64 citations · 256 across the 76 of their papers we have counts for
9 papers · 1 filter
RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
Jingqi Xu, Jingxi Lu, Chenghao Li +3
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vis…
Bitwidth-Specific Logarithmic Arithmetic for Future Hardware-Accelerated Training
Hassan Hamad, Yuou Qiu, Peter A. Beerel +1
While advancements in quantization have significantly reduced the computational costs of inference in deep learning, training still predominantly relies on complex floating-point a…
HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score
Jingqi Xu, Jingxi Lu, Chenghao Li +2
Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders i…
LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling
Zeyu Liu, Souvik Kundu, Lianghao Jiang +5
Although transformer architectures have achieved state-of-the-art performance across diverse domains, their quadratic computational complexity with respect to sequence length remai…
Opto-ViT: Architecting a Near-Sensor Region of Interest-Aware Vision Transformer Accelerator with Silicon Photonics
Mehrdad Morsali, Chengwei Zhou, Deniz Najafi +7
Vision Transformers (ViTs) have emerged as a powerful architecture for computer vision tasks due to their ability to model long-range dependencies and global contextual relationshi…
FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings
Jingqi Xu, Chenghao Li, Yuke Zhang +1
Diffusion models have demonstrated remarkable potential in generating high-quality images. However, their tendency to replicate training data raises serious privacy concerns, parti…