Imagen de Portada

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Scimeca, Luca, Jiralerspong, Thomas, Earnshaw, Berton, Hartford, Jason, Bengio, Yoshua
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
por: Jiralerspong, Thomas, et al.
Publicado: (2025)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
por: Scimeca, Luca, et al.
Publicado: (2023)

Scalable Ensemble Diversification for OOD Generalization and Detection
por: Rubinstein, Alexander, et al.
Publicado: (2024)

Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery
por: Teng, Mélisande, et al.
Publicado: (2025)

Causally Steered Diffusion for Automated Video Counterfactual Generation
por: Spyrou, Nikos, et al.
Publicado: (2025)

Learning What Matters: Prioritized Concept Learning via Relative Error-driven Sample Selection
por: Chandhok, Shivam, et al.
Publicado: (2025)

Decoding Vision Transformers: the Diffusion Steering Lens
por: Takatsuki, Ryota, et al.
Publicado: (2025)

Inline Critic Steers Image Editing
por: Kang, Weitai, et al.
Publicado: (2026)

Learning Spectral Diffusion Prior for Hyperspectral Image Reconstruction
por: Yu, Mingyang, et al.
Publicado: (2025)

MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
por: Pham, Trong-Thang, et al.
Publicado: (2026)

Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Model
por: Kim, Kwanyoung, et al.
Publicado: (2025)

Multi-view Image Diffusion via Coordinate Noise and Fourier Attention
por: Theiss, Justin, et al.
Publicado: (2024)

NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
por: Zheng, PengFei, et al.
Publicado: (2024)

GuidNoise: Single-Pair Guided Diffusion for Generalized Noise Synthesis
por: Kim, Changjin, et al.
Publicado: (2025)

Optical Flow Matters: an Empirical Comparative Study on Fusing Monocular Extracted Modalities for Better Steering
por: Makiyeh, Fouad, et al.
Publicado: (2024)

A Complexity-Based Theory of Compositionality
por: Elmoznino, Eric, et al.
Publicado: (2024)

SteerDiff: Steering towards Safe Text-to-Image Diffusion Models
por: Zhang, Hongxiang, et al.
Publicado: (2024)

Improved Noise Schedule for Diffusion Training
por: Hang, Tiankai, et al.
Publicado: (2024)

PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
por: Wang, Yibin, et al.
Publicado: (2024)

NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
por: Wu, Fang, et al.
Publicado: (2026)

What Matters in Practical Learned Image Compression
por: Tatwawadi, Kedar, et al.
Publicado: (2026)

QNCD: Quantization Noise Correction for Diffusion Models
por: Chu, Huanpeng, et al.
Publicado: (2024)

Aligning Diffusion Models with Noise-Conditioned Perception
por: Gambashidze, Alexander, et al.
Publicado: (2024)

DiffusionNFT: Online Diffusion Reinforcement with Forward Process
por: Zheng, Kaiwen, et al.
Publicado: (2025)

What Matters for Scalable and Robust Learning in End-to-End Driving Planners?
por: Holtz, David, et al.
Publicado: (2026)

What Matters to You? Towards Visual Representation Alignment for Robot Learning
por: Tian, Ran, et al.
Publicado: (2023)

Training Convolutional Neural Networks with the Forward-Forward algorithm
por: Scodellaro, Riccardo, et al.
Publicado: (2023)

LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction
por: Huang, Shuwei, et al.
Publicado: (2026)

Language Models Can Explain Visual Features via Steering
por: Ferrando, Javier, et al.
Publicado: (2026)

Stabilizing Diffusion Posterior Sampling by Noise--Frequency Continuation
por: Tian, Feng, et al.
Publicado: (2026)

Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
por: Donhauser, Konstantin, et al.
Publicado: (2024)

Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion
por: Karnik, Sathwik, et al.
Publicado: (2026)

Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
por: Papachristodoulou, Andreas, et al.
Publicado: (2023)

Agentic Surgical AI: Surgeon Style Fingerprinting and Privacy Risk Quantification via Discrete Diffusion in a Vision-Language-Action Framework
por: Zhan, Huixin, et al.
Publicado: (2025)

Resource-efficient Medical Image Analysis with Self-adapting Forward-Forward Networks
por: Müller, Johanna P., et al.
Publicado: (2024)

Forward Learning for Gradient-based Black-box Saliency Map Generation
por: Zhang, Zeliang, et al.
Publicado: (2024)

CoBELa: Steering Transparent Generation via Concept Bottlenecks on Energy Landscapes
por: Kim, Sangwon, et al.
Publicado: (2025)

Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
por: Prakash, Nirmalendu, et al.
Publicado: (2026)

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
por: Ding, Wei, et al.
Publicado: (2026)

There and Back Again: On the relation between Noise and Image Inversions in Diffusion Models
por: Staniszewski, Łukasz, et al.
Publicado: (2024)