Related papers: TFTF: Training-Free Targeted Flow for Conditional …

Image retouching, aiming to regenerate the visually pleasing renditions of given images, is a subjective task where the users are with different aesthetic sensations. Most existing methods deploy a deterministic model to learn the…

We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic…

Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each training sample supervises only a single trajectory and…

The cost of Monte Carlo sampling of lattice configurations is very high in the critical region of lattice field theory due to the high correlation between the samples. This paper suggests a Conditional Normalizing Flow (C-NF) model for…

The negative sampling strategy can effectively train collaborative filtering (CF) recommendation models based on implicit feedback by constructing positive and negative samples. However, existing methods primarily optimize the negative…

Understanding temporal dynamics in medical imaging is crucial for applications such as disease progression modeling, treatment planning and anatomical development tracking. However, most deep learning methods either consider only single…

Sampling from unnormalized densities is analogous to the generative modeling problem, but the target distribution is defined by a known energy function instead of data samples. Because evaluating the energy function is often costly, a…

Expanding on neural operators, we propose a novel framework for stochastic process learning across arbitrary domains. In particular, we develop operator flow matching (OFM) for learning stochastic process priors on function spaces. OFM…

Coarse-grained (CG) molecular simulations have become a standard tool to study molecular processes on time- and length-scales inaccessible to all-atom simulations. Parameterizing CG force fields to match all-atom simulations has mainly…

We present a novel framework for performing statistical sampling, expectation estimation, and partition function approximation using \emph{arbitrary} heuristic stochastic processes defined over discrete state spaces. Using a highly parallel…

Energy-based models (EBMs) are a powerful class of probabilistic generative models due to their flexibility and interpretability. However, relationships between potential flows and explicit EBMs remain underexplored, while contrastive…

We present a new method, Non-Stationary Forward Flux Sampling, that allows efficient simulation of rare events in both stationary and non-stationary stochastic systems. The method uses stochastic branching and pruning to achieve uniform…

Distilled autoregressive diffusion models facilitate real-time short video synthesis but suffer from severe error accumulation during long-sequence generation. While existing Test-Time Optimization (TTO) methods prove effective for images…

Guidance of generative models is typically achieved by modifying the probability flow vector field through the addition of a guidance field. In this paper, we instead propose the Source-Guided Flow Matching (SGFM) framework, which modifies…

Flow Matching enables simulation-free training of generative models on Riemannian manifolds, yet sampling typically still relies on numerically integrating a probability-flow ODE. We propose Riemannian MeanFlow (RMF), extending MeanFlow to…

Inverse rendering aims to recover scene geometry, material properties, and lighting from multi-view images. Given the complexity of light-surface interactions, importance sampling is essential for the evaluation of the rendering equation,…

Importance sampling is a Monte Carlo method that introduces a proposal distribution to sample the space according to the target distribution. Yet calibration of the proposal distribution is essential to achieving efficiency, thus the resort…

Inspired by the \emph{Well-initialized Lottery Ticket Hypothesis (WLTH)}, we introduce Soft-Transformer (Soft-TF), a parameter-efficient framework for continual learning that leverages soft, real-valued subnetworks over a frozen pre-trained…

Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires estimating the value function. This task demands access to…

Data scarcity has been the main factor that hinders the progress of event extraction. To overcome this issue, we propose a Self-Training with Feedback (STF) framework that leverages the large-scale unlabeled data and acquires feedback for…