PhD student, Korea Advanced Institute of Science & Technology
4 papers at NeurIPS 2025
In this paper, we propose uncertainty calibration method, called CalibRAG, for the RAG guided decision-making scenario.
We improve the speed and performance of LLM post-training via a new asynchronous RL approach, leveraging an off-policy objective, replay buffer, and sampling strategies.
FedSVD mitigates noise amplification in differentially private federated fine-tuning with LoRA by periodically refactorizing LoRA matrices via SVD, improving stability and performance under DP-SGD.
