EMNLP 2025

Exploration-Driven Reinforcement Learning for Expert Routing Improvement in Mixture-of-Experts Language Models

2025

EMNLP 2025

FractalLLM: Lossless Self-Speculative Decoding withLayer Embedded Self-Compression

2025

AAAI-22

Interpretable Multimodal Dialogue System with Natural Language-Based Multimodal Integration

2022