Related papers: Boosting Large Language Models for Mental Manipula…

Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of…

Sarcasm fundamentally alters meaning through tone and context, yet detecting it in speech remains a challenge due to data scarcity. In addition, existing detection systems often rely on multimodal data, limiting their applicability in…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose…

Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation…

Large Language Models (LLMs), enhanced through agent tuning, have demonstrated remarkable capabilities in Chain-of-Thought (CoT) and tool utilization, significantly surpassing the performance of standalone models. However, the multimodal…

Pornographic content occurring in human-machine interaction dialogues can cause severe side effects for users in open-domain dialogue systems. However, research on detecting pornographic language within human-machine interaction dialogues…

Recent research has explored distilling knowledge from large language models (LLMs) to optimize retriever models, especially within the retrieval-augmented generation (RAG) framework. However, most existing training methods rely on…

Depression is a major global public health challenge and its early identification is crucial. Social media data provides a new perspective for depression detection, but existing methods face limitations such as insufficient accuracy,…

Several training strategies and temporal models have been recently proposed for isolated word lip-reading in a series of independent works. However, the potential of combining the best strategies and investigating the impact of each of them…

Large Vision-Language Models (LVLMs) have exhibited impressive capabilities across various visual tasks, yet they remain hindered by the persistent challenge of hallucinations. To address this critical issue, we propose Mixture of Decoding…

This study investigates the use of Large Language Models (LLMs) for improved depression detection from users social media data. Through the use of fine-tuned GPT 3.5 Turbo 1106 and LLaMA2-7B models and a sizable dataset from earlier…

Data-free Knowledge Distillation (DFKD) has attracted attention recently thanks to its appealing capability of transferring knowledge from a teacher network to a student network without using training data. The main idea is to use a…

Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators from overwhelming and tedious tasks, allowing them to focus…

This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias and errors in data…

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models (s-MLLM) by distilling knowledge from large-scale MLLM (l-MLLM). Our approach tackles two fundamental challenges…

Fake news often involves multimedia information such as text and image to mislead readers, proliferating and expanding its influence. Most existing fake news detection methods apply the co-attention mechanism to fuse multimodal features…

In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this challenge, we propose a novel approach called Meta-learned…

The presence of offensive language on social media is very common motivating platforms to invest in strategies to make communities safer. This includes developing robust machine learning systems capable of recognizing offensive content…

This paper presents a method for text simplification based on two neural architectures: a neural machine translation (NMT) model and a fine-tuned large language model (LLaMA). Given the scarcity of existing resources for Estonian, a new…