Copertina

Neural Flow Samplers with Shortcut Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Wuhao, Ou, Zijing, Li, Yingzhen
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Inference-Time Scaling of Discrete Diffusion Models via Importance Weighting and Optimal Proposal Design
di: Ou, Zijing, et al.
Pubblicazione: (2025)

Mutual Information Multinomial Estimation
di: Chen, Yanzhi, et al.
Pubblicazione: (2024)

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

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

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

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

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

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

Neural Mutual Information Estimation with Vector Copulas
di: Chen, Yanzhi, et al.
Pubblicazione: (2025)

Corrected Samplers for Discrete Flow Models
di: Wan, Zhengyan, et al.
Pubblicazione: (2026)

Spectral Transformer Neural Processes
di: Chen, Xianhe, et al.
Pubblicazione: (2026)

A Convolution and Attention Based Encoder for Reinforcement Learning under Partial Observability
di: Wang, Wuhao, et al.
Pubblicazione: (2025)

Structured Coupling for Flow Matching
di: Sumba, Xavier, et al.
Pubblicazione: (2026)

Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Feature Learning by Learnable Channel Attention
di: Yang, Yingzhen
Pubblicazione: (2025)

Progressive Tempering Sampler with Diffusion
di: Rissanen, Severi, et al.
Pubblicazione: (2025)

Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression
di: Yang, Yingzhen, et al.
Pubblicazione: (2024)

Models Know Their Shortcuts: Deployment-Time Shortcut Mitigation
di: Li, Jiayi, et al.
Pubblicazione: (2026)

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

Proximal Diffusion Neural Sampler
di: Guo, Wei, et al.
Pubblicazione: (2025)

Elucidating Rectified Flow with Deterministic Sampler: Polynomial Discretization Complexity for Multi and One-step Models
di: Yang, Ruofeng, et al.
Pubblicazione: (2025)

Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping
di: Yang, Yingzhen, et al.
Pubblicazione: (2024)

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

No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
di: He, Jiajun, et al.
Pubblicazione: (2025)

On The Hidden Biases of Flow Matching Samplers
di: Lim, Soon Hoe
Pubblicazione: (2025)

Multi-State TD Target for Model-Free Reinforcement Learning
di: Wang, Wuhao, et al.
Pubblicazione: (2024)

Training Neural Samplers with Reverse Diffusive KL Divergence
di: He, Jiajun, et al.
Pubblicazione: (2024)

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

ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models
di: Zheng, Guangtao, et al.
Pubblicazione: (2025)

HiBBO: HiPPO-based Space Consistency for High-dimensional Bayesian Optimisation
di: Xuan, Junyu, et al.
Pubblicazione: (2025)

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

Liouville Flow Importance Sampler
di: Tian, Yifeng, et al.
Pubblicazione: (2024)

Swift Sampler: Efficient Learning of Sampler by 10 Parameters
di: Yao, Jiawei, et al.
Pubblicazione: (2024)

One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
di: Jutras-Dube, Pascal, et al.
Pubblicazione: (2025)

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
di: Cai, Xu, et al.
Pubblicazione: (2025)

Improved Generalization Bounds for Transductive Learning by Transductive Local Complexity and Its Applications
di: Yang, Yingzhen
Pubblicazione: (2023)

Entropy-based Training Methods for Scalable Neural Implicit Sampler
di: Luo, Weijian, et al.
Pubblicazione: (2023)

Projective Proximal Gradient Descent for A Class of Nonconvex Nonsmooth Optimization Problems: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property
di: Yang, Yingzhen, et al.
Pubblicazione: (2023)

Bayesian Computation in Deep Learning
di: Chen, Wenlong, et al.
Pubblicazione: (2025)

Is Your Diffusion Sampler Actually Correct? A Sampler-Centric Evaluation of Discrete Diffusion Language Models
di: Tang, Luhan, et al.
Pubblicazione: (2026)