Authors

Kewei Zhang

Publications 2

Preprint Open access

ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation

Ruicheng Zhang, Kaiwen Shen, Jiaqi Hou et al. · 2026

Generalized referring expression segmentation (GRES) requires dynamically balancing high-level semantics for identifying a variable number of language-specified referents with fine-grained visual evidence for precise boundary delineation. This requirement challenges existing cascaded vision-language architectures, whic …

Preprint Open access

SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models

Kewei Zhang, Zheng Chen, Haotong Qin et al. · 2026

Recent foundation models are moving toward native multimodal Vision-Language Models (VLMs), making VLMs a central form of next-generation foundation models. However, their large language backbones make edge deployment difficult due to high memory footprint and memory-bound autoregressive decoding. Weight-only post-trai …

Co-authors