Cover Image

Composition of Memory Experts for Diffusion World Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Stapf, Sebastian, Huertos, Pablo Acuaviva, Davtyan, Aram, Favaro, Paolo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Communication-Inspired Tokenization for Structured Image Representations
by: Davtyan, Aram, et al.
Published: (2026)

From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models
by: Acuaviva, Pablo, et al.
Published: (2025)

Rethinking Visual Intelligence: Insights from Video Pretraining
by: Acuaviva, Pablo, et al.
Published: (2025)

Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation
by: Davtyan, Aram, et al.
Published: (2023)

KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products
by: Xia, Zixuan, et al.
Published: (2025)

Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling
by: Davtyan, Aram, et al.
Published: (2026)

PoE-World: Compositional World Modeling with Products of Programmatic Experts
by: Piriyakulkij, Wasu Top, et al.
Published: (2025)

Counterfactual Probabilistic Diffusion with Expert Models
by: Mu, Wenhao, et al.
Published: (2025)

Compositional Planning with Jumpy World Models
by: Farebrother, Jesse, et al.
Published: (2026)

Neurosymbolic Grounding for Compositional World Models
by: Sehgal, Atharva, et al.
Published: (2023)

MELINOE: Fine-Tuning Enables Memory-Efficient Inference for Mixture-of-Experts Models
by: Raje, Arian, et al.
Published: (2026)

BuddyMoE: Exploiting Expert Redundancy to Accelerate Memory-Constrained Mixture-of-Experts Inference
by: Wang, Yun, et al.
Published: (2025)

KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
by: Davtyan, Aram, et al.
Published: (2021)

Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning
by: Li, Shangzhe, et al.
Published: (2025)

UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts
by: Wang, Fu-Yun, et al.
Published: (2025)

Diffusion Transformers as Open-World Spatiotemporal Foundation Models
by: Yuan, Yuan, et al.
Published: (2024)

World Models via Policy-Guided Trajectory Diffusion
by: Rigter, Marc, et al.
Published: (2023)

PROTECT: Protein circadian time prediction using unsupervised learning
by: Ogholbake, Aram Ansary, et al.
Published: (2025)

Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions
by: Veeriah, Vivek, et al.
Published: (2025)

AnyExperts: On-Demand Expert Allocation for Multimodal Language Models with Mixture of Expert
by: Gao, Yuting, et al.
Published: (2025)

Efficiently Editing Mixture-of-Experts Models with Compressed Experts
by: He, Yifei, et al.
Published: (2025)

Joint MoE Scaling Laws: Mixture of Experts Can Be Memory Efficient
by: Ludziejewski, Jan, et al.
Published: (2025)

Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detection
by: Huang, Xiaoyu, et al.
Published: (2024)

Variational Distillation of Diffusion Policies into Mixture of Experts
by: Zhou, Hongyi, et al.
Published: (2024)

Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models
by: Liang, Jingcong, et al.
Published: (2025)

Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs
by: Galesloot, Maris F. L., et al.
Published: (2025)

Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity
by: Xiong, Guangzhi, et al.
Published: (2026)

Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures
by: Nguyen-Nhat, Minh-Khoi, et al.
Published: (2025)

Forget Forgetting: Continual Learning in a World of Abundant Memory
by: Cho, Dongkyu, et al.
Published: (2025)

Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models
by: Hoover, Benjamin, et al.
Published: (2023)

Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning
by: Ding, Zihan, et al.
Published: (2024)

MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts
by: Xie, Zhitian, et al.
Published: (2024)

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models
by: Liu, Jing, et al.
Published: (2024)

Mixture of Experts in a Mixture of RL settings
by: Willi, Timon, et al.
Published: (2024)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
by: Lee, Jihoon, et al.
Published: (2025)

RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks
by: Liu, Ningyuan, et al.
Published: (2025)

Causal Composition Diffusion Model for Closed-loop Traffic Generation
by: Lin, Haohong, et al.
Published: (2024)

Reliable Trajectory Prediction and Uncertainty Quantification with Conditioned Diffusion Models
by: Neumeier, Marion, et al.
Published: (2024)

Mixture of Experts in Large Language Models
by: Zhang, Danyang, et al.
Published: (2025)

MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
by: Yang, Cheng, et al.
Published: (2024)