Cover Image

Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ou, Zijing, Pani, Chinmay, Li, Yingzhen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discrete Neural Flow Samplers with Locally Equivariant Transformer
by: Ou, Zijing, et al.
Published: (2025)

Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
by: Schröder, Tobias, et al.
Published: (2024)

Neural Flow Samplers with Shortcut Models
by: Chen, Wuhao, et al.
Published: (2025)

Improving Probabilistic Diffusion Models With Optimal Diagonal Covariance Matching
by: Ou, Zijing, et al.
Published: (2024)

TabRep: Training Tabular Diffusion Models with a Simple and Effective Continuous Representation
by: Si, Jacob, et al.
Published: (2025)

Mutual Information Multinomial Estimation
by: Chen, Yanzhi, et al.
Published: (2024)

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

Diffusion Alignment Beyond KL: Variance Minimisation as Effective Policy Optimiser
by: Ou, Zijing, et al.
Published: (2026)

Memory-Driven Self-Improvement for Decision Making with Large Language Models
by: Yan, Xue, et al.
Published: (2025)

Target Concrete Score Matching: A Holistic Framework for Discrete Diffusion
by: Zhang, Ruixiang, et al.
Published: (2025)

Learning with Importance Weighted Variational Inference
by: Daudel, Kamélia, et al.
Published: (2024)

Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions
by: Kiyohara, Naoki, et al.
Published: (2025)

VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
by: Wang, Leyang, et al.
Published: (2025)

Inference-Time Scaling of Diffusion Language Models via Trajectory Refinement
by: Dang, Meihua, et al.
Published: (2025)

Importance Weighted Variational Inference without the Reparameterization Trick
by: Daudel, Kamélia, et al.
Published: (2026)

Parameter Inference via Differentiable Diffusion Bridge Importance Sampling
by: Boserup, Nicklas, et al.
Published: (2024)

Calibrating Transformers via Sparse Gaussian Processes
by: Chen, Wenlong, et al.
Published: (2023)

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
by: Bai, Jinbin, et al.
Published: (2026)

Importance Weighted Expectation-Maximization for Protein Sequence Design
by: Song, Zhenqiao, et al.
Published: (2023)

Optimal Inference Schedules for Masked Diffusion Models
by: Chen, Sitan, et al.
Published: (2025)

Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate
by: Yang, Yingzhen, et al.
Published: (2026)

Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference
by: Fox, David, et al.
Published: (2026)

Adaptive Inference-Time Scaling via Cyclic Diffusion Search
by: Lee, Gyubin, et al.
Published: (2025)

Scaling Behavior of Discrete Diffusion Language Models
by: von Rütte, Dimitri, et al.
Published: (2025)

Do Diffusion Models Dream of Electric Planes? Discrete and Continuous Simulation-Based Inference for Aircraft Design
by: Ghiglino, Aurelien, et al.
Published: (2026)

A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillation
by: Song, Xinran, et al.
Published: (2025)

MarkovScale: Towards Optimal Sequential Scaling at Inference Time
by: Wang, Youkang, et al.
Published: (2026)

Diffusion on Graph: Augmentation of Graph Structure for Node Classification
by: Wang, Yancheng, et al.
Published: (2025)

DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models
by: Ren, Yinuo, et al.
Published: (2025)

High-Dimensional Importance-Weighted Information Criteria: Theory and Optimality
by: Cao, Yong-Syun, et al.
Published: (2025)

Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization
by: Li, Minhuan, et al.
Published: (2026)

Free energy Estimation on Any State Space
by: He, Jiajun, et al.
Published: (2026)

Inference-Time Alignment of Diffusion Models via Evolutionary Algorithms
by: Jajal, Purvish, et al.
Published: (2025)

Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage
by: Wang, Chenguang, et al.
Published: (2025)

Membership Inference Attacks on Discrete Diffusion Language Models
by: Kasivelrajan, Shailesh
Published: (2026)

Learning Informative Attention Weights for Person Re-Identification
by: Wang, Yancheng, et al.
Published: (2025)

Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement
by: Kang, Taegu, et al.
Published: (2026)

Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
by: Zhang, Zikun, et al.
Published: (2024)

The Cosine Schedule is Fisher-Rao-Optimal for Masked Discrete Diffusion Models
by: Zhang, Leo, et al.
Published: (2025)

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
by: Ou, Jingyang, et al.
Published: (2024)