分享

Diffusion Models are probabilistic models that create realistic samples by simulating the diffusion process, gradually adding and removing noise from data. These models have gained popularity in domains such as image processing, speech synthesis, and natural language processing due to their ability to produce high-quality samples. As Diffusion Models are being adopted in various domains, existing literature reviews that often focus on specific areas like computer vision or medical imaging may not serve a broader audience across multiple fields. Therefore, this review presents a comprehensive overview of Diffusion Models, covering their theoretical foundations and algorithmic innovations. We highlight their applications in diverse areas such as media quality, authenticity, synthesis, image transformation, healthcare, and more. By consolidating current knowledge and identifying emerging trends, this review aims to facilitate a deeper understanding and broader adoption of Diffusion Models and provide guidelines for future researchers and practitioners across diverse disciplines.

The potential of deep learning in clinical speech processing is immense, yet the hurdles of limited and imbalanced clinical data samples loom large. This article addresses these challenges by showcasing the utilization of automatic speech recognition and self-supervised learning representations, pre-trained on extensive datasets of normal speech. This innovative approach aims to estimate voice quality of patients with impaired vocal systems. Experiments involve checks on PVQD dataset, covering various causes of vocal system damage in English, and a Japanese dataset focusing on patients with Parkinson's disease before and after undergoing subthalamic nucleus deep brain stimulation (STN-DBS) surgery. The results on PVQD reveal a notable correlation (>0.8 on PCC) and an extraordinary accuracy (<0.5 on MSE) in predicting Grade, Breathy, and Asthenic indicators. Meanwhile, progress has been achieved in predicting the voice quality of patients in the context of STN-DBS.

Consider a scenario where a harmfulness detection metric is employed by a system to filter unsafe responses generated by a Large Language Model. When analyzing individual harmful and unethical prompt-response pairs, the metric correctly classifies each pair as highly unsafe, assigning the highest score. However, when these same prompts and responses are concatenated, the metric's decision flips, assigning the lowest possible score, thereby misclassifying the content as safe and allowing it to bypass the filter. In this study, we discovered that several harmfulness LLM-based metrics, including GPT-based, exhibit this decision-flipping phenomenon. Additionally, we found that even an advanced metric like GPT-4o is highly sensitive to input order. Specifically, it tends to classify responses as safe if the safe content appears first, regardless of any harmful content that follows, and vice versa. This work introduces automatic concatenation-based tests to assess the fundamental properties a valid metric should satisfy. We applied these tests in a model safety scenario to assess the reliability of harmfulness detection metrics, uncovering a number of inconsistencies.

Recently, applying neural networks to address combinatorial optimization problems (COPs) has attracted considerable research attention. The prevailing methods always train deep models independently on specific problems, lacking a unified framework for concurrently tackling various COPs. To this end, we propose a unified neural combinatorial optimization (UNCO) framework to solve different types of COPs by a single model. Specifically, we use natural language to formulate text-attributed instances for different COPs and encode them in the same embedding space by the large language model (LLM). The obtained embeddings are further advanced by an encoder-decoder model without any problem-specific modules, thereby facilitating a unified process of solution construction. We further adopt the conflict gradients erasing reinforcement learning (CGERL) algorithm to train the UNCO model, delivering better performance across different COPs than vanilla multi-objective learning. Experiments show that the UNCO model can solve multiple COPs after a single-session training, and achieves satisfactory performance that is comparable to several traditional or learning-based baselines. Instead of pursuing the best performance for each COP, we explore the synergy between tasks and few-shot generalization based on LLM to inspire future work.

