3 papers
cs.LG2026
RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression
Zhengjia Zhong, Shuyan Ke, Zaizhou Lin +3
Vector quantization is a fundamental tool for compressing high-dimensional embeddings, yet existing multi-codebook methods rely on static codebooks that limit expressiveness under…
cs.CV2025
HCC-3D: Hierarchical Compensatory Compression for 98% 3D Token Reduction in Vision-Language Models
Liheng Zhang, Jin Wang, Hui Li +2
3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VL…
cs.CV2025
Fine-Grained Customized Fashion Design with Image-into-Prompt benchmark and dataset from LMM
Hui Li, Yi You, Qiqi Chen +2
Generative AI evolves the execution of complex workflows in industry, where the large multimodal model empowers fashion design in the garment industry. Current generation AI models…