Tag
This paper proposes UniF-MoE, a unified framework for token-adaptive Mixture-of-Experts computation that first shares reusable computation across experts and then routes the remaining residual demand, improving performance while reducing activated computation, latency, and memory on DomainBed and GLUE benchmarks.
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.