Synthesizing electronic health records (EHR) is essential for addressing data scarcity, bias, and fairness in healthcare models. EHR data are inherently multimodal and sequential, encompassing structured codes, clinical notes, medical images, and irregular time intervals. Traditional generative models like GANs and VAEs struggle to capture these complexities, while diffusion-based models offer improvements but remain limited to task-specific applications. To address these challenges, two diffusion-based models, MedDiffusion and EHRPD, have been developed. MedDiffusion enhances health risk prediction by generating synthetic patient data and capturing visit-level relationships, while EHRPD generates sequential, multimodal EHR data, incorporating temporal interval estimation to improve diversity and fidelity. Future work aims to overcome limitations in multimodal data generation by developing a generalized model capable of handling diverse modalities simultaneously, expanding the applicability of EHR data generation across healthcare tasks.
论文检索
输入标题、作者或关键词，从 9,256 篇学术成果中精准定位
Open-World Multimodal Understanding and Generation with Efficiently Finetuned Foundation Models
PDF ↗With the astonishing ability of different pretrained foundation models (e.g., large language models (LLMs), vision-language models, diffusion models), today’s AI research and development tendency has been revolutionized. In this talk, I will answer two questions: Q1: How can we efficiently train or fine-tune foundation models? Q2: How can we build strong open-world multimodal understanding and generation models with these pretrained foundation models?
The propagation of aggressive behavior in online social networks presents a growing threat to digital well-being and social harmony. While existing research focuses on modeling aggression diffusion or detecting aggressive content, forecasting individual user aggression remains an open challenge. This work fills this gap by introducing Temporal Social Graph Attention Network (TSGAN), a social-aware sequence-to-sequence architecture designed to forecast aggressive behavior in dynamic social networks. The core of TSGAN is an adaptive socio-temporal attention module that dynamically models social influence and temporal dynamics. To capture global social influence, TSGAN employs a graph contrastive learning approach to generate global network context embeddings. TSGAN utilizes an aggression intensity metric derived from a proposed hybrid aggression content detection model (92.87% F1), combining a fine-tuned transformer with a large language model to quantify user aggression over time. TSGAN uniquely addresses user inactivity, models dynamic follower relationship impacts, and accounts for temporal behavioral decay while scaling to large networks. Experiments on real-world datasets (X for aggression forecasting and Flickr for popularity prediction) demonstrate TSGAN’s versatility and effectiveness. TSGAN outperforms baselines in forecasting across hourly, daily, and weekly temporal intervals, showing up to 24.8% improvement in daily aggression predictions.
As global populations age rapidly, incorporating age-specific considerations into urban planning has become essential to addressing the urgent demand for age-friendly built environments and ensuring sustainable urban development. However, current practices often overlook these considerations, resulting in inadequate and unevenly distributed elderly services in cities. There is a pressing need for equitable and optimized urban renewal strategies to support effective age-friendly planning. To address this challenge, we propose a novel framework, Fairness-driven Age-friendly community Planning via Conditional Diffusion generation (FAP-CD). FAP-CD leverages a conditioned graph denoising diffusion probabilistic model to learn the joint probability distribution of aging facilities and their spatial relationships at a fine-grained regional level. Our framework generates optimized facility distributions by iteratively refining noisy graphs, conditioned on the needs of the elderly during the diffusion process. Key innovations include a demand-fairness pre-training module that integrates community demand features and facility characteristics using an attention mechanism and min-max optimization, ensuring equitable service distribution across regions. Additionally, a discrete graph structure captures walkable accessibility within regional road networks, guiding model sampling. To enhance information integration, we design a graph denoising network with an attribute augmentation module and a hybrid graph message aggregation module, combining local and global node and edge information. Empirical results across multiple metrics demonstrate the effectiveness of FAP-CD in balancing age-friendly needs with regional equity, achieving an average improvement of 41% over competitive baseline models.
