搜索结果：infusion

Large language models (LLMs) have attracted significant attention due to their impressive general capabilities across diverse downstream tasks. However, without domain-specific optimization, they often underperform on specialized knowledge benchmarks and even produce hallucination. Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance. A critical challenge lies in balancing this infusion trade-off: injecting too little domain-specific data yields insufficient specialization, whereas excessive infusion triggers catastrophic forgetting of previously acquired knowledge. In this work, we focus on the phenomenon of memory collapse induced by over-infusion. Through systematic experiments, we make two key observations, i.e. 1) Critical collapse point: each model exhibits a threshold beyond which its knowledge retention capabilities sharply degrade. 2) Scale correlation: these collapse points scale consistently with the model's size. Building on these insights, we propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller cou

Multimodal generative models produce fluent outputs but remain unreliable when generation must respect structured, domain-specific, or safety-critical knowledge. Existing methods incorporate knowledge through mechanisms such as prompt augmentation, guidance, latent editing, or fine-tuning, yet they are typically categorized by technique rather than by the component of the generative process they modify. We argue that knowledge infusion in iterative generative models is fundamentally anintervention-layer problem. Since thegenerative process unfolds as a trajectory of internal states, knowledge can act on four structurally distinct components of this process: the input/output boundary, the transition function, the intermediate state, and the model parameters. This maps to four intervention layers: surface, trajectory, latent, and parametric infusion. We instantiate the framework in diffusion models, map representative methods to all four layers, and derive design principles for multi-layer composition. In a controlled safety-alignment experiment using a multimodal knowledge graph with two diffusion backbones, we implement three of the four layers cumulatively, surface (input-side and

The integration of the Internet of Medical Things (IoMT) into healthcare systems has transformed patient care by enabling real-time monitoring, enhanced diagnostics, and enhanced operational efficiency. However, this increased connectivity has also expanded the attack surface for cybercriminals, raising significant cybersecurity and privacy concerns. This study focuses on the cybersecurity vulnerabilities of IoMT infusion pumps, which are critical devices in modern healthcare. Through a targeted literature review of the past five years, we analyzed seven current studies from a pool of 132 papers to identify security vulnerabilities. Our findings indicate that infusion pumps face vulnerabilities such as device-level flaws, authentication and access control issues, network and communication weaknesses, data security and privacy risks, and operational or organizational challenges that can expose them to lateral attacks within healthcare networks. Our analysis synthesizes findings from seven recent studies to clarify how and why infusion pumps remain vulnerable in each of these areas. By categorizing the security gaps, we highlight critical risk patterns and their implications. This wo

Resin infusion (RI) and resin transfer moulding (RTM) are critical processes for the manufacturing of high-performance fibre-reinforced polymer composites, particularly for large-scale applications such as wind turbine blades. Controlling the resin flow dynamics in these processes is critical to ensure the uniform impregnation of the fibre reinforcements, thereby preventing residual porosities and dry spots that impact the consequent structural integrity of the final component. This paper presents a reinforcement learning (RL) based strategy, established using process simulations, for synchronising the different resin flow fronts in an infusion scenario involving two resin inlets and a single outlet. Using Proximal Policy Optimisation (PPO), our approach addresses the challenge of managing the fluid dynamics in a partially observable environment. The results demonstrate the effectiveness of the RL approach in achieving an accurate flow convergence, highlighting its potential towards improving process control and product quality in composites manufacturing.

Open-vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Existing OVSGG methods always adopt a two-stage pipeline: 1) \textit{Infusing knowledge} into large-scale models via pre-training on large datasets; 2) \textit{Transferring knowledge} from pre-trained models with fully annotated scene graphs during supervised fine-tuning. However, due to a lack of explicit interaction modeling, these methods struggle to distinguish between interacting and non-interacting instances of the same object category. This limitation induces critical issues in both stages of OVSGG: it generates noisy pseudo-supervision from mismatched objects during knowledge infusion, and causes ambiguous query matching during knowledge transfer. To this end, in this paper, we propose an inter\textbf{AC}tion-\textbf{C}entric end-to-end OVSGG framework (\textbf{ACC}) in an interaction-driven paradigm to minimize these mismatches. For \textit{interaction-centric knowledge infusion}, ACC employs a bidirectional interaction prompt for robust pseudo-supervision generation

We investigate the consequences of periodic, on-off glucose infusion on the glucose-insulin regulatory system on the basis of a system-level mathematical model with two explicit time delays. Studying the effects of such infusion protocols is mathematically challenging yet a promising direction for probing the system response to infusion. We pay special attention to the interplay of the infusion with intermediate-time-scale, ultradian oscillations that arise as a results of the physiological response of glucose uptake and back-release into the bloodstream. By using numerical solvers and numerical continuation software, we investigate the response of the model to different infusion patterns, and explore how these patterns affect the overall levels of glucose and insulin, and can lead to entrainment. By doing so, we provide a road-map of system responses that can potentially help identify new test strategies for detecting abnormal responses to glucose uptake.

