Meta Proposes New Fusion Framework for LLM Recommendations

_reachsumit · x · 2026-07-14

Meta has proposed a **soft-token fusion** framework for LLM-based recommendation systems. The method maps numerical and embedding features into the LLM's embedding space to improve retrieval performance in LLM-based two-tower recommendation models. The post notes that this approach enhances recall, representing a methodological advancement in the field.

Original post →

More from Research

Research channel →