Dongyan Zhao

Mixture-of-Experts (MoE) scales capacity via conditional computation, but Transformers lack a native knowledge lookup primitive. We introduce conditional memory, instantiated via Deep Sparse Embedding (DSE), which indexes a massive embedding table using local n-grams for retrieval. We formalize s...

The rapid progress of large language models (LLMs) has increased the demand for efficient and reliable evaluation of question answering (QA) systems. Existing evaluation methods either rely on rule-based matching with shallow semantic understanding or adopt LLM-as-a-Judge approaches that incur hi...

Long-reasoning models achieve strong accuracy on complex reasoning tasks, but their extended reasoning trajectories incur substantial memory and latency costs. Several existing shortening methods rely on additional supervision or multi-stage post-training, which primarily reduces inference length...