Imagen de Portada

Equivariant Deep Weight Space Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Navon, Aviv, Shamsian, Aviv, Fetaya, Ethan, Chechik, Gal, Dym, Nadav, Maron, Haggai
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Improved Generalization of Weight Space Networks via Augmentations
por: Shamsian, Aviv, et al.
Publicado: (2024)

Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization
por: Shamsian, Aviv, et al.
Publicado: (2025)

PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space
por: Buchnick, Asaf, et al.
Publicado: (2026)

Multi Task Inverse Reinforcement Learning for Common Sense Reward
por: Glazer, Neta, et al.
Publicado: (2024)

GradMetaNet: An Equivariant Architecture for Learning on Gradients
por: Gelberg, Yoav, et al.
Publicado: (2025)

Drax: Speech Recognition with Discrete Flow Matching
por: Navon, Aviv, et al.
Publicado: (2025)

Keyword-Guided Adaptation of Automatic Speech Recognition
por: Shamsian, Aviv, et al.
Publicado: (2024)

Beyond Transcription: Mechanistic Interpretability in ASR
por: Glazer, Neta, et al.
Publicado: (2025)

Spanning the Visual Analogy Space with a Weight Basis of LoRAs
por: Manor, Hila, et al.
Publicado: (2026)

On the Expressive Power of Permutation-Equivariant Weight-Space Networks
por: Dayan, Adir, et al.
Publicado: (2026)

WhisperNER: Unified Open Named Entity and Speech Recognition
por: Ayache, Gil, et al.
Publicado: (2024)

Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR
por: Segal-Feldman, Yael, et al.
Publicado: (2024)

FlowTSE: Target Speaker Extraction with Flow Matching
por: Navon, Aviv, et al.
Publicado: (2025)

Efficient GNN Training Through Structure-Aware Randomized Mini-Batching
por: Balaji, Vignesh, et al.
Publicado: (2025)

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
por: Putterman, Theo, et al.
Publicado: (2024)

Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
por: Achituve, Idan, et al.
Publicado: (2024)

UmbraTTS: Adapting Text-to-Speech to Environmental Contexts with Flow Matching
por: Glazer, Neta, et al.
Publicado: (2025)

Weisfeiler Leman for Euclidean Equivariant Machine Learning
por: Hordan, Snir, et al.
Publicado: (2024)

Equivariant Frames and the Impossibility of Continuous Canonicalization
por: Dym, Nadav, et al.
Publicado: (2024)

Revisiting Multi-Permutation Equivariance through the Lens of Irreducible Representations
por: Sverdlov, Yonatan, et al.
Publicado: (2024)

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
por: Yemini, Yochai, et al.
Publicado: (2023)

Adversarial Attacks in Weight-Space Classifiers
por: Shor, Tamir, et al.
Publicado: (2025)

Diverse Sampling in Diffusion Models with Marginal Preserving Particle Guidance
por: Vinograd, Gal, et al.
Publicado: (2026)

A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
por: Bar-Shalom, Guy, et al.
Publicado: (2024)

On the Hölder Stability of Multiset and Graph Neural Networks
por: Davidson, Yair, et al.
Publicado: (2024)

Fourier Sliced-Wasserstein Embedding for Multisets and Measures
por: Amir, Tal, et al.
Publicado: (2024)

Online Weighted Paging with Unknown Weights
por: Levy, Orin, et al.
Publicado: (2024)

FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
por: Elbaz, Ran, et al.
Publicado: (2025)

Training Transformers for KV Cache Compressibility
por: Gelberg, Yoav, et al.
Publicado: (2026)

Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
por: Bar-Shalom, Guy, et al.
Publicado: (2025)

Fourier Sliced-Wasserstein Embedding for Multisets and Measures
por: Amir, Tal, et al.
Publicado: (2025)

On the (Non) Injectivity of Piecewise Linear Janossy Pooling
por: Reshef, Ilai, et al.
Publicado: (2025)

On the Expressive Power of Sparse Geometric MPNNs
por: Sverdlov, Yonatan, et al.
Publicado: (2024)

LR-DWM: Efficient Watermarking for Diffusion Language Models
por: Raban, Ofek, et al.
Publicado: (2026)

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning
por: Tamirisa, Rishub, et al.
Publicado: (2024)

It Takes a Graph to Know a Graph: Rewiring for Homophily with a Reference Graph
por: Mendelman, Harel, et al.
Publicado: (2025)

RoboArm-NMP: a Learning Environment for Neural Motion Planning
por: Jurgenson, Tom, et al.
Publicado: (2024)

DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles
por: Daniel, Tal, et al.
Publicado: (2023)

Quantitative Approximation Rates for Group Equivariant Learning
por: Siegel, Jonathan W., et al.
Publicado: (2026)

Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them
por: Hordan, Snir, et al.
Publicado: (2026)