5 papers
MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs
Zhongyang Li, Yaqian Li, Faming Fang +6
Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence for language modeling. Most e…
CSD: Content-aware Speculative Decoding for Efficient Image Generation
Mingcheng Wang, Junbo Qiao, Yunchen Li +8
Speculative decoding (SD) has emerged as a key solution to accelerate the inference of autoregressive models. However, in the field of image generation, it faces the challenge of l…
QMoP: Query Guided Mixture-of-Projector for Efficient Visual Token Compression
Zhongyang Li, Yaqian Li, Faming Fang +6
Multimodal large language models suffer from severe computational and memory bottlenecks, as the number of visual tokens far exceeds that of textual tokens. While recent methods em…
First-order State Space Model for Lightweight Image Super-resolution
Yujie Zhu, Xinyi Zhang, Yekai Lu +3
State space models (SSMs), particularly Mamba, have shown promise in NLP tasks and are increasingly applied to vision tasks. However, most Mamba-based vision models focus on networ…
Monocular Depth Estimation with Global-Aware Discretization and Local Context Modeling
Heng Wu, Qian Zhang, Guixu Zhang
Accurate monocular depth estimation remains a challenging problem due to the inherent ambiguity that stems from the ill-posed nature of recovering 3D structure from a single view,…