cross-layer

DepthWeave-KV is a token-adaptive cross-layer residual factorization method for compressing KV cache in long-context transformer inference, achieving 8.3x memory reduction and 72.8 tokens/s at 64K context while preserving near-full-cache task quality across benchmarks.

InnerZoom proposes a single-forward framework for cross-layer evidence bridging in GUI grounding, achieving state-of-the-art performance on multiple benchmarks while reducing latency by up to 31.8%.