Related papers: AReUReDi: Annealed Rectified Updates for Refining …
Diffusion Models represent a significant advancement in generative modeling, employing a dual-phase process that first degrades domain-specific information via Gaussian noise and restores it through a trainable model. This framework enables…
The effectiveness of collision-free trajectory planners depends on the quality and diversity of training data, especially for rare scenarios. A widely used approach to improve dataset diversity involves generating realistic synthetic…
Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging due to interleaved inference and noisy log-probability…
The scarcity of annotated surgical data poses a significant challenge for developing deep learning systems in computer-assisted interventions. While diffusion models can synthesize realistic images, they often suffer from data memorization,…
We propose a unified diffusion model-based correction and super-resolution method to enhance the fidelity and resolution of diverse low-quality data through a two-step pipeline. First, the correction step employs a novel enhanced stochastic…
The design and implementation of a new framework for adaptive mesh refinement (AMR) calculations is described. It is intended primarily for applications in astrophysical fluid dynamics, but its flexible and modular design enables its use…
Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper…
We introduce $\texttt{PairFlow}$, a lightweight preprocessing step for training Discrete Flow Models (DFMs) to achieve few-step sampling without requiring a pretrained teacher. DFMs have recently emerged as a new class of generative models…
Advancements in deep learning have significantly improved model performance across tasks involving code, text, and image processing. However, these models still exhibit notable mispredictions in real-world applications, even when trained on…
The caliber and configuration of retinal blood vessels serve as important biomarkers for various diseases and medical conditions. A thorough analysis of the retinal vasculature requires the segmentation of the blood vessels and their…
Unsupervised depth completion and estimation methods are trained by minimizing reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are amongst the many undesirable by-products of common data…
Adaptive medical AI models often face performance drops in dynamic clinical environments due to data drift. We propose an autonomous continuous monitoring and data integration framework that maintains robust performance over time. Focusing…
Deep neural networks (DNNs) have substantial computational and memory requirements, and the compilation of its computational graphs has a great impact on the performance of resource-constrained (e.g., computation, I/O, and memory-bound)…
Speculative decoding is an effective technique for accelerating large language model inference by drafting multiple tokens in parallel. In practice, its speedup is often bottlenecked by a rigid verification step that strictly enforces the…
Drug development and pharmacovigilance are frequently bottlenecked by legacy clinical reporting pipelines. These monolithic systems encode regulatory-grade logic but resist AI integration by producing opaque output with no machine-readable…
We present JanusFlow, a powerful framework that unifies image understanding and generation in a single model. JanusFlow introduces a minimalist architecture that integrates autoregressive language models with rectified flow, a…
Training neural networks sequentially in time to approximate solution fields of time-dependent partial differential equations can be beneficial for preserving causality and other physics properties; however, the sequential-in-time training…
We present an adaptive regularization algorithm that can be effectively applied to the optimization problem in deep learning framework. Our regularization algorithm aims to take into account the fitness of data to the current state of model…
Normalising Flows are non-parametric statistical models characterised by their dual capabilities of density estimation and generation. This duality requires an inherently invertible architecture. However, the requirement of invertibility…
Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth maps is a very time consuming procedure. Therefore, recent…