3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with nove

Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first analyze overfitting, categorizing it into concept-agnostic overfitting, which undermines non-customized concept knowledge, and concept-specific overfitting, which is confined to customize on limited modalities, i.e, backgrounds, layouts, styles. To evaluate the overfitting degree, we further introduce two metrics, i.e, Latent Fisher divergence and Wasserstein metric to measure the distribution changes of non-customized and customized concept respectively. Drawing from the analysis, we propose Infusion, a T2I customization method that enables the learning of target concepts to avoid being constrained by limited training modalities, while preserving non-customized knowledge. Remarkably, Infusion achieves this feat with remarkable efficiency, requiring a mere 11KB of trained parameters. Extensive experiments also demonstrate that our approach outperforms state-of-the-art methods in both single and multi-concept customized generation.

Recent advancements in large-scale models have showcased remarkable generalization capabilities in various tasks. However, integrating multimodal processing into these models presents a significant challenge, as it often comes with a high computational burden. To address this challenge, we introduce a new parameter-efficient multimodal tuning strategy for large models in this paper, referred to as Multimodal Infusion Tuning (MiT). MiT leverages decoupled self-attention mechanisms within large language models to effectively integrate information from diverse modalities such as images and acoustics. In MiT, we also design a novel adaptive rescaling strategy at the attention head level, which optimizes the representation of infused multimodal features. Notably, all foundation models are kept frozen during the tuning process to reduce the computational burden and only 2.5\% parameters are tunable. We conduct experiments across a range of multimodal tasks, including image-related tasks like referring segmentation and non-image tasks such as sentiment analysis. Our results showcase that MiT achieves state-of-the-art performance in multimodal understanding while significantly reducing com

Endotoxin administration is commonly used to study the inflammatory response, and though traditionally given as a bolus injection, it can be administered as a continuous infusion over multiple hours. Several studies hypothesize that the latter better represents the prolonged and pronounced inflammation observed in conditions like sepsis. Yet, very few experimental studies have administered endotoxin using both strategies, leaving significant gaps in determining the underlying mechanisms responsible for their differing immune responses. We use mathematical modeling to analyze cytokine data from two studies administering a 2 ng/kg dose of endotoxin, one as a bolus and the other as a continuous infusion over four hours. Using our model, we simulate the dynamics of mean and subject-specific cytokine responses as well as the response to long-term endotoxin administration. Cytokine measurements reveal that the bolus injection leads to significantly higher peaks for IL-8, while IL-10 reaches significantly higher peaks during continuous administration. Moreover, the peak timing of all measured cytokines occurs later in the continuous infusion. We identify three model parameters that signif

Stance detection is the view towards a specific target by a given context (\textit{e.g.} tweets, commercial reviews). Target-related knowledge is often needed to assist stance detection models in understanding the target well and making detection correctly. However, prevailing works for knowledge-infused stance detection predominantly incorporate target knowledge from a singular source that lacks knowledge verification in limited domain knowledge. The low-resource training data further increases the challenge for the data-driven large models in this task. To address those challenges, we propose a collaborative knowledge infusion approach for low-resource stance detection tasks, employing a combination of aligned knowledge enhancement and efficient parameter learning techniques. Specifically, our stance detection approach leverages target background knowledge collaboratively from different knowledge sources with the help of knowledge alignment. Additionally, we also introduce the parameter-efficient collaborative adaptor with a staged optimization algorithm, which collaboratively addresses the challenges associated with low-resource stance detection tasks from both network structure

To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines.

Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge Distillation (KD) from Large Visual Language Models (LVLMs) and knowledge infusion to enhance the performance of toxicity detection in hateful memes. Our approach extracts sub-knowledge graphs from ConceptNet, a large-scale commonsense Knowledge Graph (KG) to be infused within a compact VLM framework. The relational context between toxic phrases in captions and memes, as well as visual concepts in memes enhance the model's reasoning capabilities. Experimental results from our study on two hate speech benchmark datasets demonstrate superior performance over the state-of-the-art baselines across AU-ROC, F1, and Recall with improvements of 1.1%, 7%, and 35%, respectively. Given the contextual complexity of the toxicity detection task, our approach showcases the significance of learning from both explicit (i.e. KG) as well as implicit (i.e. LVLMs) contextual cues incorporated through a hybrid neurosymbolic approach. This is crucial for real-

