Related papers: Fractal Language Modelling by Universal Sequence M…

Design of large software systems requires rigorous application of software engineering methods covering all phases of the software process. Debugging during the early design phases is extremely important, because late bug-fixes are…

Embedding learning, a.k.a. representation learning, has been shown to be able to model large-scale semantic knowledge graphs. A key concept is a mapping of the knowledge graph to a tensor representation whose entries are predicted by models…

Decoding language from neural signals holds considerable theoretical and practical importance. Previous research has indicated the feasibility of decoding text or speech from invasive neural signals. However, when using non-invasive neural…

Large Language Models (LLMs) can help robots reason about abstract task specifications. This requires augmenting classical representations of the environment used by robots, such as point-clouds and meshes, with natural language-based…

Multi-scale tile maps are essential for geographic information services, serving as fundamental outcomes of surveying and cartographic workflows. While existing image generation networks can produce map-like outputs from remote sensing…

Scene graph (SG) representations can neatly and efficiently describe scene semantics, which has driven sustained intensive research in SG generation. In the real world, multiple modalities often coexist, with different types, such as…

In this work we address three questions: can we successfully describe (observed) deviations from the standard model in the SMEFT language? Can we learn something about the underlying, beyond the standard model, physics using the SMEFT…

Computed tomography (CT) is extensively used for accurate visualization and segmentation of organs and lesions. While deep learning models such as convolutional neural networks (CNNs) and vision transformers (ViTs) have significantly…

Unified models (UMs) hold promise for their ability to understand and generate content across heterogeneous modalities. Compared to merely generating visual content, the use of UMs for interleaved cross-modal reasoning is more promising and…

Large Language Models (LLMs) are increasingly deployed on edge devices with Neural Processing Units (NPUs), yet the decode phase remains memory-intensive, limiting performance. Processing-in-Memory (PIM) offers a promising solution, but…

We present a bijection between some quadrangular dissections of an hexagon and unrooted binary trees, with interesting consequences for enumeration, mesh compression and graph sampling. Our bijection yields an efficient uniform random…

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…

The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ…

Multimodal Small-to-Medium sized Language Models (MSLMs) have demonstrated strong capabilities in integrating visual and textual information but still face significant limitations in visual comprehension and mathematical reasoning,…

Enterprise software companies maintain thousands of user interface screens across products and versions, creating critical challenges for design consistency, pattern discovery, and compliance check. Existing approaches rely on visual…

A critical step of genome sequence analysis is the mapping of sequenced DNA fragments (i.e., reads) collected from an individual to a known linear reference genome sequence (i.e., sequence-to-sequence mapping). Recent works replace the…

This paper introduces a novel unified representation of diffusion models for image generation and segmentation. Specifically, we use a colormap to represent entity-level masks, addressing the challenge of varying entity numbers while…

The uniform infinite planar quadrangulation is an infinite random graph embedded in the plane, which is the local limit of uniformly distributed finite quadrangulations with a fixed number of faces. We study asymptotic properties of this…

This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms. The graphical inputs consist of node and edge representations constructed from…

Understanding the locus of semantic representation in large language models (LLMs) is crucial for interpretability and architectural innovation. The dominant paradigm posits that trainable input embeddings serve as foundational "meaning…