Hung Le

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

RCD: Retrieval-augmented Contextual Decoding for Truthful Generation

SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models

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

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

Rapid Selection and Ordering of In-Context Demonstrations via Prompt Embedding Clustering

On the Effectiveness of Discrete Representations in Sparse Mixture of Experts

Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer