Related papers: DMARF AND GIPSY High Level Architecture and Requir…

Reinforcement learning (RL) has become the pivotal post-training technique for large language model (LLM). Effectively scaling reinforcement learning is now the key to unlocking advanced reasoning capabilities and ensuring safe,…

The GIPSY system provides a framework for a distributed multi-tier demand-driven evaluation of heterogeneous programs, in which certain tiers can generate demands, while others can respond to demands to work on them. They are connected…

Effective communication is a critical factor in successful software engineering collaboration. However, communication gaps remain a persistent challenge, often leading to misunderstandings, inefficiencies, and defects. This research…

Quality assurance is of great importance for deep learning (DL) systems, especially when they are applied in safety-critical applications. While quality issues of native DL applications have been extensively analyzed, the issues of…

The past few years has witnessed specialized large language model (LLM) inference systems, such as vLLM, SGLang, Mooncake, and DeepFlow, alongside rapid LLM adoption via services like ChatGPT. Driving these system design efforts is the…

As part of a research on a novel in-process multiprogramming-language interoperability system, this study investigates the interoperability and usage of multiple programming languages within a large dataset of GitHub projects and Stack…

This work formulates the machine learning mechanism as a bi-level optimization problem. The inner level optimization loop entails minimizing a properly chosen loss function evaluated on the training data. This is nothing but the…

Improving the code generation capabilities of large language models (LLMs) typically relies on supervised fine-tuning or preference optimization, both of which require costly external resources such as powerful teacher models or reliable…

Traditional Digital Signal Processing ( DSP ) compilers work at low level ( C-level / assembly level ) and hence lose much of the optimization opportunities present at high-level ( domain-level ). The emerging multi-level compiler…

Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and…

In the swiftly expanding domain of Natural Language Processing (NLP), the potential of GPT-based models for the financial sector is increasingly evident. However, the integration of these models with financial datasets presents challenges,…

Significant efforts has been made to expand the use of Large Language Models (LLMs) beyond basic language tasks. While the generalizability and versatility of LLMs have enabled widespread adoption, evolving demands in application…

The internal structure and operation mechanism of large-scale language models are analyzed theoretically, especially how Transformer and its derivative architectures can restrict computing efficiency while capturing long-term dependencies.…

The development and operation of smart cities relyheavily on large-scale Internet-of-Things (IoT) networks and sensor infrastructures that continuously monitor various aspects of urban environments. These networks generate vast amounts of…

The Deep Noise Suppression (DNS) challenge is designed to foster innovation in the area of noise suppression to achieve superior perceptual speech quality. We recently organized a DNS challenge special session at INTERSPEECH 2020. We open…

Deep reinforcement learning (deep RL) research has grown significantly in recent years. A number of software offerings now exist that provide stable, comprehensive implementations for benchmarking. At the same time, recent deep RL research…

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

[Background] Large Language Model (LLM)-based multi-agent systems (MAS) are transforming software development by enabling autonomous collaboration. Classical software processes such asWaterfall, V-Model, and Agile offer structured…

Learning mappings between functional spaces, also known as function-on-function regression, is a fundamental problem in functional data analysis with broad applications, including spatiotemporal forecasting, curve prediction, and climate…

Large language models (LLMs) and transformer-based architectures are increasingly utilized for source code analysis. As software systems grow in complexity, integrating LLMs into code analysis workflows becomes essential for enhancing…