Related papers: Critically Damped Third-Order Langevin Dynamics
Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…
In this work, we aimed to replicate and extend the results presented in the DiffFluid paper[1]. The DiffFluid model showed that diffusion models combined with Transformers are capable of predicting fluid dynamics. It uses a denoising…
Tool-integrated (TI) reinforcement learning (RL) enables large language models (LLMs) to perform multi-step reasoning by interacting with external tools such as search engines and retrievers. Group Relative Policy Optimization (GRPO),…
The recent development of connected and automated vehicle (CAV) technologies has spurred investigations to optimize dense urban traffic to maximize vehicle speed and throughput. This paper explores advisory autonomy, in which real-time…
Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical…
Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed…
Collaborative edge computing uses edge nodes in different locations to execute tasks, necessitating dynamic task offloading decisions to maintain low latency and high reliability, especially under unpredictable node failures. Although deep…
We present a data-driven point of view for rare events, which represent conformational transitions in biochemical reactions modeled by over-damped Langevin dynamics on manifolds in high dimensions. We first reinterpret the transition state…
We investigate the theoretical properties of general diffusion (interpolation) paths and their Langevin Monte Carlo implementation, referred to as diffusion annealed Langevin Monte Carlo (DALMC), under weak conditions on the data…
Langevin algorithms are popular Markov chain Monte Carlo methods that are often used to solve high-dimensional large-scale sampling problems in machine learning. The most classical Langevin Monte Carlo algorithm is based on the overdamped…
Out-of-distribution (OOD) detection remains challenging for deep learning models, particularly when test-time OOD samples differ significantly from training outliers. We propose OODD, a novel test-time OOD detection method that dynamically…
The Lorenz 1963 dynamical system is known to reduce in the steady state to a one-dimensional motion of a classical particle subjected to viscous damping in a past history-dependent potential field. If the potential field is substituted by a…
Extended Lagrangian molecular dynamics (XLMD) is a general method for performing molecular dynamics simulations using quantum and classical many-body potentials. Recently several new XLMD schemes have been proposed and tested on several…
Clustering temporal and dynamically changing multivariate time series from real-world fields, called temporal clustering for short, has been a major challenge due to inherent complexities. Although several deep temporal clustering…
Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Correlation of Loss Differences (CLD), a simple and…
Doubly robust methods hold considerable promise for off-policy evaluation in Markov decision processes (MDPs) under sequential ignorability: They have been shown to converge as $1/\sqrt{T}$ with the horizon $T$, to be statistically…
Dynamic mode decomposition (DMD) is a popular technique for modal decomposition, flow analysis, and reduced-order modeling. In situations where a system is time varying, one would like to update the system's description online as time…
Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Yet, its standard formulations rely on instantaneous data-consistent estimates, which induce…
Healthcare providers are increasingly using machine learning to predict patient outcomes to make meaningful interventions. However, despite innovations in this area, deep learning models often struggle to match performance of shallow linear…
Test-time adaptation (TTA) aims to adapt a pretrained model to distribution shifts using only unlabeled test data. While promising, existing methods like Tent suffer from instability and can catastrophically forget the source knowledge,…