← Search

Songlin Fei

2 accepted papers

2026

Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning

AAAI 2026technical

Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However, ICL performance remains unstable even when the in-context dem

Cited by 0SourcePDFScholar
2024

Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors

ECCV 2024poster

"We introduce , featuring the first collection of 600,000 environmentally aware, 3D simulation-ready tree models generated through Diffusion priors. Each reconstructed 3D tree model corresponds to an image from Google’s Auto Arborist Dataset, comprising street view images and associated genus labels…

Cited by 4SourcePDFScholar