Skip to main content
Search

# Entropy-aware Decoding

1 related articles

Subscribe to updates
  1. arXiv

    Entropy curves become an alarm for multimodal reasoning: SEED realigns vision mid-decode and lifts six benchmarks by 3.2%–3.7% on average

    Multimodal large language models often hallucinate content unfaithful to the image during long-chain reasoning, and SEED treats the entropy of the decoding process as a real-time diagnostic: when a trajectory sits in a relatively low-entropy convergence regime while showing a local entropy spike, it triggers a visual attention realignment. The training-free method improves average accuracy by 3.2%–3.7% across six benchmarks and nine settings on Qwen3-VL-8B, Qwen3-VL-4B and Llama-3.2-11B, adding less than 5% inference latency.

You’re all caught up