
The core of knowledge distillation lies in transferring the teacher's rich 'dark knowledge'-subtle probabilistic patterns that reveal how classes are related and the distribution o…
MIND: AI Co-Scientist for Material Research
Geonhee Ahn, Donghyun Lee, Hayoung Doo +3
Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental veri…
QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
Doyeon Lee, Eunyi Lyou, Hyunsoo Cho +3
GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to…
TwinShift: Benchmarking Audio Deepfake Detection across Synthesizer and Speaker Shifts
Jiyoung Hong, Yoonseo Chung, Seungyeon Oh +4
Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse sp…