Related papers: CBCMS: A Compliance Management System for Cross-Bo…

Concurrent computation and communication (C3) is a pervasive paradigm in ML and other domains, making its performance optimization crucial. In this paper, we carefully characterize C3 in ML on GPUs, which are most widely deployed for ML…

We introduce a novel algorithm for the task of coherently controlling a quantum mechanical system to implement any chosen unitary dynamics. It performs faster than existing state of the art methods by one to three orders of magnitude…

As language models (LMs) become more capable, it is increasingly important to align them with human preferences. However, the dominant paradigm for training Preference Models (PMs) for that purpose suffers from fundamental limitations, such…

Labeling training datasets has become a key barrier to building medical machine learning models. One strategy is to generate training labels programmatically, for example by applying natural language processing pipelines to text reports…

In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications…

One-sided communication is a useful paradigm for irregular parallel applications, but most one-sided programming environments, including MPI's one-sided interface and PGAS programming languages, lack application level libraries to support…

Text-Based Person Search (TBPS) aims to retrieve target person images from a large-scale gallery using natural language descriptions, posing fundamental challenges in cross-modal representation learning. Existing methods often struggle to…

Concept Bottleneck Models (CBMs) enhance the interpretability of neural networks by basing predictions on human-understandable concepts. However, current CBMs typically rely on concept sets extracted from large language models or extensive…

Line-level code completion requires a critical balance between high accuracy and low latency. Existing methods suffer from a trade-off: large language models (LLMs) provide high-quality suggestions but incur high latency, while small…

Database Forensics (DBF) domain is a branch of digital forensics, concerned with the identification, collection, reconstruction, analysis, and documentation of database crimes. Different researchers have introduced several identification…

There are now over 20 commercial vector database management systems (VDBMSs), all produced within the past five years. But embedding-based retrieval has been studied for over ten years, and similarity search a staggering half century and…

We propose an extension of the Cross Industry Standard Process for Data Mining (CRISPDM) which addresses specific challenges of machine learning and data mining for context and model reuse handling. This new general context-aware process…

Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these two capabilities independently and do not examine whether…

Despite great successes, model predictive control (MPC) relies on an accurate dynamical model and requires high onboard computational power, impeding its wider adoption in engineering systems, especially for nonlinear real-time systems with…

Managing the transactions in real time distributed computing system is not easy, as it has heterogeneously networked computers to solve a single problem. If a transaction runs across some different sites, it may commit at some sites and may…

Controlling stochastic systems with unknown dynamics and under complex specifications is specially challenging in safety-critical settings, where performance guarantees are essential. We propose a data-driven policy synthesis framework that…

Machine learning is critical for innovation and efficiency in financial markets, offering predictive models and data-driven decision-making. However, challenges such as missing data, lack of transparency, untimely updates, insecurity, and…

The key to effective point cloud compression is to obtain a robust context model consistent with complex 3D data structures. Recently, the advancement of large language models (LLMs) has highlighted their capabilities not only as powerful…

Process Management Systems (PMSs) are currently more and more used as a supporting tool for cooperative processes in pervasive and highly dynamic situations, such as emergency situations, pervasive healthcare or domotics/home automation.…

With the recent success of large language models (LLMs), the idea of AI-augmented Business Process Management systems is becoming more feasible. One of their essential characteristics is the ability to be conversationally actionable,…