HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 13764-13778
Abstract
No abstract availableThis publication has 32 references indexed in Scilit:
- Instruction-guided fusion of multi-layer visual features in Large Vision-Language ModelsPattern Recognition, 2025
- OCRBench: on the hidden mystery of OCR in large multimodal modelsScience China Information Sciences, 2024
- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models2024
- MMBench: Is Your Multi-modal Model an All-Around Player?2024
- V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs2024
- GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering2019
- Towards VQA Models That Can Read2019
- VizWiz Grand Challenge: Answering Visual Questions from Blind People2018
- Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering2017
- A Diagram is Worth a Dozen Images2016