Image de couverture de livre

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhao, Chongyang, Li, Mingsong, Lu, Haodong, Gong, Dong
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
par: Xu, Zukang, et autres
Publié: (2026)

Scaling Capability in Token Space: An Analysis of Large Vision Language Model
par: Li, Tenghui, et autres
Publié: (2024)

EAC-MoE: Expert-Selection Aware Compressor for Mixture-of-Experts Large Language Models
par: Chen, Yuanteng, et autres
Publié: (2025)

Reinforcement Learning with Promising Tokens for Large Language Models
par: Pang, Jing-Cheng, et autres
Publié: (2026)

Expert Divergence Learning for MoE-based Language Models
par: Li, Jiaang, et autres
Publié: (2026)

LocMoE: A Low-Overhead MoE for Large Language Model Training
par: Li, Jing, et autres
Publié: (2024)

GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory
par: Wu, Haoze, et autres
Publié: (2024)

Length-MAX Tokenizer for Language Models
par: Dong, Dong, et autres
Publié: (2025)

Collaborative Compression for Large-Scale MoE Deployment on Edge
par: Chen, Yixiao, et autres
Publié: (2025)

MoE-PHDS: One MoE checkpoint for flexible runtime sparsity
par: Hannah, Lauren. A, et autres
Publié: (2025)

Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modelling
par: Ganescu, Bianca-Mihaela, et autres
Publié: (2025)

FFT-MoE: Efficient Federated Fine-Tuning for Foundation Models via Large-scale Sparse MoE under Heterogeneous Edge
par: Hu, Gang, et autres
Publié: (2025)

Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling
par: Liao, Ning, et autres
Publié: (2025)

ProToken: Token-Level Attribution for Federated Large Language Models
par: Gill, Waris, et autres
Publié: (2026)

Token-Efficient Leverage Learning in Large Language Models
par: Zeng, Yuanhao, et autres
Publié: (2024)

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models
par: Pasten, Hector, et autres
Publié: (2025)

MoE$^2$: Optimizing Collaborative Inference for Edge Large Language Models
par: Jin, Lyudong, et autres
Publié: (2025)

PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts
par: Su, Yang, et autres
Publié: (2025)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
par: Guo, Zhenyuan, et autres
Publié: (2026)

Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
par: Wang, Siqi, et autres
Publié: (2024)

D$^{2}$MoE: Dual Routing and Dynamic Scheduling for Efficient On-Device MoE-based LLM Serving
par: Wang, Haodong, et autres
Publié: (2025)

SD-MoE: Spectral Decomposition for Effective Expert Specialization
par: Huang, Ruijun, et autres
Publié: (2026)

Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs
par: Li, Bo, et autres
Publié: (2026)

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
par: Li, Bo, et autres
Publié: (2026)

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs
par: Zhang, Wuyue, et autres
Publié: (2026)

Counterfactual Token Generation in Large Language Models
par: Chatzi, Ivi, et autres
Publié: (2024)

ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate
par: Lafuente-Mercado, Rodney
Publié: (2026)

Training-Trajectory-Aware Token Selection
par: Shen, Zhanming, et autres
Publié: (2026)

Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning
par: Milecki, Leo, et autres
Publié: (2026)

Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding
par: Zhang, Zhongjian, et autres
Publié: (2026)

Exploring Token Pruning in Vision State Space Models
par: Zhan, Zheng, et autres
Publié: (2024)

DOT-MoE: Differentiable Optimal Transport for MoEfication
par: Bamba, Udbhav, et autres
Publié: (2026)

Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language to Multimodality
par: Kong, Zhenglun, et autres
Publié: (2025)

Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Series Analysis with Large Language Models
par: Li, Musheng, et autres
Publié: (2026)

Cognitive Load-Aware Inference: A Neuro-Symbolic Framework for Optimizing the Token Economy of Large Language Models
par: Zhang, Yilun
Publié: (2025)

UniMoT: Unified Molecule-Text Language Model with Discrete Token Representation
par: Guo, Shuhan, et autres
Publié: (2024)

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
par: Li, Yu, et autres
Publié: (2026)

Compositional Steering of Large Language Models with Steering Tokens
par: Radevski, Gorjan, et autres
Publié: (2026)

Probabilistic Token Alignment for Large Language Model Fusion
par: Zeng, Runjia, et autres
Publié: (2025)

DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
par: Jin, Can, et autres
Publié: (2025)