Related papers: Fractal Language Modelling by Universal Sequence M…
Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by…
Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowledge. To this end, we present two complementary experimental…
Panoptic maps enable robots to reason about both geometry and semantics. However, open-vocabulary models repeatedly produce closely related labels that split panoptic entities and degrade volumetric consistency. The proposed UPPM advances…
Despite the well-developed cut-edge representation learning for language, most language representation models usually focus on specific levels of linguistic units. This work introduces universal language representation learning, i.e.,…
Biological classification with interpretability remains a challenging task. For this, we introduce a novel encoding framework, Multi-Scale Reversible Chaos Game Representation (MS-RCGR), that transforms biological sequences into…
Continuous sign language recognition (CSLR) requires precise spatio-temporal modeling to accurately recognize sequences of gestures in videos. Existing frameworks often rely on CNN-based spatial backbones combined with temporal convolution…
The Universal Similarity Metric (USM) has been demonstrated to give practically useful measures of "similarity" between sequence data. Here we have used the USM as an alternative distance metric in a K-Nearest Neighbours (K-NN) learner to…
Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for…
Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the…
We introduce a transductive model for parsing into Universal Decompositional Semantics (UDS) representations, which jointly learns to map natural language utterances into UDS graph structures and annotate the graph with decompositional…
Recent work on mini-batch consistency (MBC) for set functions has brought attention to the need for sequentially processing and aggregating chunks of a partitioned set while guaranteeing the same output for all partitions. However, existing…
Speech foundation models (SFMs) are increasingly hailed as powerful computational models of human speech perception. However, since their representations are inherently black-box, it remains unclear what drives their alignment with brain…
Graph-based design languages in UML (Unified Modeling Language) are presented as a method to encode and automate the complete design process and the final optimization of the product or complex system. A design language consists of a…
The advancement of artificial intelligence (AI) for organ segmentation and tumor detection is propelled by the growing availability of computed tomography (CT) datasets with detailed, per-voxel annotations. However, these AI models often…
Molecular representation learning is fundamental for many drug related applications. Most existing molecular pre-training models are limited in using single molecular modality, either SMILES or graph representation. To effectively leverage…
The integration of multi-omic data is pivotal for understanding complex diseases, but its high dimensionality and noise present significant challenges. Graph Neural Networks (GNNs) offer a robust framework for analyzing large-scale…
In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing. We first introduce a cascade model for UDS parsing that decomposes the complex parsing task into semantically appropriate subtasks.…
Program classification can be regarded as a high-level abstraction of code, laying a foundation for various tasks related to source code comprehension, and has a very wide range of applications in the field of software engineering, such as…
Prior work has shown that large language models (LLMs) often converge to accurate input embedding for numbers, based on sinusoidal representations. In this work, we quantify that these representations are in fact strikingly systematic, to…
Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…