SOURCE-LINKED INTELLIGENCE

Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Multi-encoder fusion extends Large Audio-Language Models (LALMs) beyond speech-centric recognition, but selecting encoders via intuition or exhaustive search often introduces redundant representations and inflates an already constrained compute budget. We propose CUES (Correlation-gUided Encoder Selection), a lightweight heuristic that estimates complementarity through task- and category-level Pearson correlations between encoders' performance profiles, scoring a candidate set from single-encoder evaluations alone--without fusion training during selection. Evaluated on the XARES-LLM benchmark

Read original source ↗ Open in workspace

recordType

paper

region

Global