🗣️ Dialogue Systems

📷 CVPR2026 · 1 paper notes

Evolutionary Multimodal Reasoning via Hierarchical Semantic Representation for Intent Recognition

This paper proposes HIER, which combines hierarchical semantic representation (a three-level hierarchy of tokens → concepts → relations) with a self-evolutionary reasoning mechanism driven by MLLM feedback, consistently outperforming SOTA methods and leading MLLMs by 1–3% on three multimodal intent recognition benchmarks.