Imagen de Portada

Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cho, Hyunmin, Han, Woo Kyoung, Jin, Kyong Hwan
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Geometry-Aware Attention Guidance for Diffusion Models via Modern Hopfield Dynamics
por: Kim, Kwanyoung
Publicado: (2026)

Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
por: Ahn, Donghoon, et al.
Publicado: (2024)

Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
por: Han, Woo Kyoung, et al.
Publicado: (2025)

NoiseFormer -- Noise Diffused Symmetric Attention Transformer
por: Kumar, Phani, et al.
Publicado: (2026)

Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models
por: Wu, Dennis, et al.
Publicado: (2024)

Outlier-Efficient Hopfield Layers for Large Transformer-Based Models
por: Hu, Jerry Yao-Chieh, et al.
Publicado: (2024)

Nonparametric Modern Hopfield Models
por: Hu, Jerry Yao-Chieh, et al.
Publicado: (2024)

On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis
por: Hu, Jerry Yao-Chieh, et al.
Publicado: (2024)

Interpretable Diffusion via Information Decomposition
por: Kong, Xianghao, et al.
Publicado: (2023)

Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies
por: Zhou, Changhai, et al.
Publicado: (2025)

BiSHop: Bi-Directional Cellular Learning for Tabular Data with Generalized Sparse Modern Hopfield Model
por: Xu, Chenwei, et al.
Publicado: (2024)

Evo: Autoregressive-Diffusion Large Language Models with Evolving Balance
por: Wu, Junde, et al.
Publicado: (2026)

Symmetric Reinforcement Learning Loss for Robust Learning on Diverse Tasks and Model Scales
por: Byun, Ju-Seung, et al.
Publicado: (2024)

Robust Policy Learning via Offline Skill Diffusion
por: Kim, Woo Kyung, et al.
Publicado: (2024)

A Noise is Worth Diffusion Guidance
por: Ahn, Donghoon, et al.
Publicado: (2024)

Balancing Graph Embedding Smoothness in Self-Supervised Learning via Information-Theoretic Decomposition
por: Jung, Heesoo, et al.
Publicado: (2025)

Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model
por: Lin, Han, et al.
Publicado: (2024)

In-Context Policy Adaptation via Cross-Domain Skill Diffusion
por: Yoo, Minjong, et al.
Publicado: (2025)

On the Role of Hidden States of Modern Hopfield Network in Transformer
por: Masumura, Tsubasa, et al.
Publicado: (2025)

Deep Generative Model for Mechanical System Configuration Design
por: Etesam, Yasaman, et al.
Publicado: (2024)

HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing
por: Fang, Yuan, et al.
Publicado: (2026)

Scalable Diffusion for Materials Generation
por: Yang, Sherry, et al.
Publicado: (2023)

Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks
por: Moriai, Ryo, et al.
Publicado: (2025)

Symmetric Equilibrium Propagation for Thermodynamic Diffusion Training
por: De, Aditi
Publicado: (2026)

High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training
por: Huang, Zhuoyi, et al.
Publicado: (2025)

SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention
por: Xu, Hongtao, et al.
Publicado: (2026)

DPAC: Distribution-Preserving Adversarial Control for Diffusion Sampling
por: Lee, Han-Jin, et al.
Publicado: (2025)

e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration
por: Cheong, Hyunmin, et al.
Publicado: (2025)

Attention-based Iterative Decomposition for Tensor Product Representation
por: Park, Taewon, et al.
Publicado: (2024)

SEA: State-Exchange Attention for High-Fidelity Physics Based Transformers
por: Esmati, Parsa, et al.
Publicado: (2024)

Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation
por: Gu, Shangding, et al.
Publicado: (2024)

RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals
por: Heo, Jaemu, et al.
Publicado: (2025)

Self-Tuning Sparse Attention: Multi-Fidelity Hyperparameter Optimization for Transformer Acceleration
por: Dev, Arundhathi, et al.
Publicado: (2026)

Revealing the Attention Floating Mechanism in Masked Diffusion Models
por: Dai, Xin, et al.
Publicado: (2026)

ToMA: Token Merge with Attention for Diffusion Models
por: Lu, Wenbo, et al.
Publicado: (2025)

Auditing Language Model Unlearning via Information Decomposition
por: Goel, Anmol, et al.
Publicado: (2026)

CURing Large Models: Compression via CUR Decomposition
por: Park, Sanghyeon, et al.
Publicado: (2025)

LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights
por: Dewage, Kasun, et al.
Publicado: (2026)

Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion
por: Che, Xujun, et al.
Publicado: (2026)

Efficient Diffusion Models for Symmetric Manifolds
por: Mangoubi, Oren, et al.
Publicado: (2025)