RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Terminology
Sources
- OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- LLaVA-OneVision: Easy Visual Task Transfer
- SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
- Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning
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