BtsPruner: Role-Aware Visual Token Pruning for Large Vision-Language Models
cs.CV, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Code: https://github.com/Halenbest/BtsPruner
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen Technical Report
- Matryoshka Multimodal Models
- Efficient Large Multi-modal Models via Visual Context Compression
- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
- Mistral 7B
- TokenPacker: Efficient Visual Projector for Multimodal LLM
- Evaluating Object Hallucination in Large Vision-Language Models
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
- Gemini: A Family of Highly Capable Multimodal Models
- LLaMA: Open and Efficient Foundation Language Models
- PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
- Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment
- VisionZip: Longer is Better but Not Necessary in Vision Language Models
- Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
- MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
- SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs