Copertina

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Oldfield, James, Georgopoulos, Markos, Chrysos, Grigorios G., Tzelepis, Christos, Panagakis, Yannis, Nicolaou, Mihalis A., Deng, Jiankang, Patras, Ioannis
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multilinear Operator Networks
di: Cheng, Yixin, et al.
Pubblicazione: (2024)

Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
di: Oldfield, James, et al.
Pubblicazione: (2025)

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery
di: Demou, Andreas D., et al.
Pubblicazione: (2026)

Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2026)

Environment-Aware Satellite Image Generation with Diffusion Models
di: Kostagiolas, Nikos, et al.
Pubblicazione: (2025)

Enabling Local Editing in Diffusion Models by Joint and Individual Component Analysis
di: Kouzelis, Theodoros, et al.
Pubblicazione: (2024)

PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2026)

Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2024)

Are CLIP features all you need for Universal Synthetic Image Origin Attribution?
di: Cioni, Dario, et al.
Pubblicazione: (2024)

MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance
di: Meng, Debin, et al.
Pubblicazione: (2024)

Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks
di: Cheng, Yixin, et al.
Pubblicazione: (2024)

A Principled Framework for Multi-View Contrastive Learning
di: Koromilas, Panagiotis, et al.
Pubblicazione: (2025)

One-shot Neural Face Reenactment via Finding Directions in GAN's Latent Space
di: Bounareli, Stella, et al.
Pubblicazione: (2024)

DiffusionAct: Controllable Diffusion Autoencoder for One-shot Face Reenactment
di: Bounareli, Stella, et al.
Pubblicazione: (2024)

CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning
di: Krestenitis, Marios, et al.
Pubblicazione: (2026)

MI-NeRF: Learning a Single Face NeRF from Multiple Identities
di: Chatziagapi, Aggelina, et al.
Pubblicazione: (2024)

MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
di: Chatziagapi, Aggelina, et al.
Pubblicazione: (2024)

Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models
di: Wang, Jeffrey, et al.
Pubblicazione: (2026)

Specializing Foundation Models via Mixture of Low-Rank Experts for Comprehensive Head CT Analysis
di: Yoo, Youngjin, et al.
Pubblicazione: (2026)

Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
di: Zhao, Zengqun, et al.
Pubblicazione: (2026)

Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling
di: Chu, Sanghyeok, et al.
Pubblicazione: (2026)

Domain-Specialized Object Detection via Model-Level Mixtures of Experts
di: Pavlitska, Svetlana, et al.
Pubblicazione: (2026)

Audio-visual video-to-speech synthesis with synthesized input audio
di: Kefalas, Triantafyllos, et al.
Pubblicazione: (2023)

Large-scale unsupervised audio pre-training for video-to-speech synthesis
di: Kefalas, Triantafyllos, et al.
Pubblicazione: (2023)

Neural Experts: Mixture of Experts for Implicit Neural Representations
di: Ben-Shabat, Yizhak, et al.
Pubblicazione: (2024)

ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization
di: Cheng, Anzhe, et al.
Pubblicazione: (2025)

Self-Supervised Facial Representation Learning with Facial Region Awareness
di: Gao, Zheng, et al.
Pubblicazione: (2024)

Prompting Visual-Language Models for Dynamic Facial Expression Recognition
di: Zhao, Zengqun, et al.
Pubblicazione: (2023)

Three Heads Are Better Than One: Complementary Experts for Long-Tailed Semi-supervised Learning
di: Ma, Chengcheng, et al.
Pubblicazione: (2023)

MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding
di: Chopra, Shivang, et al.
Pubblicazione: (2025)

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
di: Deschenaux, Justin, et al.
Pubblicazione: (2024)

Metanetworks as Regulatory Operators: Learning to Edit for Requirement Compliance
di: Kalogeropoulos, Ioannis, et al.
Pubblicazione: (2025)

Scale Equivariant Graph Metanetworks
di: Kalogeropoulos, Ioannis, et al.
Pubblicazione: (2024)

Exploring Expert Specialization through Unsupervised Training in Sparse Mixture of Experts
di: Nikolic, Strahinja, et al.
Pubblicazione: (2025)

The Last Mile to Supervised Performance: Semi-Supervised Domain Adaptation for Semantic Segmentation
di: Morales-Brotons, Daniel, et al.
Pubblicazione: (2024)

Alpha Divergence Losses for Biometric Verification
di: Koutsianos, Dimitrios, et al.
Pubblicazione: (2025)

LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
di: Zhao, Zengqun, et al.
Pubblicazione: (2026)

Sparse Mixture-of-Experts for Non-Uniform Noise Reduction in MRI Images
di: Deng, Zeyun, et al.
Pubblicazione: (2025)

YOLO Meets Mixture-of-Experts: Adaptive Expert Routing for Robust Object Detection
di: Meiraz, Ori, et al.
Pubblicazione: (2025)

GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection
di: Psiris, Aggelos, et al.
Pubblicazione: (2026)