Related papers: Process-oriented Iterative Multiple Alignment for …
Artificial intelligence (AI) is increasingly being utilized to optimize magnetic resonance imaging (MRI) protocols. Given that image details are critical for diagnostic accuracy, optimizing MRI acquisition protocols is essential for…
Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…
Human motion analysis is used in many different fields and applications. Currently, existing systems either focus on one single limb or one single class of movements. Many proposed systems are designed to be used in an indoor controlled…
We examine the problem of learning sequential tasks from a single visual demonstration. A key challenge arises when demonstrations are temporally misaligned due to variations in timing, differences in embodiment, or inconsistencies in…
Despite the fact that offline methods for Large Language Models (LLMs) alignment do not require a direct reward model, they remain susceptible to overoptimization. This issue arises when the trained model deviates excessively from the…
Multiple sequence alignment is a basic procedure in molecular biology, and it is often treated as being essentially a solved computational problem. However, this is not so, and here I review the evidence for this claim, and outline the…
One primary goal of precision medicine is to estimate the individualized treatment rules (ITRs) that optimize patients' health outcomes based on individual characteristics. Health studies with multiple treatments are commonly seen in…
Machine learning components commonly appear in larger decision-making pipelines; however, the model training process typically focuses only on a loss that measures accuracy between predicted values and ground truth values. Decision-focused…
We address the problem of visually guided rearrangement planning with many movable objects, i.e., finding a sequence of actions to move a set of objects from an initial arrangement to a desired one, while relying on visual inputs coming…
Many physical systems are described by partial differential equations (PDEs), and solving these equations and estimating their coefficients or boundary conditions (BCs) from observational data play a crucial role in understanding the…
Routine and repetitive infrastructure inspections present safety, efficiency, and consistency challenges as they are performed manually, often in challenging or hazardous environments. They can also introduce subjectivity and errors into…
Multi-image alignment, bringing a group of images into common register, is an ubiquitous problem and the first step of many applications in a wide variety of domains. As a result, a great amount of effort is being invested in developing…
Human trajectory forecasting requires capturing the multimodal nature of pedestrian behavior. However, existing approaches suffer from prior misalignment. Their learned or fixed priors often fail to capture the full distribution of…
Pivot tables are ubiquitous in data lakes of modern data ecosystems, making accurate schema matching over pivot tables a key prerequisite for data integration. In this paper, we focus on matching for pivot table schema, which is a novel…
End-to-end motion planning is promising for simplifying complex autonomous driving pipelines. However, challenges such as scene understanding and effective prediction for decision-making continue to present substantial obstacles to its…
Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23…
Sequence alignment is common nowadays as it is used in many fields to determine how closely two sequences are related and at times to see how little they differ. In computational biology / Bioinformatics, there are many algorithms developed…
Trail running is an endurance sport in which athletes face severe physical challenges. Due to the growing number of participants, the organization of limited staff, equipment, and medical support in these races now plays a key role.…
Current visual text generation models struggle with the trade-off between text accuracy and overall image coherence. We find that achieving high text accuracy can reduce aesthetic quality and instruction-following capability. Although…
High performance large scale graph analytics are essential to timely analyze relationships in big data sets. Conventional processor architectures suffer from inefficient resource usage and bad scaling on those workloads. To enable efficient…