Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but aggressive compression can sharply degrade performance, often attributed to irreversible loss of task-relevant visual information. We show...
Ahmadreza Jeddi, En-Ming Zhang, Jasper Gerigk et al.· 0 citations
Results show that a persistent open-vocabulary 3D scene map can be maintained directly by a single vision-language model using only a lightweight text representation.
Adam Lilja, Fabio Hübel, Si-Ming He et al.· 0 citations
WildCity, a real-world multimodal dataset collected by autonomous fleets traversing complex urban environments, aims to catalyze progress not only in city-scale rendering, but more broadly in the pursuit of AI that can perceive, remember, and reason across space at a scale comparable to human cognition.
Xiangyu Han, Mengyu Yang, Jiaqi Li et al.· arXiv.org· 0 citations
This work proposes COMPACT-VA, a planning-aligned working memory framework built on conditional VQ-VAE, compressing extended context into bounded representations, and evaluates on high-signal dynamic scenarios where historical context is most critical for behavior correctness, and accordingly design behavioral metrics.
Zhixuan Liang, Yuxiao Chen, Yurong You et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
