Upgrading embedding models in production vector databases typically necessitates reencoding the entire corpus and rebuilding the Approximate Nearest Neighbor (ANN) index, leading to significant operational disruption and computational cost.This paper presents Drift-Adapter, a lightweight, learnable transformation layer designed to bridge embedding spaces between model versions.By mapping new queries into the legacy embedding space, Drift-Adapter enables the continued use of the existing ANN index, effectively deferring full re-computation.We systematically evaluate three adapter parameterizations: Orthogonal Procrustes, Low-Rank Affine, and a compact Residual MLP, trained on a small sample of paired old/new embeddings.Experiments on MTEB text corpora and a CLIP image model upgrade (1M items) show that Drift-Adapter recovers 95-99% of the retrieval recall (Recall@10, MRR) of a full re-embedding, adding less than 10 µs query latency.Compared to operational strategies like full re-indexing or dual-index serving, Drift-Adapter dramatically reduces recompute costs (by over 100×) and facilitates upgrades with near-zero operational interruption.We analyze robustness to varied model drift, training data size, scalability to billion-item systems, and the impact of design choices like diagonal scaling, demonstrating Drift-Adapter's viability as a pragmatic solution for agile model deployment.

Mixture-of-Experts (MoE) layers scale transformers by routing tokens to a sparse subset of feed-forward experts.Token-level routing, however, assigns an entire semantic spectrum to each expert, creating capacity bottlenecks, load-balancing pathologies, and limited specialisation.We introduce SliceMoE, an architecture that routes contiguous slices of a token's hidden vector.A d-dimensional embedding is partitioned into S slices, and for each slice, a lightweight shared router predicts the top-k experts.Experts operate on their assigned slices independently, and outputs are re-assembled, maintaining per-token FLOP efficiency.Because slices from different tokens interleave within an expert, utilisation is naturally smoother.We propose a slice-level capacity loss, cross-slice dropout, and efficient fused batched-GEMM kernels.Experiments on WikiText-103 language modelling, WMT En-De translation, and three text-classification datasets show SliceMoE attains up to 1.7× faster inference than dense baselines, 12-18% lower perplexity than parameter-matched token-MoE, and improved expert balance, with interpretable expertise over syntactic versus semantic sub-spaces.