Related papers: Exploring State Space and Reasoning by Elimination…

Machine learning fits model parameters to approximate input-output mappings, predicting unknown samples. However, these models often require extensive arithmetic computations during inference, increasing latency and power consumption. This…

We propose a novel framework for target speech extraction based on semantic information, called ConceptBeam. Target speech extraction means extracting the speech of a target speaker in a mixture. Typical approaches have been exploiting…

The paper introduces a novel framework based on category theory to enhance the explainability of artificial intelligence systems, particularly focusing on word embeddings. Key topics include the construction of categories $\mathcal{L}_T$…

Large Language Models (LLMs) have grown increasingly expensive to deploy, driving the need for effective model compression techniques. While block pruning offers a straightforward approach to reducing model size, existing methods often…

Target speech extraction (TSE) focuses on extracting the speech of a specific target speaker from a mixture of signals. Existing TSE models typically utilize static embeddings as conditions for extracting the target speaker's voice.…

All applications in fifth-generation (5G) networks rely on stable radio-frequency (RF) environments to support mission-critical services in mobility, automation, and connected intelligence. Their exposure to intentional interference or…

Recent advances in machine learning have significantly impacted the field of information extraction, with Language Models (LMs) playing a pivotal role in extracting structured information from unstructured text. Prior works typically…

We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs,…

This paper presents a new view of Explanation-Based Learning (EBL) of natural language parsing. Rather than employing EBL for specializing parsers by inferring new ones, this paper suggests employing EBL for learning how to reduce ambiguity…

While Large Language Models (LLMs) have found success in real-world applications, their underlying explanatory process is still poorly understood. This paper proposes IBE-Eval, a framework inspired by philosophical accounts on Inference to…

Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning requires (1) a feature space composed of human-understandable…

Despite the great success of word embedding, sentence embedding remains a not-well-solved problem. In this paper, we present a supervised learning framework to exploit sentence embedding for the medical question answering task. The learning…

Automatic term extraction (ATE) is a Natural Language Processing (NLP) task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms. As units of knowledge in a specific field…

A Restricted Boltzmann Machine (RBM) is an unsupervised machine-learning bipartite graphical model that jointly learns a probability distribution over data and extracts their relevant statistical features. As such, RBM were recently…

In many situations, we would like to hear desired sound events (SEs) while being able to ignore interference. Target sound extraction (TSE) tackles this problem by estimating the audio signal of the sounds of target SE classes in a mixture…

Modern large language models (LLMs) are powerful generators driven by statistical next-token prediction. While effective at producing fluent text, this design biases models toward high-probability continuations rather than exhaustive and…

Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by generating explicit chain-of-thought (CoT) rationales before extracting embeddings, enabling…

Large Language Models (LLMs) offer extensive knowledge across various domains, but they may inadvertently memorize sensitive, unauthorized, or malicious data, such as personal information in the medical and financial sectors. Machine…

Recent research has demonstrated that Universal Multimodal Embedding (UME) benefits significantly from Chain-of-Thought (CoT) reasoning. In this paradigm, a generative model produces explicit reasoning traces for a multimodal query, with…

Reasoning LLMs (RLMs) such as OpenAI o1, DeepSeek-R1, and Qwen3 deliver strong multi-step reasoning through chain-of-thought generation, but their large model sizes and lengthy decode-time outputs make them costly to deploy and unsuitable…