C squared-Routing: Complementary Cropping and Compression for Efficient Vision-Language Inference
cs.CV, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- Qwen2.5-VL Technical Report
- Input-Adaptive Visual Preprocessing for Efficient Fast Vision-Language Model Inference
- PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking
- Can Multimodal Large Language Models Truly Understand Small Objects?
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models
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