COVID-19 appeared abruptly in early 2020, requiring a rapid response amid a context of great uncertainty. Good quality data and knowledge was initially lacking, and many early models had to be developed with causal assumptions and estimations built in to supplement limited data, often with no reliable approach for identifying, validating and documenting these causal assumptions. Our team embarked on a knowledge engineering process to develop a causal knowledge base consisting of several causal BNs for diverse aspects of COVID-19. The unique challenges of the setting lead to experiments with the elicitation approach, and what emerged was a knowledge engineering method we call Causal Knowledge Engineering (CKE). The CKE provides a structured approach for building a causal knowledge base that can support the development of a variety of application-specific models. Here we describe the CKE method, and use our COVID-19 work as a case study to provide a detailed discussion and analysis of the method.
The conformational landscape of proteins is crucial to understanding their functionality in complex biological processes. Traditional physics-based computational methods, such as molecular dynamics (MD) simulations, suffer from rare event sampling and long equilibration time problems, hindering their applications in general protein systems. Recently, deep generative modeling techniques, especially diffusion models, have been employed to generate novel protein conformations. However, existing score-based diffusion methods cannot properly incorporate important physical prior knowledge to guide the generation process, causing large deviations in the sampled protein conformations from the equilibrium distribution. In this paper, to overcome these limitations, we propose a force-guided SE(3) diffusion model, ConfDiff, for protein conformation generation. By incorporating a force-guided network with a mixture of data-based score models, ConfDiff can can generate protein conformations with rich diversity while preserving high fidelity. Experiments on a variety of protein conformation prediction tasks, including 12 fast-folding proteins and the Bovine Pancreatic Trypsin Inhibitor (BPTI), demonstrate that our method surpasses the state-of-the-art method.
Text-to-image diffusion models suffer from the risk of generating outdated, copyrighted, incorrect, and biased content. While previous methods have mitigated the issues on a small scale, it is essential to handle them simultaneously in larger-scale real-world scenarios. We propose a two-stage method, Editing Massive Concepts In Diffusion Models (EMCID). The first stage performs memory optimization for each individual concept with dual self-distillation from text alignment loss and diffusion noise prediction loss. The second stage conducts massive concept editing with multi-layer, closed form model editing. We further propose a comprehensive benchmark, named ImageNet Concept Editing Benchmark (ICEB), for evaluating massive concept editing for T2I models with two subtasks, free-form prompts, massive concept categories, and extensive evaluation metrics. Extensive experiments conducted on our proposed benchmark and previous benchmarks demonstrate the superior scalability of EMCID for editing up to 1,000 concepts, providing a practical approach for fast adjustment and re-deployment of T2I diffusion models in real-world applications.
Recently, infrared small target detection (ISTD) has made significant progress, thanks to the development of basic models. Specifically, the structures combining convolutional networks with transformers can successfully extract both local and global features. However, the disadvantage of the transformer is also inherited, i.e., the quadratic computational complexity to the length of the sequence. Inspired by the recent basic model with linear complexity for long-distance modeling, called Mamba, we explore the potential of this state space model for ISTD task in terms of effectiveness and efficiency in the paper. However, directly applying Mamba achieves poor performance since local features, which are critical to detecting small targets, cannot be fully exploited. Instead, we tailor a Mamba-in-Mamba (MiM-ISTD) structure for efficient ISTD. Specifically, we treat the local patches as "visual sentences" and use the Outer Mamba to explore the global information. We then decompose each visual sentence into sub-patches as "visual words" and use the Inner Mamba to further explore the local information among words in the visual sentence with negligible computational costs. By aggregating the word and sentence features, the MiM-ISTD can effectively explore both global and local information. Experiments on NUAA-SIRST and IRSTD-1k show the superior accuracy and efficiency of our method. Specifically, MiM-ISTD is $10 \times$ faster than the SOTA method and reduces GPU memory usage by 73.4$\%$ when testing on $2048 \times 2048$ image, overcoming the computation and memory constraints on high-resolution infrared images. Source code is available at https://github.com/txchen-USTC/MiM-ISTD.
In this paper, we introduce PixArt-\Sigma, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-\Sigma represents a significant advancement over its predecessor, PixArt-\alpha, offering images of markedly higher fidelity and improved alignment with text prompts. A key feature of PixArt-\Sigma is its training efficiency. Leveraging the foundational pre-training of PixArt-\alpha, it evolves from the `weaker' baseline to a `stronger' model via incorporating higher quality data, a process we term "weak-to-strong training". The advancements in PixArt-\Sigma are twofold: (1) High-Quality Training Data: PixArt-\Sigma incorporates superior-quality image data, paired with more precise and detailed image captions. (2) Efficient Token Compression: we propose a novel attention module within the DiT framework that compresses both keys and values, significantly improving efficiency and facilitating ultra-high-resolution image generation. Thanks to these improvements, PixArt-\Sigma achieves superior image quality and user prompt adherence capabilities with significantly smaller model size (0.6B parameters) than existing text-to-image diffusion models, such as SDXL (2.6B parameters) and SD Cascade (5.1B parameters). Moreover, PixArt-\Sigma's capability to generate 4K images supports the creation of high-resolution posters and wallpapers, efficiently bolstering the production of high-quality visual content in industries such as film and gaming.
