Author

Liqun Huang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

VIG: Visual Information Gain as a Reward Signal for Multimodal Chain-of-Thought Compression

Across six main multimodal reasoning benchmarks and three Qwen3-VL-Thinking model sizes, VIG consistently improves the accuracy--efficiency trade-off, supporting the central claim: efficient multimodal reasoning emerges from raising visual information density.

Wen Luo, Xiao-Han Yi, Xiao-Tao Huang et al. · 0 citations