Related papers: Adjusted Objects: An Efficient and Principled Appr…
Workflow and serverless frameworks have empowered new approaches to distributed application design by abstracting compute resources. However, their typically limited or one-size-fits-all support for advanced data flow patterns leaves…
Hardware heterogeneity is here to stay for high-performance computing. Large-scale systems are currently equipped with multiple GPU accelerators per compute node and are expected to incorporate more specialized hardware in the future. This…
Generic Object Tracking (GOT) is the problem of tracking target objects, specified by bounding boxes in the first frame of a video. While the task has received much attention in the last decades, researchers have almost exclusively focused…
Multi-objective optimisation problems involve finding solutions with varying trade-offs between multiple and often conflicting objectives. Ising machines are physical devices that aim to find the absolute or approximate ground states of an…
Present day machine learning is computationally intensive and processes large amounts of data. It is implemented in a distributed fashion in order to address these scalability issues. The work is parallelized across a number of computing…
In object-oriented or object-relational databases such as multimedia databases or most XML databases, access patterns are not static, i.e., applications do not always access the same objects in the same order repeatedly. However, this has…
While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between…
Flexible and performant Persistency Service is a necessary component of any HEP Software Framework. The building of a modular, non-intrusive and performant persistency component have been shown to be very difficult task. In the past, it was…
A syntax-directed formal system for the development of totally correct programs with respect to an unfair shared-state parallel while-language is proposed. The system can be understood as a compositional reformulation of the Owicki/Gries…
Object tracking is a long standing problem in vision. While great efforts have been spent to improve tracking performance, a simple yet reliable prior knowledge is left unexploited: the target object in tracking must be an object other than…
Software development has been changing rapidly. This development process can be influenced through changing developer friendly approaches. We can save time consumption and accelerate the development process if we can automatically guide…
For aligning large language models (LLMs), prior work has leveraged reinforcement learning via human feedback (RLHF) or variations of direct preference optimization (DPO). While DPO offers a simpler framework based on maximum likelihood…
Considering a group of users, each specifying individual preferences over categorical attributes, the problem of determining a set of objects that are objectively preferable by all users is challenging on two levels. First, we need to…
To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…
Object stores are widely used software stacks that achieve excellent scale-out with a well-defined interface and robust performance. However, their traditional get/put interface is unable to exploit data locality at its fullest, and limits…
We describe a system that simplifies the process of debugging programs produced by computer-aided parallelization tools. The system uses relative debugging techniques to compare serial and parallel executions in order to show where the…
In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an image and a set of corrections made by the user as input,…
Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate…
This paper introduces several techniques that improve the scalability of the deductive verification of data-level programs working on arrays and matrices. First of all, we introduce a technique to rewrite expressions with (nested)…
Debugging is hard. Interactive debuggers are mostly the same. They show you a stack, a way to sample the state of the stack, and, if the debugger is live, a way to step through execution. The standard interactive debugger for a…