Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models
cs.LG
Submitted: 2026-05-25
Updated: 2026-11-05
Code: https://github.com/infiniteYuanyl/VRCD
Terminology
Sources
- Flamingo: a Visual Language Model for Few-Shot Learning
- Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Efficient Large Multi-modal Models via Visual Context Compression
- Optimizing Decoding Paths in Masked Diffusion Models by Quantifying Uncertainty
- From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
- Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
- Accelerating Diffusion LLMs via Adaptive Parallel Decoding
- Learning Unmasking Policies for Diffusion Language Models
- DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
- Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
- A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models
- RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
- Why Diffusion Language Models Struggle with Truly Parallel (Non-Autoregressive) Decoding?
- Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models
- LaViDa: A Large Diffusion Language Model for Multimodal Understanding
- Visual Instruction Tuning
- Plan for Speed: Dilated Scheduling for Masked Diffusion Language Models
- Large Language Diffusion Models
- Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis