GitHub

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

In vision-language models (VLMs), visual tokens usually consume a significant amount of computational overhead, despite their sparser information density compared to text tokens. To address this, ...
GitHub

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction (CVPR 2025)

[2025.3.6] [Update🔥] Please place any models that need to be compatible with pdrop in this issue [2025.2.27] 🚀 Our paper has been accepted by CVPR 2025!!! [2024.10.24] 🚀 Our paper has been featured ...
Idaho Public Press on MSN

Disney turned Fourth of July fireworks into a 24-hour TV bet

Disney’s America 250 celebration used fireworks, parks, ABC News and streaming platforms to turn July Fourth into a ...
IEEE

NVILA: Efficient Frontier Visual Language Models

Abstract: Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of ...
IEEE

Mitigating Object Hallucination in Large Vision-Language Models via Visual Attention Direct Preference Optimization

Abstract: Large Vision-Language Models (LVLMs) suffer from severe object hallucinations, leading them to frequently generate outputs that do not correspond to the image content, significantly reducing ...