Imagen de Portada

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ma, Nanye, Tong, Shangyuan, Jia, Haolin, Hu, Hexiang, Su, Yu-Chuan, Zhang, Mingda, Yang, Xuan, Li, Yandong, Jaakkola, Tommi, Jia, Xuhui, Xie, Saining
Formato:	Preprint
Publicado:	2025
Materias:	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

Flow Map Distillation Without Data
por: Tong, Shangyuan, et al.
Publicado: (2025)

Diffusion Transformers with Representation Autoencoders
por: Zheng, Boyang, et al.
Publicado: (2025)

Next Semantic Scale Prediction via Hierarchical Diffusion Language Models
por: Zhou, Cai, et al.
Publicado: (2025)

Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
por: Lifar, Egor, et al.
Publicado: (2026)

Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders
por: Tong, Shengbang, et al.
Publicado: (2026)

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
por: Ma, Nanye, et al.
Publicado: (2024)

Transition Matching Distillation for Fast Video Generation
por: Nie, Weili, et al.
Publicado: (2026)

Deconstructing Denoising Diffusion Models for Self-Supervised Learning
por: Chen, Xinlei, et al.
Publicado: (2024)

Think While You Generate: Discrete Diffusion with Planned Denoising
por: Liu, Sulin, et al.
Publicado: (2024)

BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing
por: Chen, Jiacheng, et al.
Publicado: (2025)

Continuously Tempered Diffusion Samplers
por: Erives, Ezra, et al.
Publicado: (2025)

Correcting Diffusion Generation through Resampling
por: Liu, Yujian, et al.
Publicado: (2023)

A Cosmic-Scale Benchmark for Symmetry-Preserving Data Processing
por: Balla, Julia, et al.
Publicado: (2024)

Epsilon-VAE: Denoising as Visual Decoding
por: Zhao, Long, et al.
Publicado: (2024)

ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos
por: Yang, Haolin, et al.
Publicado: (2025)

Deep Confident Steps to New Pockets: Strategies for Docking Generalization
por: Corso, Gabriele, et al.
Publicado: (2024)

Calibrated Selective Classification
por: Fisch, Adam, et al.
Publicado: (2022)

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
por: Jing, Bowen, et al.
Publicado: (2023)

Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models
por: Erives, Ezra, et al.
Publicado: (2024)

LEAPS: A discrete neural sampler via locally equivariant networks
por: Holderrieth, Peter, et al.
Publicado: (2025)

AI-based Methods for Simulating, Sampling, and Predicting Protein Ensembles
por: Jing, Bowen, et al.
Publicado: (2025)

AlphaFold Meets Flow Matching for Generating Protein Ensembles
por: Jing, Bowen, et al.
Publicado: (2024)

Hamiltonian Score Matching and Generative Flows
por: Holderrieth, Peter, et al.
Publicado: (2024)

Instruct-Imagen: Image Generation with Multi-modal Instruction
por: Hu, Hexiang, et al.
Publicado: (2024)

DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
por: Xu, Yilun, et al.
Publicado: (2024)

Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy
por: Chun, Inkook, et al.
Publicado: (2025)

Navigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
por: Su, Xun, et al.
Publicado: (2025)

Diffusion models in protein structure and docking
por: Jason Yim, et al.
Publicado: (2024)

Residual Denoising Diffusion Models
por: Liu, Jiawei, et al.
Publicado: (2023)

ProxelGen: Generating Proteins as 3D Densities
por: Faltings, Felix, et al.
Publicado: (2025)

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning
por: Liu, Yujian, et al.
Publicado: (2024)

Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective
por: Liu, Yujian, et al.
Publicado: (2024)

Harmonic Self-Conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
por: Stärk, Hannes, et al.
Publicado: (2023)

Generative Modeling of Molecular Dynamics Trajectories
por: Jing, Bowen, et al.
Publicado: (2024)

Protein FID: Improved Evaluation of Protein Structure Generative Models
por: Faltings, Felix, et al.
Publicado: (2025)

Sample, estimate, aggregate: A recipe for causal discovery foundation models
por: Wu, Menghua, et al.
Publicado: (2024)

Thought calibration: Efficient and confident test-time scaling
por: Wu, Menghua, et al.
Publicado: (2025)

Fewer Denoising Steps or Cheaper Per-Step Inference: Towards Compute-Optimal Diffusion Model Deployment
por: Du, Zhenbang, et al.
Publicado: (2025)

Remasking Discrete Diffusion Models with Inference-Time Scaling
por: Wang, Guanghan, et al.
Publicado: (2025)

GLASS Flows: Transition Sampling for Alignment of Flow and Diffusion Models
por: Holderrieth, Peter, et al.
Publicado: (2025)