MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models
cs.CV
Submitted: 2026-09-27
Updated: 2026-09-27
Comments: 13 pages
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- DeepSeek-VL: Towards Real-World Vision-Language Understanding
- Qwen2.5-VL Technical Report
- LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models
- RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models
- Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
- GRASP: Guided Region-Aware Sparse Prompting for Adapting MLLMs to Remote Sensing
- Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain
- MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
- MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
- Universal Transformers
- Looped Transformers are Better at Learning Learning Algorithms
- Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
- Looping Back to Move Forward: Recursive Transformers for Efficient and Flexible Large Multimodal Models
- Gaussian Error Linear Units (GELUs)
- Decoupled Weight Decay Regularization
- SGDR: Stochastic Gradient Descent with Warm Restarts
- SVIT: Scaling up Visual Instruction Tuning
- To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning
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