Related papers: Semantic Fusion with Fuzzy-Membership Features for…

Developing effective multimodal data fusion strategies has become increasingly essential for improving the predictive power of statistical machine learning methods across a wide range of applications, from autonomous driving to medical…

With the widespread use of machine learning to support decision-making, it is increasingly important to verify and understand the reasons why a particular output is produced. Although post-training feature importance approaches assist this…

The widespread use of large language models has resulted in a multitude of tokenizers and embedding spaces, making knowledge transfer in prompt discovery tasks difficult. In this work, we propose FUSE (Flexible Unification of Semantic…

Recent advancements in semantic communication have primarily focused on image transmission, where neural network-based joint source-channel coding modules play a central role. However, such systems often experience semantic communication…

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

Continuous dimensional speech emotion recognition captures affective variation along valence, arousal, and dominance, providing finer-grained representations than categorical approaches. Yet most multimodal methods rely solely on global…

The Fuzzy transform is ubiquitous in different research fields and applications, such as image and data compression, data mining, knowledge discovery, and the analysis of linguistic expressions. As a generalisation of the Fuzzy transform,…

Although fusing multiple sensor modalities can enhance object detection performance, existing fusion approaches often overlook subtle variations in environmental conditions and sensor inputs. As a result, they struggle to adaptively weight…

Humans often communicate by using imprecise language, suggesting that fuzzy concepts with unclear boundaries are prevalent in language use. In this paper, we test the extent to which models trained to capture the distributional statistics…

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

In the domain of Computing with words (CW), fuzzy linguistic approaches are known to be relevant in many decision-making problems. Indeed, they allow us to model the human reasoning in replacing words, assessments, preferences, choices,…

This paper proposes a multimodal emotion recognition system based on hybrid fusion that classifies the emotions depicted by speech utterances and corresponding images into discrete classes. A new interpretability technique has been…

Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with collaborative representations via representation alignment,…

The ambiguity at the boundaries of different semantic classes in point cloud semantic segmentation often leads to incorrect decisions in intelligent perception systems, such as autonomous driving. Hence, accurate delineation of the…

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without…

This paper provides an in-depth examination of the concept of semantic diffusion as a complementary instrument to large language models (LLMs) for design applications. Conventional LLMs and diffusion models fail to induce a convergent,…

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary LLMs. However, many languages written in non-Latin scripts…

Despite the recent success of large language models (LLMs) in time-series forecasting, most existing methods still adopt a Deep Synchronous Fusion strategy, where dense interactions between textual and temporal features are enforced at…

Although many efforts have been made on decreasing the model complexity for speaker verification, it is still challenging to deploy speaker verification systems with satisfactory result on low-resource terminals. We design a transformation…

We address text-assisted speech intelligibility prediction for hearing-impaired listeners in CPC3. Although the target is a sentence-level percentage, it is determined by reference-word recognition outcomes. We formulate prediction as…