MiCo: Mutual Information Coverage Optimization through Semantic Erasure Modeling for Efficient MLLM Inference
cs.CV
Submitted: 2026-09-28
Updated: 2026-09-30
Terminology
Sources
- GPT-4 Technical Report
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen3-VL Technical Report
- Qwen2.5-VL Technical Report
- Are We on the Right Way for Evaluating Large Vision-Language Models?
- SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- The Llama 3 Herd of Models
- GREC: Generalized Referring Expression Comprehension
- Gemini: A Family of Highly Capable Multimodal Models
- PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
- Qwen3 Technical Report
- LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models
- SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models