Cover Image

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Shuochen, Zhang, Xiaofeng, Liu, Qingyang, Niu, Li
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MuMA-ToM: Multi-modal Multi-Agent Theory of Mind
by: Shi, Haojun, et al.
Published: (2024)

Context Tokens are Anchors: Understanding the Repetition Curse in dMLLMs from an Information Flow Perspective
by: Zhao, Qiyan, et al.
Published: (2026)

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
by: Yang, Enneng, et al.
Published: (2024)

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
by: Li, Chaoyu, et al.
Published: (2025)

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs
by: Han, Tianyang, et al.
Published: (2024)

Image Generation Based on Image Style Extraction
by: Chang, Shuochen
Published: (2025)

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
by: Wu, Qiong, et al.
Published: (2024)

Multimodal Latent Language Modeling with Next-Token Diffusion
by: Sun, Yutao, et al.
Published: (2024)

Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
by: Li, He, et al.
Published: (2026)

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
by: Shi, Dachuan, et al.
Published: (2023)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

Not All Tokens Matter Equally: Dynamic In-context Vector Distillation with Decisive-Token Supervision for Long-form Medical Report Generation
by: Wu, Ning, et al.
Published: (2026)

M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
by: AI, Inclusion, et al.
Published: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
by: Zou, Chang, et al.
Published: (2024)

Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language Models
by: Yi, Hao, et al.
Published: (2024)

Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP
by: Kim, Eunji, et al.
Published: (2024)

MLLMs-Augmented Visual-Language Representation Learning
by: Liu, Yanqing, et al.
Published: (2023)

Token Caching for Diffusion Transformer Acceleration
by: Lou, Jinming, et al.
Published: (2024)

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
by: Li, Yulin, et al.
Published: (2025)

SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions
by: Fan, Xianzhe, et al.
Published: (2025)

Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding
by: Xiao, Zhongyu, et al.
Published: (2026)

Multi-Task Model Merging via Adaptive Weight Disentanglement
by: Xiong, Feng, et al.
Published: (2024)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
by: He, Yifei, et al.
Published: (2024)

Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
by: Du, Yao, et al.
Published: (2026)

Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs
by: Xu, Xiao, et al.
Published: (2025)

Realistic Evaluation of Model Merging for Compositional Generalization
by: Tam, Derek, et al.
Published: (2024)

Linking Perception, Confidence and Accuracy in MLLMs
by: Du, Yuetian, et al.
Published: (2026)

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
by: Zhang, Yiming, et al.
Published: (2024)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
by: Zhang, Evelyn, et al.
Published: (2024)

Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder
by: Li, Siting, et al.
Published: (2024)

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
by: Zhang, Jun, et al.
Published: (2024)

How to Merge Your Multimodal Models Over Time?
by: Dziadzio, Sebastian, et al.
Published: (2024)

DAM: Dynamic Adapter Merging for Continual Video QA Learning
by: Cheng, Feng, et al.
Published: (2024)

HiDrop: Hierarchical Vision Token Reduction in MLLMs via Late Injection, Concave Pyramid Pruning, and Early Exit
by: Wu, Hao, et al.
Published: (2026)

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
by: Fan, Ziyang, et al.
Published: (2026)

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
by: Chang, Shuochen, et al.
Published: (2026)

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
by: Shu, Fangxun, et al.
Published: (2025)

Parameter Competition Balancing for Model Merging
by: Du, Guodong, et al.
Published: (2024)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
by: Zhong, Yiwu, et al.
Published: (2024)

MileBench: Benchmarking MLLMs in Long Context
by: Song, Dingjie, et al.
Published: (2024)