Dung Nguyen

Spectral Retrieval-Augmented Time-Series Forecasting

CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning

Reviving Error Correction in Modern Deep Time-Series Forecasting

Uncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning