Babak Ehteshami Bejnordi

KaVa: Latent Reasoning via Compressed KV-Cache Distillation

2025 · arXiv (Cornell University)

Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhead, and often carry redundant, stylistic artifacts. Latent reasoning has emerged as an …