Accurately predicting anesthetic effects is essential for target-controlled infusion systems. The traditional (PK-PD) models for Bispectral index (BIS) prediction require manual selection of model parameters, which can be challenging in clinical settings. Recently proposed deep learning methods can only capture general trends and may not predict abrupt changes in BIS. To address these issues, we propose a transformer-based method for predicting the depth of anesthesia (DOA) using drug infusions of propofol and remifentanil. Our method employs long short-term memory (LSTM) and gate residual network (GRN) networks to improve the efficiency of feature fusion and applies an attention mechanism to discover the interactions between the drugs. We also use label distribution smoothing and reweighting losses to address data imbalance. Experimental results show that our proposed method outperforms traditional PK-PD models and previous deep learning methods, effectively predicting anesthetic depth under sudden and deep anesthesia conditions.

This paper explores the use of deep learning-based computer vision for real-time monitoring of the flow in intravenous (IV) infusions. IV infusions are among the most common therapies in hospitalized patients and, given that both over-infusion and under-infusion can cause severe damages, monitoring the flow rate of the fluid being administered to patients is very important for their safety. The proposed system uses a camera to film the IV drip infusion kit and a deep learning-based algorithm to classify acquired frames into two different states: frames with a drop that has just begun to take shape and frames with a well-formed drop. The alternation of these two states is used to count drops and derive a measurement of the flow rate of the drip. The usage of a camera as sensing element makes the proposed system safe in medical environments and easier to be integrated into current health facilities. Experimental results are reported in the paper that confirm the accuracy of the system and its capability to produce real-time estimates. The proposed method can be therefore effectively adopted to implement IV infusion monitoring and control systems.

In a data-centric era, concerns regarding privacy and ethical data handling grow as machine learning relies more on personal information. This empirical study investigates the privacy, generalization, and stability of deep learning models in the presence of additive noise in federated learning frameworks. Our main objective is to provide strategies to measure the generalization, stability, and privacy-preserving capabilities of these models and further improve them. To this end, five noise infusion mechanisms at varying noise levels within centralized and federated learning settings are explored. As model complexity is a key component of the generalization and stability of deep learning models during training and evaluation, a comparative analysis of three Convolutional Neural Network (CNN) architectures is provided. The paper introduces Signal-to-Noise Ratio (SNR) as a quantitative measure of the trade-off between privacy and training accuracy of noise-infused models, aiming to find the noise level that yields optimal privacy and accuracy. Moreover, the Price of Stability and Price of Anarchy are defined in the context of privacy-preserving deep learning, contributing to the syste

The integration of knowledge graphs with deep learning is thriving in improving the performance of various natural language processing (NLP) tasks. In this paper, we focus on knowledge-infused link prediction and question answering using language models, T5, and BLOOM across three domains: Aviation, Movie, and Web. In this context, we infuse knowledge in large and small language models and study their performance, and find the performance to be similar. For the link prediction task on the Aviation Knowledge Graph, we obtain a 0.2 hits@1 score using T5-small, T5-base, T5-large, and BLOOM. Using template-based scripts, we create a set of 1 million synthetic factoid QA pairs in the aviation domain from National Transportation Safety Board (NTSB) reports. On our curated QA pairs, the three models of T5 achieve a 0.7 hits@1 score. We validate out findings with the paired student t-test and Cohen's kappa scores. For link prediction on Aviation Knowledge Graph using T5-small and T5-large, we obtain a Cohen's kappa score of 0.76, showing substantial agreement between the models. Thus, we infer that small language models perform similar to large language models with the infusion of knowledg

Adopting contextually appropriate, audience-tailored linguistic styles is critical to the success of user-centric language generation systems (e.g., chatbots, computer-aided writing, dialog systems). While existing approaches demonstrate textual style transfer with large volumes of parallel or non-parallel data, we argue that grounding style on audience-independent external factors is innately limiting for two reasons. First, it is difficult to collect large volumes of audience-specific stylistic data. Second, some stylistic objectives (e.g., persuasiveness, memorability, empathy) are hard to define without audience feedback. In this paper, we propose the novel task of style infusion - infusing the stylistic preferences of audiences in pretrained language generation models. Since humans are better at pairwise comparisons than direct scoring - i.e., is Sample-A more persuasive/polite/empathic than Sample-B - we leverage limited pairwise human judgments to bootstrap a style analysis model and augment our seed set of judgments. We then infuse the learned textual style in a GPT-2 based text generator while balancing fluency and style adoption. With quantitative and qualitative assessme