PrecipDiff: Leveraging Image Diffusion Models to Enhance Satellite-Based Precipitation Observations
PDF ↗A recent report from the World Meteorological Organization (WMO) highlights that water-related disasters have caused the highest human losses among natural disasters over the past 50 years, with over 91\% of deaths occurring in low-income countries. This disparity is largely due to the lack of adequate ground monitoring stations, such as weather surveillance radars (WSR), which are expensive to install. For example, while the US and Europe combined possess over 600 WSRs, Africa, despite having almost one and half times their landmass, has fewer than 40. To address this issue, satellite-based observations offer a global, near-real-time monitoring solution. However, they face several challenges like accuracy, bias, and low spatial resolution. This study leverages the power of diffusion models and residual learning to address these limitations in a unified framework. We introduce the first diffusion model for correcting the inconsistency between different precipitation products. Our method demonstrates the effectiveness in downscaling satellite precipitation estimates from 10 km to 1 km resolution. Extensive experiments conducted in the Seattle region demonstrate significant improvements in accuracy, bias reduction, and spatial detail. Importantly, our approach achieves these results using only precipitation data, showcasing the potential of a purely computer vision-based approach for enhancing satellite precipitation products and paving the way for further advancements in this domain.
Training advanced AI models requires large investments in computational resources, or compute. Yet, as hardware innovation reduces the price of compute and algorithmic advances make its use more efficient, the cost of training an AI model to a given performance falls over time - a concept we describe as increasing compute efficiency. We find that while an access effect increases the number of actors who can train models to a given performance over time, a performance effect simultaneously increases the performance available to each actor. This potentially enables large compute investors to pioneer new capabilities, maintaining a performance advantage even as capabilities diffuse. Since large compute investors tend to develop new capabilities first, it will be particularly important that they share information about their AI models, evaluate them for emerging risks, and, more generally, make responsible development and release decisions. Further, as compute efficiency increases, governments will need to prepare for a world where dangerous AI capabilities are widely available - for instance, by developing defenses against harmful AI models or by actively intervening in the diffusion of particularly dangerous capabilities.
Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints
PDF ↗Recent work has proposed automated red-teaming methods for testing the vulnerabilities of a given target large language model (LLM). These methods use red-teaming LLMs to uncover inputs that induce harmful behavior in a target LLM. In this paper, we study red-teaming strategies that enable a targeted security assessment. We propose an optimization framework for red-teaming with proximity constraints, where the discovered prompts must be similar to reference prompts from a given dataset. This dataset serves as a template for the discovered prompts, anchoring the search for test-cases to specific topics, writing styles, or types of harmful behavior. We show that established auto-regressive model architectures do not perform well in this setting. We therefore introduce a black-box red-teaming method inspired by text-diffusion models: Diffusion for Auditing and Red-Teaming (DART). DART modifies the reference prompt by perturbing it in the embedding space, directly controlling the amount of change introduced. We systematically evaluate our method by comparing its effectiveness with established methods based on model fine-tuning and zero- and few-shot prompting. Our results show that DART is significantly more effective at discovering harmful inputs in close proximity to the reference prompt.
The emergence of Vision-Language Models (VLMs) is significant advancement in integrating computer vision with Large Language Models (LLMs) to enhance multi-modal machine learning capabilities. However, this progress has made VLMs vulnerable to advanced adversarial attacks, raising concerns about reliability. Objective of this paper is to assess resilience of VLMs against jailbreak attacks that can compromise model safety compliance and result in harmful outputs. To evaluate VLM's ability to maintain robustness against adversarial input perturbations, we propose novel metric called \textbf{Retention Score}. Retention Score is multi-modal evaluation metric that includes Retention-I and Retention-T scores for quantifying jailbreak risks in visual and textual components of VLMs. Our process involves generating synthetic image-text pairs using conditional diffusion model. These pairs are then predicted for toxicity score by VLM alongside toxicity judgment classifier. By calculating margin in toxicity scores, we can quantify robustness of VLM in attack-agnostic manner. Our work has four main contributions. First, we prove that Retention Score can serve as certified robustness metric. Second, we demonstrate that most VLMs with visual components are less robust against jailbreak attacks than corresponding plain VLMs. Additionally, we evaluate black-box VLM APIs and find that security settings in Google Gemini significantly affect score and robustness. Moreover, robustness of GPT4V is similar to medium settings of Gemini. Finally, our approach offers time-efficient alternative to existing adversarial attack methods and provides consistent model robustness rankings when evaluated on VLMs including MiniGPT-4, InstructBLIP, and LLaVA.
Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the Model-as-a-Service (MaaS) scenario, where users query diffusion models through APIs or directly download them from the internet. To mitigate the threat of backdoor attacks under MaaS, black-box input-level backdoor detection has drawn recent interest, where defenders aim to build a firewall that filters out backdoor samples in the inference stage, with access only to input queries and the generated results from diffusion models. Despite some preliminary explorations on the traditional classification tasks, these methods cannot be directly applied to the generative tasks due to two major challenges: (1) more diverse failures and (2) a multi-modality attack surface. In this paper, we propose a black-box input-level backdoor detection framework on diffusion models, called UFID. Our defense is motivated by an insightful causal analysis: Backdoor attacks serve as the confounder, introducing a spurious path from input to target images, which remains consistent even when we perturb the input samples with Gaussian noise. We further validate the intuition with theoretical analysis. Extensive experiments across different datasets on both conditional and unconditional diffusion models show that our method achieves superb performance on detection effectiveness and run-time efficiency.
In social online platforms, identifying influential seed users to maximize influence spread is a crucial as it can greatly diminish the cost and efforts required for information dissemination. While effective, traditional methods for Multiplex Influence Maximization (MIM) have reached their performance limits, prompting the emergence of learning-based approaches. These novel methods aim for better generalization and scalability for more sizable graphs but face significant challenges, such as (1) inability to handle unknown diffusion patterns and (2) reliance on high-quality training samples. To address these issues, we propose the Reinforced Expert Maximization framework (REM). REM leverages a Propagation Mixture of Experts technique to encode dynamic propagation of large multiplex networks effectively in order to generate enhanced influence propagation. Noticeably, REM treats a generative model as a policy to autonomously generate different seed sets and learn how to improve them from a Reinforcement Learning perspective. Extensive experiments on several real-world datasets demonstrate that REM surpasses state-of-the-art methods in terms of influence spread, scalability, and inference time in influence maximization tasks.
Multi-objective Bayesian optimization (MOBO) has shown promising performance on various expensive multi-objective optimization problems (EMOPs). However, effectively modeling complex distributions of the Pareto optimal solutions is difficult with limited function evaluations. Existing Pareto set learning algorithms may exhibit considerable instability in such expensive scenarios, leading to significant deviations between the obtained solution set and the Pareto set (PS). In this paper, we propose a novel Composite Diffusion Model based Pareto Set Learning algorithm (CDM-PSL) for expensive MOBO. CDM-PSL includes both unconditional and conditional diffusion model for generating high-quality samples efficiently. Besides, we introduce a weighting method based on information entropy to balance different objectives. This method is integrated with a guiding strategy to appropriately balancing different objectives during the optimization process. Experimental results on both synthetic and real-world problems demonstrates that CDM-PSL attains superior performance compared with state-of-the-art MOBO algorithms.
Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leaked gradients. However, can gradient perturbation protection mechanisms truly defend against all gradient leakage attacks? In this paper, we present the first attempt to break the shield of gradient perturbation protection in Federated Learning for the extraction of private information. We focus on common noise distributions, specifically Gaussian and Laplace, and apply our approach to DNN and CNN models. We introduce Mjölnir, a perturbation-resilient gradient leakage attack that is capable of removing perturbations from gradients without requiring additional access to the original model structure or external data. Specifically, we leverage the inherent diffusion properties of gradient perturbation protection to develop a novel diffusion-based gradient denoising model for Mjölnir. By constructing a surrogate client model that captures the structure of perturbed gradients, we obtain crucial gradient data for training the diffusion model. We further utilize the insight that monitoring disturbance levels during the reverse diffusion process can enhance gradient denoising capabilities, allowing Mjölnir to generate gradients that closely approximate the original, unperturbed versions through adaptive sampling steps. Extensive experiments demonstrate that Mjölnir effectively recovers the protected gradients and exposes the Federated Learning process to the threat of gradient leakage, achieving superior performance in gradient denoising and private data recovery.
