Recent advances in text-to-image generation have made remarkable progress in synthesizing realistic human photos conditioned on given text prompts. However, existing personalized generation methods cannot simultaneously satisfy the requirements of high efficiency, promising identity (ID) fidelity, and flexible text controllability. In this work, we introduce PhotoMaker, an efficient personalized text-to-image generation method, which mainly encodes an arbitrary number of input ID images into a stack ID embedding for preserving ID information. Such an embedding, serving as a unified ID representation, can not only encapsulate the characteristics of the same input ID comprehensively, but also accommodate the characteristics of different IDs for subsequent integration. This paves the way for more intriguing and practically valuable applications. Besides, to drive the training of our PhotoMaker, we propose an ID-oriented data construction pipeline to assemble the training data. Under the nourishment of the dataset constructed through the proposed pipeline, our PhotoMaker demonstrates better ID preservation ability than test-time fine-tuning based methods, yet provides significant speed improvements, high-quality generation results, strong generalization capabilities, and a wide range of applications. Our project page is available at https://photo-maker.github.io/

The performance of automatic summarization models has improved dramatically in recent years. Yet, there is still a gap in meeting specific information needs of users in real-world scenarios, particularly when a targeted summary is sought, such as in the useful aspect-based summarization setting targeted in this paper. Previous datasets and studies for this setting have predominantly concentrated on a limited set of pre-defined aspects, focused solely on single document inputs, or relied on synthetic data. To advance research on more realistic scenarios, we introduce OpenAsp, a benchmark for multi-document \textit{open} aspect-based summarization. This benchmark is created using a novel and cost-effective annotation protocol, by which an open aspect dataset is derived from existing generic multi-document summarization datasets. We analyze the properties of OpenAsp showcasing its high-quality content. Further, we show that the realistic open-aspect setting realized in OpenAsp poses a challenge for current state-of-the-art summarization models, as well as for large language models.

Fully homomorphic encryption (FHE) is a promising cryptographic primitive for realizing private neural network inference (PI) services by allowing a client to fully offload the inference task to a cloud server while keeping the client data oblivious to the server. This work proposes NeuJeans, an FHE-based solution for the PI of deep convolutional neural networks (CNNs). NeuJeans tackles the critical problem of the enormous computational cost for the FHE evaluation of convolutional layers (conv2d), mainly due to the high cost of data reordering and bootstrapping. We first propose an encoding method introducing nested structures inside encoded vectors for FHE, which enables us to develop efficient conv2d algorithms with reduced data reordering costs. However, the new encoding method also introduces additional computations for conversion between encoding methods, which could negate its advantages. We discover that fusing conv2d with bootstrapping eliminates such computations while reducing the cost of bootstrapping. Then, we devise optimized execution flows for various types of conv2d and apply them to end-to-end implementation of CNNs. NeuJeans accelerates the performance of conv2d by up to 5.68 times compared to state-of-the-art FHE-based PI work and performs the PI of a CNN at the scale of ImageNet (ResNet18) within a mere few seconds

Measurement uncertainties, represented by cyber-attacks and data losses, seriously degrade the quality of power system measurements. Fortunately, the powerful generation ability of the denoising diffusion models can enable more precise measurement generation for power system data recovery. However, the controllable data generation and efficient computing methods of denoising diffusion models for deterministic trajectory still need further investigation. To this end, this paper proposes an improved two-stage denoising diffusion model (TSDM) to identify and reconstruct the measurements with various measurement uncertainties. The first stage of the model comprises a classifier-guided conditional anomaly detection component, while the second stage involves diffusion-based measurement imputation component. Moreover, the proposed TSDM adopts precise means and optimal variances to accelerate the diffusion generation process with subsequence sampling. Extensive numerical case studies demonstrate that the proposed TSDM can accurately recover power system measurements despite strong randomness under renewable energy integration and highly nonlinear dynamics under complex cyber-physical contingencies. Additionally, the proposed TSDM has stronger robustness compared to existing reconstruction networks and exhibits lower computational complexity than general denoising diffusion models.

