Related papers: Towards Refactoring DMARF and GIPSY OSS

Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learning systems (e.g., GNNs). Existing solutions typically rely…

This paper presents DFR (Decompose, Fuse and Reconstruct), a novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segmentation (FSS). While existing approaches primarily rely on…

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming (GP) pipeline that…

The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipelines are typically implemented using hard-coded "prompt…

Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple…

This study presents an exploratory evaluation of Music Generation Systems (MGS) within contemporary music production workflows by examining eight open-source systems. The evaluation framework combines technical insights with practical…

This paper describes several improvements to a new method for signal decomposition that we recently formulated under the name of Differentiable Dictionary Search (DDS). The fundamental idea of DDS is to exploit a class of powerful deep…

It is no longer a debate that quality is an essential requirement in any software product, especially in a highly competitive market and a context of mission critical product. To obtain better product quality, software metrics are the only…

Diffusion-based text-to-speech (TTS) systems have made remarkable progress in zero-shot speech synthesis, yet optimizing all components for perceptual metrics remains challenging. Prior work with DMOSpeech demonstrated direct metric…

Pure Lucid programs are concurrent with very fine granularity. Sequential Threads (STs) are functions introduced to enlarge the grain size; they are passed from server to workers by Communication Procedures (CPs) in the General Intensional…

It is commonly agreed that highly parallel software on Exascale computers will suffer from many more runtime failures due to the decreasing trend in the mean time to failures (MTTF). Therefore, it is not surprising that a lot of research is…

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…

This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound…

We propose DFModel, a modeling framework for mapping dataflow computation graphs onto large-scale systems. Mapping a workload to a system requires optimizing dataflow mappings at various levels, including the inter-chip (between chips)…

Currently, artificial intelligence is profoundly transforming the audio domain; however, numerous advanced algorithms and tools remain fragmented, lacking a unified and efficient framework to unlock their full potential. Existing audio…

Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data…

As artificial intelligence methods are increasingly applied to complex task scenarios, high dimensional multi-label learning has emerged as a prominent research focus. At present, the curse of dimensionality remains one of the major…

Intelligent transportation systems (ITS) localization is of significant importance as it provides fundamental position and orientation for autonomous operations like intelligent vehicles. Integrating diverse and complementary sensors such…

Multimodal conversational agents are highly desirable because they offer natural and human-like interaction. However, there is a lack of comprehensive end-to-end solutions to support collaborative development and benchmarking. While…

Software engineers are faced with the challenge of creating control algorithms for increasingly complex dynamic systems, such as the management of communication network topologies. To support rapid prototyping for these increasingly complex…