In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In our preliminary experiments, we find that the artifacts in fake images always change with the development of the generative model, while natural images exhibit stable statistical properties. In this paper, we employ natural traces shared only by real images as an additional target for a classifier. Specifically, we introduce a self-supervised feature mapping process for natural trace extraction and develop a transfer learning based on soft contrastive loss to bring them closer to real images and further away from fake ones. This motivates the detector to make decisions based on the proximity of images to the natural traces. To conduct a comprehensive experiment, we built a high-quality and diverse dataset that includes generative models comprising GANs and diffusion models, to evaluate the effectiveness in generalizing unknown forgery techniques and robustness in surviving different transformations. Experimental results show that our proposed method gives 96.2% mAP significantly outperforms the baselines. Extensive experiments conducted on the widely recognized platform Midjourney reveal that our proposed method achieves an accuracy exceeding 78.4%, underscoring its practicality for real-world application deployment.
Digital watermarking has shown its effectiveness in protecting multimedia content. However, existing watermarking is predominantly tailored for specific media types, rendering them less effective for the protection of content displayed on computer screens, which is often multi-modal and dynamic. Visual Screen Content (VSC), is particularly susceptible to theft and leakage through screenshots, a vulnerability that current watermarking methods fail to adequately address. To address these challenges, we propose ScreenMark, a robust and practical watermarking method designed specifically for arbitrary VSC protection. ScreenMark utilizes a three-stage progressive watermarking framework. Initially, inspired by diffusion principles, we initialize the mutual transformation between regular watermark information and irregular watermark patterns. Subsequently, these patterns are integrated with screen content using a pre-multiplication alpha blending technique, supported by a pre-trained screen decoder for accurate watermark retrieval. The progressively complex distorter enhances the robustness of the watermark in real-world screenshot scenarios. Finally, the model undergoes fine-tuning guided by a joint-level distorter to ensure optimal performance. To validate the effectiveness of ScreenMark, we compiled a dataset comprising 100,000 screenshots from various devices and resolutions. Extensive experiments on different datasets confirm the superior robustness, imperceptibility, and practical applicability of the method.
In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. These models often struggle to disentangle the target language context from sociocultural biases, resulting in biased image generation. To overcome this challenge, we propose Fair Mapping, a flexible, model-agnostic, and lightweight approach that modifies a pre-trained text-to-image diffusion model by controlling the prompt to achieve fair image generation. One key advantage of our approach is its high efficiency. It only requires updating an additional linear network with few parameters at a low computational cost. By developing a linear network that maps conditioning embeddings into a debiased space, we enable the generation of relatively balanced demographic results based on the specified text condition. With comprehensive experiments on face image generation, we show that our method significantly improves image generation fairness with almost the same image quality compared to conventional diffusion models when prompted with descriptions related to humans. By effectively addressing the issue of implicit language bias, our method produces more fair and diverse image outputs.
BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning
PDF ↗Generating novel active molecules for a given protein is an extremely challenging task for generative models that requires an understanding of the complex physical interactions between the molecule and its environment. This paper presents a novel generative model, BindGPT, which uses a conceptually simple but powerful approach to create 3D molecules within the protein's binding site. Our model produces molecular graphs and conformations jointly, eliminating the need for an extra graph reconstruction step. We pre-train BindGPT on a large-scale dataset and fine-tune it with reinforcement learning using scores from external simulation software. We demonstrate how a single pre-trained language model can serve at the same time as a 3D molecular generative model, a conformer generator conditioned on the molecular graph, and a pocket-conditioned 3D molecule generator. Notably, the model does not make any representational equivariance assumptions about the domain of generation. We show how such a simple conceptual approach combined with pre-training and scaling can perform on par or better than the current best-specialized diffusion models, language models, and graph neural networks while being two orders of magnitude cheaper to sample.
Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) current approaches primarily focus on adapting timbre from unseen speakers and are unable to transfer style and timbre to different unseen speakers independently; 2) these approaches often suffer from slower inference speeds due to the autoregressive modeling methods or the need for numerous sampling steps; 3) the quality and similarity of the converted samples are still not fully satisfactory. To address these challenges, we propose a Style controllable zero-shot VC approach named StableVC, which aims to transfer timbre and style from source speech to different unseen target speakers. Specifically, we decompose speech into linguistic content, timbre, and style, and then employ a conditional flow matching module to reconstruct the high-quality mel-spectrogram based on these decomposed features. To effectively capture timbre and style in a zero-shot manner, we introduce a novel dual attention mechanism with an adaptive gate, rather than using conventional feature concatenation. With this non-autoregressive design, StableVC can efficiently capture the intricate timbre and style from different unseen speakers and generate high-quality speech significantly faster than real-time. Experiments demonstrate that our proposed StableVC outperforms state-of-the-art baseline systems in zero-shot VC and achieves flexible control over timbre and style from different unseen speakers. Moreover, StableVC offers approximately 25x and 1.65x faster sampling compared to autoregressive and diffusion-based baselines.
The emergence of novel generative modeling paradigms, particularly audio language models, has significantly advanced the field of song generation. Although state-of-the-art models are capable of synthesizing both vocals and accompaniment tracks up to several minutes long concurrently, research about partial adjustments or editing of existing songs is still underexplored, which allows for more flexible and effective production. In this paper, we present SongEditor, the first song editing paradigm that introduces the editing capabilities into language-modeling song generation approaches, facilitating both segment-wise and track-wise modifications. SongEditor offers the flexibility to adjust lyrics, vocals, and accompaniments, as well as synthesizing songs from scratch. The core components of SongEditor include a music tokenizer, an autoregressive language model, and a diffusion generator, enabling generating an entire section, masked lyrics, or even separated vocals and background music. Extensive experiments demonstrate that the proposed SongEditor achieves exceptional performance in end-to-end song editing, as evidenced by both objective and subjective metrics.
TEncDM: Understanding the Properties of the Diffusion Model in the Space of Language Model Encodings
PDF ↗This paper presents the Text Encoding Diffusion Model (TEncDM), a novel approach to diffusion modeling that operates in the space of pre-trained language model encodings. In contrast to traditionally used embeddings, encodings integrate contextual information. In our approach, we also employ a transformer-based decoder, specifically designed to incorporate context in the token prediction process. We conduct a comprehensive examination of the influence of the encoder, decoder, noise scheduler, and self-conditioning on zero-shot generation. Furthermore, we compare TEncDM with previous approaches on three conditional text generation tasks: QQP, XSum, and Wiki-Auto. The results show that TEncDM exhibits superior performance compared to existing non-autoregressive diffusion models.
In recent years, diffusion modeling has shown great potential for image generation and editing. Beyond single-model approaches, various drawing workflows now exist to handle diverse drawing tasks. However, few solutions effectively identify user intentions through dialogue and progressively complete drawings. We introduce DialogDraw, which facilitates image generation and editing through continuous dialogue interaction. DialogDraw enables users to create and refine drawings using natural language and integrates with numerous open-source drawing workflows and models. The system accurately recognizes intentions and extracts user inputs via parameterization, adapts to various drawing function parameters, and provides an intuitive interaction mode. It effectively executes user instructions, supports dozens of image generation and editing methods, and offers robust scalability. Moreover, we employ SFT and RLHF to iterate the Intention Recognition and Parameter Extraction Model (IRPEM). To evaluate DialogDraw's functionality, we propose DrawnConvos, a dataset rich in drawing functions and command dialogue data collected from the open-source community. Our evaluation demonstrates that DialogDraw excels in command compliance, identifying and adapting to user drawing intentions, thereby proving the effectiveness of our method.