LLMs are increasingly used to design reward functions based on human preferences in Reinforcement Learning (RL). We focus on LLM-designed rewards for Restless Multi-Armed Bandits, a framework for allocating limited resources among agents. In applications such as public health, this approach empowers grassroots health workers to tailor automated allocation decisions to community needs. In the presence of multiple agents, altering the reward function based on human preferences can impact subpopulations very differently, leading to complex tradeoffs and a multi-objective resource allocation problem. We are the first to present a principled method termed Social Choice Language Model for dealing with these tradeoffs for LLM-designed rewards for multiagent planners in general and restless bandits in particular. The novel part of our model is a transparent and configurable selection component, called an adjudicator, external to the LLM that controls complex tradeoffs via a user-selected social welfare function. Our experiments demonstrate that our model reliably selects more effective, aligned, and balanced reward functions compared to purely LLM-based approaches.

In today's world, making decisions as a group is common, whether choosing a restaurant or deciding on a holiday destination. Group decision-making (GDM) systems play a crucial role by facilitating consensus among participants with diverse preferences. Discussions are one of the main tools people use to make decisions. When people discuss alternatives, they use natural language to express their opinions. Traditional GDM systems generally require participants to provide explicit opinion values to the system. However, in real-life scenarios, participants often express their opinions through some text (e.g., in comments, social media, messengers, etc.). This paper introduces a sentiment and emotion-aware multi-criteria fuzzy GDM system designed to enhance consensus-reaching effectiveness in group settings. This system incorporates natural language processing to analyze sentiments and emotions expressed in textual data, enabling an understanding of participant opinions besides the explicit numerical preference inputs. Once all the experts have provided their preferences for the alternatives, the individual preferences are aggregated into a single collective preference matrix. This matrix represents the collective expert opinion regarding the other options. Then, sentiments, emotions, and preference scores are inputted into a fuzzy inference system to get the overall score. The proposed system was used for a small decision-making process - choosing the hotel for a vacation by a group of friends. Our findings demonstrate that integrating sentiment and emotion analysis into GDM systems allows everyone's feelings and opinions to be considered during discussions and significantly improves consensus among participants.

This paper presents MaVEn, an innovative Multi-granularity Visual Encoding framework designed to enhance the capabilities of Multimodal Large Language Models (MLLMs) in multi-image reasoning. Current MLLMs primarily focus on single-image visual understanding, limiting their ability to interpret and integrate information across multiple images. MaVEn addresses this limitation by combining discrete visual symbol sequences, which abstract coarse-grained semantic concepts, with traditional continuous representation sequences that model fine-grained features. This dual approach bridges the semantic gap between visual and textual data, thereby improving the model's ability to process and interpret information from multiple images effectively. Additionally, we design a dynamic reduction mechanism by for long-sequence continuous features to enhance multi-image processing efficiency. Experimental results demonstrate that MaVEn significantly enhances MLLMs' understanding in complex multi-image scenarios, while also improving performance in single-image contexts.

The vision-language modeling capability of multi-modal large language models has attracted wide attention from the community. However, in medical domain, radiology report generation using vision-language models still faces significant challenges due to the imbalanced data distribution caused by numerous negated descriptions in radiology reports and issues such as rough alignment between radiology reports and radiography. In this paper, we propose a truthful radiology report generation framework, namely TRRG, based on stage-wise training for cross-modal disease clue injection into large language models. In pre-training stage, During the pre-training phase, contrastive learning is employed to enhance the ability of visual encoder to perceive fine-grained disease details. In fine-tuning stage, the clue injection module we proposed significantly enhances the disease-oriented perception capability of the large language model by effectively incorporating the robust zero-shot disease perception. Finally, through the cross-modal clue interaction module, our model effectively achieves the multi-granular interaction of visual embeddings and an arbitrary number of disease clue embeddings. This significantly enhances the report generation capability and clinical effectiveness of multi-modal large language models in the field of radiology reportgeneration. Experimental results demonstrate that our proposed pre-training and fine-tuning framework achieves state-of-the-art performance in radiology report generation on datasets such as IU-Xray and MIMIC-CXR. Further analysis indicates that our proposed method can effectively enhance the model to perceive diseases and improve its clinical effectiveness.

