MHR-Router: Multimodal Heterogeneous Retrieval-Enhanced Adaptive Routing for VLM Inference

cs.LG

Submitted: 2026-10-09

Updated: 2026-10-09

Project page: https://llava-vl.github.io

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Pro-Router: Token-Aware Progressive Model Routing with Adaptive Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
• MoA-Off: Adaptive Heterogeneous Modality-Aware Offloading with Edge-Cloud Collaboration for Efficient Multimodal LLM Inference
• An Effective Router for Vision-Language Model Selection
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Qwen2.5-VL Technical Report
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks