Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
5 papers published across 1 lab.
HeteroFold unlocks $10.7\times$ faster cross-family KV cache transfer for LLMs, eliminating receiver prefill and matching text-based communication performance.
Latent communication can be compressed by 75% without accuracy loss by conditioning KV cache transmissions on receiver information needs.
This study proposes an adaptive EFL writing feedback generation framework that combines a dual-stream generative network, low-rank adaptation, and proximal policy optimization to solve the challenges of coarse intervention granularity and homogeneous feedback in EFL writing.