Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models
cs.CV, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- One Layer's Trash is Another Layer's Treasure: Adaptive Layer-wise Visual Token Selection in LVLMs
- GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
- KV Prediction for Improved Time to First Token
- Kimi-VL Technical Report
- LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
- Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference
- EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model
- GPT-4o System Card
- SwiftVLM: Efficient Vision-Language Model Inference via Cross-Layer Token Bypass
- Qwen3-VL Technical Report
- Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
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