In recent years Plug-and-Play (PnP) methods have achieved state-of-the-art performance in inverse imaging problems by replacing proximal operators with denoisers. Based on the proximal gradient method, some theoretical results of PnP have appeared, where appropriate step size is crucial for convergence analysis. However, in practical applications, applying PnP methods with theoretically guaranteed step sizes is difficult, and these algorithms are limited to Gaussian noise. In this paper,from a perspective of split convex feasibility problems (SCFP), an adaptive PnP algorithm with Projected Landweber Operator (PnP-PLO) is proposed to address these issues. Numerical experiments on image deblurring, super-resolution, and compressed sensing MRI experiments illustrate that PnP-PLO with theoretical guarantees outperforms state-of-the-art methods such as RED and RED-PRO.

Video saliency prediction aims to identify the regions in a video that attract human attention and gaze, driven by bottom-up features from the video and top-down processes like memory and cognition. Among these top-down influences, language plays a crucial role in guiding attention by shaping how visual information is interpreted. Existing methods primarily focus on modeling perceptual information while neglecting the reasoning process facilitated by language, where ranking cues are crucial outcomes of this process and practical guidance for saliency prediction. In this paper, we propose CaRDiff (Caption, Rank, and generate with Diffusion), a framework that imitates the process by integrating a multimodal large language model (MLLM), a grounding module, and a diffusion model, to enhance video saliency prediction. Specifically, we introduce a novel prompting method VSOR-CoT (Video Salient Object Ranking Chain of Thought), which utilizes an MLLM with a grounding module to caption video content and infer salient objects along with their rankings and positions. This process derives ranking maps that can be sufficiently leveraged by the diffusion model to decode the saliency maps for the given video accurately. Extensive experiments show the effectiveness of VSOR-CoT in improving the performance of video saliency prediction. The proposed CaRDiff performs better than state-of-the-art models on the MVS dataset and demonstrates cross-dataset capabilities on the DHF1k dataset through zero-shot evaluation.

Emotion recognition through artificial intelligence and smart sensing of physical and physiological signals (Affective Computing) is achieving very interesting results in terms of accuracy, inference times, and user-independent models. In this sense, there are applications related to the safety and well-being of people (sexual aggressions, gender-based violence, children and elderly abuse, mental health, etc.) that require even more improvements. Emotion detection should be done with fast, discrete, and non-luxurious systems working in real-time and real life (wearable devices, wireless communications, battery-powered). Furthermore, emotional reactions to violence are not equal in all people. Then, large general models cannot be applied to a multiuser system for people protection, and customized and simple AI models would be welcomed by health and social workers and law enforcement agents. These customized models will be applicable to clusters of subjects sharing similarities in their emotional reactions to external stimuli. This customization requires several steps: creating clusters of subjects with similar behaviors, creating AI models for every cluster, continually updating these models with new data, and enrolling new subjects in clusters when required. A methodology for clustering data compiled (physical and physiological data, together with emotional labels) is presented in this work, as well as the method for including new subjects once the AI model is generated. Experimental results demonstrate an improvement of 4% in accuracy and 3% in f1-score w.r.t. the general model, along with a 14% reduction in variability.

Large language models (LLMs) have revolutionized natural language processing (NLP) with impressive performance across various text-based tasks. However, the extension of text-dominant LLMs to with speech generation tasks remains under-explored. In this work, we introduce a text-to-speech (TTS) system powered by a fine-tuned Llama model, named TTS-Llama, that achieves state-of-the-art speech synthesis performance. Building on TTS-Llama, we further propose MoLE-Llama, a text-and-speech multimodal LLM developed through purely late-fusion parameter-efficient fine-tuning (PEFT) and a mixture-of-expert architecture. Extensive empirical results demonstrate MoLE-Llama's competitive performance on both text-only question-answering (QA) and TTS tasks, mitigating catastrophic forgetting issue in either modality. Finally, we further explore MoLE-Llama in text-in-speech-out QA tasks, demonstrating its great potential as a multimodal dialog system capable of speech generation.