Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation
Zihua Wang, Ruibo Li, Haozhe Du +3
Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handl…
cs.CV2025
GRAM-MAMBA: Holistic Feature Alignment for Wireless Perception with Adaptive Low-Rank Compensation
Weiqi Yang, Xu Zhou, Jingfu Guan +2
Multi-modal fusion is crucial for Internet of Things (IoT) perception, widely deployed in smart homes, intelligent transport, industrial automation, and healthcare. However, existi…