Conditional Visual Evidence Utility: State-Dependent Rank Reversals in Frozen Vision-Language Encoders
cs.CV
Submitted: 2026-08-28
Updated: 2026-09-23
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
- The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
- Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding
- V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs
- SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
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