English
Related papers

Related papers: Inference-Time Alignment of Diffusion Models via T…

200 papers

Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity of the reference…

Machine Learning · Statistics 2026-02-05 Jinyuan Chang , Chenguang Duan , Yuling Jiao , Yi Xu , Jerry Zhijian Yang

Diffusion models are state-of-the-art generative models, yet their samples often fail to satisfy application objectives such as safety constraints or domain-specific validity. Existing techniques for alignment require gradients, internal…

We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt $\exp(\lambda r)$ into $N$ sequential smaller tilts, each admitting a…

Machine Learning · Statistics 2025-12-04 Jean Pachebat , Giovanni Conforti , Alain Durmus , Yazid Janati

Diffusion and flow models achieve State-Of-The-Art (SOTA) generative performance, yet many practically important behaviors such as fine-grained prompt fidelity, compositional correctness, and text rendering are weakly specified by score or…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yuanzhi Zhu , Xi Wang , Stéphane Lathuilière , Vicky Kalogeiton

Sampling-based model predictive control (MPC) algorithms, such as model predictive path integral (MPPI), enable approximate, gradient-free solutions to optimal control problems by drawing samples from a proposal distribution, evaluating…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Markus Walker , Marcel Reith-Braun , Daniel Frisch , Uwe D. Hanebeck

Leveraging the model's internal information as the self-reward signal in Reinforcement Learning (RL) has received extensive attention due to its label-free nature. While prior works have made significant progress in applying the Test-Time…

Machine Learning · Computer Science 2026-03-18 Xizhong Yang , Yinan Xia , Huiming Wang , Mofei Song

A common recipe to improve diffusion models at test-time so that samples score highly against a user-specified reward is to introduce the gradient of the reward into the dynamics of the diffusion itself. This procedure is often ill posed,…

Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settings is achieving comprehensive mode coverage, ensuring the…

Machine Learning · Computer Science 2025-05-27 Chenguang Wang , Xiaoyu Zhang , Kaiyuan Cui , Weichen Zhao , Yongtao Guan , Tianshu Yu

Restricted Boltzmann Machines are simple and powerful generative models that can encode any complex dataset. Despite all their advantages, in practice the trainings are often unstable and it is difficult to assess their quality because the…

Machine Learning · Computer Science 2023-03-16 Nicolas Béreux , Aurélien Decelle , Cyril Furtlehner , Beatriz Seoane

We propose a new Monte Carlo method for sampling from multimodal distributions. The idea of this technique is based on splitting the task into two: finding the modes of a target distribution $\pi$ and sampling, given the knowledge of the…

Computation · Statistics 2019-01-14 Emilia Pompe , Chris Holmes , Krzysztof Łatuszyński

Reflected diffusions in polyhedral domains are commonly used as approximate models for stochastic processing networks in heavy traffic. Stationary distributions of such models give useful information on the steady state performance of the…

Probability · Mathematics 2012-05-24 Amarjit Budhiraja , Jiang Chen , Sylvain Rubenthaler

Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores. This alignment typically requires…

The particle filter (PF), also known as sequential Monte Carlo (SMC), approximates high-dimensional probability distributions and their normalizing constants in the discrete-time setting. To reduce the variance of the Monte Carlo…

Computation · Statistics 2026-05-05 Jianfeng Lu , Yuliang Wang

Monte Carlo Tree Search (MCTS) has emerged as a powerful tool for decision-making in robotics, enabling efficient exploration of large search spaces. However, traditional MCTS methods struggle in environments characterized by high…

Robotics · Computer Science 2025-03-10 Xibai Wang

Inference-time controllable generation is essential for real-world applications of unconditional diffusion models. However, most existing techniques focus on individual samples, struggling in applications that require the sample population…

Machine Learning · Computer Science 2026-05-11 Hao Luan , See-Kiong Ng , Chun Kai Ling

Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classical (dual-ascent) IRL guarantees monotonic performance improvement but requires fully…

Machine Learning · Computer Science 2026-05-13 Anish Diwan , Davide Tateo , Christopher E. Mower , Haitham Bou-Ammar , Jan Peters , Oleg Arenz

Discrete diffusion models are a class of generative models that produce samples from an approximated data distribution within a discrete state space. Often, there is a need to target specific regions of the data distribution. Current…

Machine Learning · Computer Science 2025-09-03 Cheuk Kit Lee , Paul Jeha , Jes Frellsen , Pietro Lio , Michael Samuel Albergo , Francisco Vargas

We propose sequential Monte Carlo (SMC) methods for sampling the posterior distribution of state-space models under highly informative observation regimes, a situation in which standard SMC methods can perform poorly. A special case is…

Computation · Statistics 2015-07-10 Pierre Del Moral , Lawrence M. Murray

In the context of Bayesian inversion for scientific and engineering modeling, Markov chain Monte Carlo sampling strategies are the benchmark due to their flexibility and robustness in dealing with arbitrary posterior probability density…

Computation · Statistics 2021-12-07 Han Lu , Mohammad Khalil , Thomas Catanach , Jiefu Chen , Xuqing Wu , Xin Fu , Cosmin Safta , Yueqin Huang

A core problem in statistics and probabilistic machine learning is to compute probability distributions and expectations. This is the fundamental problem of Bayesian statistics and machine learning, which frames all inference as…

Machine Learning · Statistics 2024-12-06 Christian A. Naesseth , Fredrik Lindsten , Thomas B. Schön