Tianyu Fu

Cache-to-Cache: Direct Semantic Communication Between Large Language Models

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression