Remote sensing image fusion and semantic interpretation are usually optimized separately, so reconstruction quality need not preserve downstream retrieval utility. We propose LANCE, which uses structured language as an explicit, indexable semantic state. A frozen vision–language model maps the input to a closed-vocabul...
Guang-Yuan Dong, Ling-Dong Shen, Xu-Dong Zhang et al.· Proceedings of the 35th ACM...· 1 citation
Remote sensing image fusion and semantic interpretation are usually optimized separately, so reconstruction quality need not preserve downstream retrieval utility. We propose LANCE, which uses structured language as an explicit, indexable semantic state. A frozen vision-language model maps the input to a closed-vocabul...
Guang-Yuan Dong, Ling-Dong Shen, Xu-Dong Zhang et al.· 0 citations
Inspired by Kahneman's account of fast and slow thinking, MemDuet is a dual-process memory framework that learns to coordinate a small language model for fast, parallel evidence selection from raw context chunks with a large language model for memory-update verification and memory updates in document order.
Jiang-Cheng Song, Hao-Dong Jing, Yu-Ling Mu et al.· 0 citations
The results show that sharing observations across objectives and ignoring irrelevant objective-wise distinctions can substantially reduce the sampling cost, as confirmed by experiments on synthetic and real-world tasks.
Bo Xue, Yi-Lu Liu, Hao-Dong Jing et al.· 0 citations
Spatial-OPSD, a label-free self-improvement framework that instead exploits spatial structure naturally available from perception and reconstruction tools, is introduced, achieving the highest average among the open models and the best results on three of five spatial reasoning benchmarks.
Zhen-Yu Liu, Zhangquan Chen, Ke-Yi Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.