Yinhong Liu

A strong LLM can review grounded drafts from a weak model, retaining most task performance while halving latency and memory traffic.

The current RL checkpoint outperforms larger LLMs in redesigning training environments, revealing that iterative learning enhances diagnostic capabilities.

A single pair of boundary tokens transforms hidden-state reasoning into a trainable and interpretable framework, revealing causal insights that were previously obscured.

Operadic consistency reveals a powerful new way to diagnose reasoning failures in LLMs, achieving correlations with accuracy that exceed traditional confidence metrics.

Multilingual spoken dialogue systems still struggle with consistent performance across languages, even with high-resource languages, as shown by a new large-scale dataset.