Artificial intelligence (AI) has gained significant attention in healthcare consultation due to its potential to improve clinical workflow and enhance medical communication. However, owing to the complex nature of medical information, large language models (LLM) trained with general world knowledge might not possess the capability to tackle medical-related tasks at an expert level. Here, we introduce EyeGPT, a specialized LLM designed specifically for ophthalmology, using three optimization strategies including role-playing, finetuning, and retrieval-augmented generation. In particular, we proposed a comprehensive evaluation framework that encompasses a diverse dataset, covering various subspecialties of ophthalmology, different users, and diverse inquiry intents. Moreover, we considered multiple evaluation metrics, including accuracy, understandability, trustworthiness, empathy, and the proportion of hallucinations. By assessing the performance of different EyeGPT variants, we identify the most effective one, which exhibits comparable levels of understandability, trustworthiness, and empathy to human ophthalmologists (all Ps>0.05). Overall, ur study provides valuable insights for future research, facilitating comprehensive comparisons and evaluations of different strategies for developing specialized LLMs in ophthalmology. The potential benefits include enhancing the patient experience in eye care and optimizing ophthalmologists' services.
Multi-view learning aims to combine multiple features to achieve more comprehensive descriptions of data. Most previous works assume that multiple views are strictly aligned. However, real-world multi-view data may contain low-quality conflictive instances, which show conflictive information in different views. Previous methods for this problem mainly focus on eliminating the conflictive data instances by removing them or replacing conflictive views. Nevertheless, real-world applications usually require making decisions for conflictive instances rather than only eliminating them. To solve this, we point out a new Reliable Conflictive Multi-view Learning (RCML) problem, which requires the model to provide decision results and attached reliabilities for conflictive multi-view data. We develop an Evidential Conflictive Multi-view Learning (ECML) method for this problem. ECML first learns view-specific evidence, which could be termed as the amount of support to each category collected from data. Then, we can construct view-specific opinions consisting of decision results and reliability. In the multi-view fusion stage, we propose a conflictive opinion aggregation strategy and theoretically prove this strategy can exactly model the relation of multi-view common and view-specific reliabilities. Experiments performed on 6 datasets verify the effectiveness of ECML.
Large language models(LLM) such as ChatGPT have substantially simplified the generation of marketing copy, yet producing content satisfying domain specific requirements, such as effectively engaging customers, remains a significant challenge. In this work, we introduce the Genetic Copy Optimization Framework (GCOF) designed to enhance both efficiency and engagememnt of marketing copy creation. We conduct explicit feature engineering within the prompts of LLM. Additionally, we modify the crossover operator in Genetic Algorithm (GA), integrating it into the GCOF to enable automatic feature engineering. This integration facilitates a self-iterative refinement of the marketing copy. Compared to human curated copy, Online results indicate that copy produced by our framework achieves an average increase in click-through rate (CTR) of over $50\%$.
The typical phases of Bayesian network (BN) structured development include specification of purpose and scope, structure development, parameterisation and validation. Structure development is typically focused on qualitative issues and parameterisation quantitative issues, however there are qualitative and quantitative issues that arise in both phases. A common step that occurs after the initial structure has been developed is to perform a rough parameterisation that only captures and illustrates the intended qualitative behaviour of the model. This is done prior to a more rigorous parameterisation, ensuring that the structure is fit for purpose, as well as supporting later development and validation. In our collective experience and in discussions with other modellers, this step is an important part of the development process, but is under-reported in the literature. Since the practice focuses on qualitative issues, despite being quantitative in nature, we call this step qualitative parameterisation and provide an outline of its role in the BN development process.
How to effectively interact audio with vision has garnered considerable interest within the multi-modality research field. Recently, a novel audio-visual segmentation (AVS) task has been proposed, aiming to segment the sounding objects in video frames under the guidance of audio cues. However, most existing AVS methods are hindered by a modality imbalance where the visual features tend to dominate those of the audio modality, due to a unidirectional and insufficient integration of audio cues. This imbalance skews the feature representation towards the visual aspect, impeding the learning of joint audio-visual representations and potentially causing segmentation inaccuracies. To address this issue, we propose AVSAC. Our approach features a Bidirectional Audio-Visual Decoder (BAVD) with integrated bidirectional bridges, enhancing audio cues and fostering continuous interplay between audio and visual modalities. This bidirectional interaction narrows the modality imbalance, facilitating more effective learning of integrated audio-visual representations. Additionally, we present a strategy for audio-visual frame-wise synchrony as fine-grained guidance of BAVD. This strategy enhances the share of auditory components in visual features, contributing to a more balanced audio-visual representation learning. Extensive experiments show that our method attains new benchmarks in AVS performance.