Author

Yiming Xu

View on Semantic Scholar

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

Seeing Before Answering: Training-Free Visual Layer Profiling for Vision-Language Models

Pre-projector VDE tracks layer-wise accuracy and its top-ranked layers cover the oracle best layer on every task for the SigLIP-based LLaVA-Video, while giving region-level guidance for the CLIP-based Video-LLaVA.

Ruchen Liu, Yi Yang, Yiming Xu et al. · 0 citations