An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Authors:
Top Cited Papers
- 1 November 2024
- book chapter
- Published by Springer Nature
- p. 19-35
Abstract
No abstract availableKeywords
This publication has 20 references indexed in Scilit:
- PYRA: Parallel Yielding Re-activation for Training-Inference Efficient Task Adaptation2024
- LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models2024
- Improved Baselines with Visual Instruction Tuning2024
- MMMU: A Massive Multi-Discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI2024
- Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action2024
- Monkey: Image Resolution and Text Label are Important Things for Large Multi-Modal Models2024
- A-OKVQA: A Benchmark for Visual Question Answering Using World Knowledge2022
- SPViT: Enabling Faster Vision Transformers via Latency-Aware Soft Token Pruning2022
- TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering2017
- CIDEr: Consensus-based image description evaluation2015