Author

Ming-Da Li

h-index 4 View on Semantic Scholar

We have 1 of 9 papers

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

LUT: Latent Utility Training for Visual Reasoning

Experiments on perception-intensive visual reasoning benchmarks show that LUT outperforms previous latent reasoning methods and remains competitive with latent-text interleaved methods with lower annotation cost.

J. Kang, Siyue Chen, Mingda Li et al. · 1 citation