The increasing size and severity of wildfires across western North America have generated dangerous levels of PM$_{2.5}$ pollution in recent years. In a warming climate, expanding the use of prescribed fires is widely considered to be the most robust fire mitigation strategy. However, reliably forecasting the potential air quality impact from these prescribed fires, a critical ingredient in determining the fires' location and time, at hourly to daily time scales remains a challenging problem. This paper proposes a novel integration of prescribed fire simulation with a spatio-temporal graph neural network-based PM$_{2.5}$ forecasting model. The experiments in this work focus on determining the optimal time for implementing prescribed fires in California as well as quantifying the potential air quality trade-offs involved in conducting more prescribed fires outside the fire season.

In an era where information is ubiquitous, the news media's role expands beyond mere reporting; it actively constructs and frames public discourse[Raza and Ding, 2022]. The power of the media to influence perception and decision-making cannot be understated, especially in a world where news is consumed in real-time from a number of sources[Raza, 2021]. Traditional notions of media as impartial observers are giving way to a more critical understanding of its participatory role in shaping socio-political narratives. The dataset introduced in this research represents a crucial step in addressing the multifaceted nature of news media bias. This data includes a wide array of dimensions such as race, gender, age, occupation, and climate change. The dataset provides a holistic tool for showing the complex interplay of factors that characterize contemporary news media. This approach acknowledges that biases in media are not monolithic but are instead a confluence of various underlying factors, each contributing to the overarching narrative in its unique way [Lei et al., 2022]. This expansive scope is particularly important given the current global landscape, where issues of racial and gender equality, climate change, and political polarization are at the forefront of public consciousness.

Large language models (LLMs) exhibit superior performance on various natural language tasks, but they are susceptible to issues stemming from outdated data and domain-specific limitations. In order to address these challenges, researchers have pursued two primary strategies, knowledge editing and retrieval augmentation, to enhance LLMs by incorporating external information from different aspects. Nevertheless, there is still a notable absence of a comprehensive survey. In this paper, we propose a review to discuss the trends in integration of knowledge and large language models, including taxonomy of methods, benchmarks, and applications. In addition, we conduct an in-depth analysis of different methods and point out potential research directions in the future. We hope this survey offers the community quick access and a comprehensive overview of this research area, with the intention of inspiring future research endeavors.

In many text-generation problems, users may prefer not only a single response, but a diverse range of high-quality outputs from which to choose. Quality-diversity (QD) search algorithms aim at such outcomes, by continually improving and diversifying a population of candidates. However, the applicability of QD to qualitative domains, like creative writing, has been limited by the difficulty of algorithmically specifying measures of quality and diversity. Interestingly, recent developments in language models (LMs) have enabled guiding search through AI feedback, wherein LMs are prompted in natural language to evaluate qualitative aspects of text. Leveraging this development, we introduce Quality-Diversity through AI Feedback (QDAIF), wherein an evolutionary algorithm applies LMs to both generate variation and evaluate the quality and diversity of candidate text. When assessed on creative writing domains, QDAIF covers more of a specified search space with high-quality samples than do non-QD controls. Further, human evaluation of QDAIF-generated creative texts validates reasonable agreement between AI and human evaluation. Our results thus highlight the potential of AI feedback to guide open-ended search for creative and original solutions, providing a recipe that seemingly generalizes to many domains and modalities. In this way, QDAIF is a step towards AI systems that can independently search, diversify, evaluate, and improve, which are among the core skills underlying human society's capacity for innovation.

Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life. However, the practical implementations of these models have also exposed inherent risks, bringing to the forefront their evil sides and sparking concerns regarding their trustworthiness. Despite the wealth of literature on this subject, a comprehensive survey specifically delving into the intersection of large-scale generative models and their trustworthiness remains largely absent. To bridge this gap, this paper investigates both the long-standing and emerging threats associated with these models across four fundamental dimensions: 1) privacy, 2) security, 3) fairness, and 4) responsibility. Based on the investigation results, we develop an extensive map outlining the trustworthiness of large generative models. After that, we provide practical recommendations and potential research directions for future secure applications equipped with large generative models, ultimately promoting the trustworthiness of the models and benefiting the society as a whole.

In computational social choice, the distortion of a voting rule quantifies the degree to which the rule overcomes limited preference information to select a socially desirable outcome. This concept has been investigated extensively, but only through a worst-case lens. Instead, we study the expected distortion of voting rules with respect to an underlying distribution over voter utilities. Our main contribution is the design and analysis of a novel and intuitive rule, binomial voting, which provides strong distribution-independent guarantees for both expected distortion and expected welfare.