LatentRouter: Can We Choose the Right Multimodal Large Language Model Before Seeing Its Answer?
cs.AI, cs.CL, cs.CV
Submitted: 2026-05-11
Updated: 2026-11-15
Code: https://github.com/LabRAI/LatentRouter
Terminology
Sources
- AutoMix: Automatically Mixing Language Models
- Phi-4-reasoning-vision-15B Technical Report
- Qwen2.5-VL Technical Report
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
- A Unified Approach to Routing and Cascading for LLMs
- Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
- GraphRouter: A Graph-based Router for LLM Selections
- OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
- Training Large Language Models to Reason in a Continuous Latent Space
- PLUME: Latent Reasoning Based Universal Multimodal Embedding
- RouterBench: A Benchmark for Multi-LLM Routing System
- Efficient Multimodal Large Language Models: A Survey
- Text encoders bottleneck compositionality in contrastive vision-language models
- LLaVA-OneVision: Easy Visual Task Transfer
- A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks
- OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
- MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents