Yanhong Li

Distilling to Hybrid Attention Models via KL-Guided Layer Selection

On the Predictive Power of Representation Dispersion in Language Models

Substituting from the Input: Distilling Sequential Computation in Transformer Language Models

Reduce What You Use: Input‑Aware Matrix‑Multiplication Pruning for LLMs

OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand Open Knowledge Benchmarking

Chunk-Distilled Language Modeling