Related papers: SG-OIF: A Stability-Guided Online Influence Framew…

In clinical machine learning, the coexistence of multiple models with comparable performance (a manifestation of the Rashomon Effect) poses fundamental challenges for trustworthy deployment and evaluation. Small, imbalanced, and noisy…

Currently, it is a hot research topic to realize accurate, efficient, and real-time identification of massive spectral data with the help of deep learning and IoT technology. Deep neural networks played a key role in spectral analysis.…

A novel method for performing error control coding in Symmetric $\alpha-$Stable noise environments without any prior knowledge about the value of $\alpha$ is introduced. We use an online learning framework which employs multiple…

Imitation learning presents an effective approach to alleviate the resource-intensive and time-consuming nature of policy learning from scratch in the solution space. Even though the resulting policy can mimic expert demonstrations…

Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or classifier pretraining. That is why guidance was harnessed from self-supervised learning backbones, like…

Diffusion models have been widely studied for removing unsafe content learned during pre-training. Existing methods require expensive supervised data, either unsafe-text paired with safe-image groundtruth or negative/positive image pairs,…

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Neural surface reconstruction relies heavily on accurate camera poses as input. Despite utilizing advanced pose estimators like COLMAP or ARKit, camera poses can still be noisy. Existing pose-NeRF joint optimization methods handle poses…

Machine Learning (ML) is poised to play a pivotal role in the development and operation of next-generation fusion devices. Fusion data shows non-stationary behavior with distribution drifts, resulted by both experimental evolution and…

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…

Deploying deep learning agents for autonomous navigation in unstructured environments faces critical challenges regarding safety, data scarcity, and limited computational resources. Traditional solvers often suffer from high latency, while…

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated.…

Ensuring safety in autonomous systems requires controllers that aim to satisfy state-wise constraints without relying on online interaction.While existing Safe Offline RL methods typically enforce soft expected-cost constraints, they…

The National Synchrotron Light Source II (NSLS-II) uses highly stable electron beam to produce high-quality X-ray beams with high brightness and low-emittance synchrotron radiation. The traditional algorithm to stabilize the beam applies…

Ensuring safety in the sense of constraint satisfaction for learning-based control is a critical challenge, especially in the model-free case. While safety filters address this challenge in the model-based setting by modifying unsafe…

We study the problem of learning the objective functions or constraints of a multiobjective decision making model, based on a set of sequentially arrived decisions. In particular, these decisions might not be exact and possibly carry…

Reconstructing accurate implicit surface representations from point clouds remains a challenging task, particularly when data is captured using low-quality scanning devices. These point clouds often contain substantial noise, leading to…

This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT). While the training…

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

Quantifying the influence of infinitesimal changes in training data on model performance is crucial for understanding and improving machine learning models. In this work, we reformulate this problem as a weighted empirical risk minimization…