Related papers: IntSeqBERT: Learning Arithmetic Structure in OEIS …

Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE)…

Reading comprehension, a fundamental cognitive ability essential for knowledge acquisition, is a complex skill, with a notable number of learners lacking proficiency in this domain. This study introduces innovative tasks for Brain-Computer…

Multiview Self-Supervised Learning (MSSL) is based on learning invariances with respect to a set of input transformations. However, invariance partially or totally removes transformation-related information from the representations, which…

Cloud formations often obscure optical satellite-based monitoring of the Earth's surface, thus limiting Earth observation (EO) activities such as land cover mapping, ocean color analysis, and cropland monitoring. The integration of machine…

The HeartBert model is introduced with three primary objectives: reducing the need for labeled data, minimizing computational resources, and simultaneously improving performance in machine learning systems that analyze Electrocardiogram…

Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when…

As integrated circuit (IC) dimensions shrink below the lithographic wavelength, optical lithography faces growing challenges from diffraction and process variability. Model-based optical proximity correction (OPC) and inverse lithography…

Sequence set is a widely-used type of data source in a large variety of fields. A typical example is protein structure prediction, which takes an multiple sequence alignment (MSA) as input and aims to infer structural information from it.…

White matter tract segmentation is crucial for studying brain structural connectivity and neurosurgical planning. However, segmentation remains challenging due to issues like class imbalance between major and minor tracts, structural…

Irregular Multivariate Time Series (IMTS) are common in practice, yet their irregular sampling complicates effective modeling. Existing approaches typically either (i) design specialized architectures that limit the reuse of proven…

Security issues are threatened in various types of networks, especially in the Internet of Things (IoT) environment that requires early detection. IoT is the network of real-time devices like home automation systems and can be controlled by…

Invertible neural networks (INNs) have been used to design generative models, implement memory-saving gradient computation, and solve inverse problems. In this work, we show that commonly-used INN architectures suffer from exploding…

Molecular representation is a critical element in our understanding of the physical world and the foundation for modern molecular machine learning. Previous molecular machine learning models have employed strings, fingerprints, global…

Multi-frequency Electrical Impedance Tomography (mfEIT) is an emerging biomedical imaging modality to reveal frequency-dependent conductivity distributions in biomedical applications. Conventional model-based image reconstruction methods…

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited.…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Regularization methods using prior knowledge are essential in solving ill-posed inverse problems such as Electrical Impedance Tomography (EIT). However, designing effective regularization and integrating prior information into EIT remains…

Accurate segmentation of tissues and instruments in surgical scenes is annotation-intensive due to irregular shapes, thin structures, specularities, and frequent occlusions. While SAM models support point, box, and mask prompts, points are…

Implicit neural representations (INRs) such as NeRF and SIREN encode a signal in neural network parameters and show excellent results for signal reconstruction. Using INRs for downstream tasks, such as classification, is however not…

Learning neural program embeddings is key to utilizing deep neural networks in program languages research --- precise and efficient program representations enable the application of deep models to a wide range of program analysis tasks.…