recommendation

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Expertsarxiv.org

IntBMoE introduces block‑level conditioning to MoE, decoupling token participation, compute execution, and memory materialization. A hypernetwork merges all experts into a composed expert per block, while routing remains sparse. Dual‑Path Residual Gating further mixes two composed paths. Experiments show consistent gains on vision, language, and recommendation tasks, and the model is live in AMap…