Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence
Ling Lin, Yang Bai, Congcong Zhu +6
Multimodal large language models (MLLMs) have demonstrated significant potential in complex spatial scene understanding and reasoning tasks. However, their open-ended reasoning pro…
cs.CV2024
Evolutionary Generalized Zero-Shot Learning
Dubing Chen, Chenyi Jiang, Haofeng Zhang
Attribute-based Zero-Shot Learning (ZSL) has revolutionized the ability of models to recognize new classes not seen during training. However, with the advancement of large-scale mo…