Air pollution kills 7 million people annually. The brick kiln sector significantly contributes to economic development but also accounts for 8-14\% of air pollution in India. Policymakers have implemented compliance measures to regulate brick kilns. Emission inventories are critical for air quality modeling and source apportionment studies. However, the largely unorganized nature of the brick kiln sector necessitates labor-intensive survey efforts for monitoring. Recent efforts by air quality researchers have relied on manual annotation of brick kilns using satellite imagery to build emission inventories, but this approach lacks scalability. Machine-learning-based object detection methods have shown promise for detecting brick kilns; however, previous studies often rely on costly high-resolution imagery and fail to integrate with governmental policies. In this work, we developed a scalable machine-learning pipeline that detected and classified 30638 brick kilns across five states in the Indo-Gangetic Plain using free, moderate-resolution satellite imagery from Planet Labs. Our detections have a high correlation with on-ground surveys. We performed automated compliance analysis based on government policies. In the Delhi airshed, stricter policy enforcement has led to the adoption of efficient brick kiln technologies. This study highlights the need for inclusive policies that balance environmental sustainability with the livelihoods of workers.

How to properly conduct human evaluations for text summarization is a longstanding challenge. The Pyramid human evaluation protocol, which assesses content selection by breaking the reference summary into sub-units and verifying their presence in the system summary, has been widely adopted. However, it suffers from a lack of systematicity in the definition and granularity of the sub-units. We address these problems by proposing QAPyramid, which decomposes each reference summary into finer-grained question-answer (QA) pairs according to the QA-SRL framework. We collect QA-SRL annotations for reference summaries from CNN/DM and evaluate 10 summarization systems, resulting in 8.9K QA-level annotations. We show that, compared to Pyramid, QAPyramid provides more systematic and fine-grained content selection evaluation while maintaining high inter-annotator agreement without needing expert annotations. Furthermore, we propose metrics that automate the evaluation pipeline and achieve higher correlations with QAPyramid than other widely adopted metrics, allowing future work to accurately and efficiently benchmark summarization systems.

The card game Hanabi is considered a strong medium for the testing and development of multi-agent reinforcement learning (MARL) algorithms, due to its cooperative nature, hidden information, limited communication and remarkable complexity. Previous research efforts have explored the capabilities of MARL algorithms within Hanabi, focusing largely on advanced architecture design and algorithmic manipulations to achieve state-of-the-art performance for a various number of cooperators. However, this often leads to complex solution strategies with high computational cost and requiring large amounts of training data. For humans to solve the Hanabi game effectively, they require the use of conventions, which often allows for a means to implicitly convey ideas or knowledge based on a predefined, and mutually agreed upon, set of ``rules''. Multi-agent problems containing partial observability, especially when limited communication is present, can benefit greatly from the use of implicit knowledge sharing. In this paper, we propose a novel approach to augmenting the action space using conventions, which act as special cooperative actions that span over multiple time steps and multiple agents, requiring agents to actively opt in for it to reach fruition. These conventions are based on existing human conventions, and result in a significant improvement on the performance of existing techniques for self-play and cross-play across a various number of cooperators within Hanabi.

In the modern world, our cities and societies face several technological and societal challenges, such as rapid urbanization, global warming & climate change, the digital divide, and social inequalities, increasing the need for more sustainable cities and societies. Addressing these challenges requires a multifaceted approach involving all the stakeholders, sustainable planning, efficient resource management, innovative solutions, and modern technologies. Like other modern technologies, social media informatics also plays its part in developing more sustainable and resilient cities and societies. Despite its limitations, social media informatics has proven very effective in various sustainable cities and society applications. In this paper, we review and analyze the role of social media informatics in sustainable cities and society by providing a detailed overview of its applications, associated challenges, and potential solutions. This work is expected to provide a baseline for future research in the domain.

With the rise of generative AI and rapid growth of high-quality video generation, video guardrails have become more crucial than ever to ensure safety and security across platforms. Current video guardrails, however, are either overly simplistic, relying on pure classification models trained on simple policies with limited unsafe categories, which lack detailed explanations, or prompting multimodal large language models (MLLMs) with long safety guidelines, which are inefficient and impractical for guardrailing real-world content. To bridge this gap, we propose SafeWatch, an efficient MLLM-based video guardrail model designed to follow customized safety policies and provide multi-label video guardrail outputs with content-specific explanations in a zero-shot manner. In particular, unlike traditional MLLM-based guardrails that encode all safety policies autoregressively, causing inefficiency and bias, SafeWatch uniquely encodes each policy chunk in parallel and eliminates their position bias such that all policies are attended simultaneously with equal importance. In addition, to improve efficiency and accuracy, SafeWatch incorporates a policy-aware visual token pruning algorithm that adaptively selects the most relevant video tokens for each policy, discarding noisy or irrelevant information. This allows for more focused, policy-compliant guardrail with significantly reduced computational overhead. Considering the limitations of existing video guardrail benchmarks, we propose SafeWatch-Bench, a large-scale video guardrail benchmark comprising over 2M videos spanning six safety categories which covers over 30 tasks to ensure a comprehensive coverage of all potential safety scenarios. SafeWatch outperforms SOTA by 28.2% on SafeWatch-Bench, 13.6% on benchmarks, cuts costs by 10%, and delivers top-tier explanations validated by LLM and human reviews.

Understanding the internal computations of large language models (LLMs) is crucial for aligning them with human values and preventing undesirable behaviors like toxic content generation. However, mechanistic interpretability is hindered by polysemanticity -- where individual neurons respond to multiple, unrelated concepts. While Sparse Autoencoders (SAEs) have attempted to disentangle these features through sparse dictionary learning, they have compromised LLM performance due to reliance on post-hoc reconstruction loss. To address this issue, we introduce Mixture of Monosemantic Experts for Transformers (Monet) architecture, which incorporates sparse dictionary learning directly into end-to-end Mixture-of-Experts pretraining. Our novel expert decomposition method enables scaling the expert count to 262,144 per layer while total parameters scale proportionally to the square root of the number of experts. Our analyses demonstrate mutual exclusivity of knowledge across experts and showcase the parametric knowledge encapsulated within individual experts. Moreover, Monet allows knowledge manipulation over domains, languages, and toxicity mitigation without degrading general performance. Our pursuit of transparent LLMs highlights the potential of scaling expert counts to enhance mechanistic interpretability and directly resect the internal knowledge to fundamentally adjust model behavior. The source code and pretrained checkpoints are available at https://github.com/dmis-lab/Monet.

Despite the rapid pace at which deep networks are improving on standardized vision benchmarks, they are still outperformed by humans on real-world vision tasks. This paradoxical lack of generalization could be addressed by making deep networks more brain-like. Although several benchmarks have compared the ability of deep networks to predict brain responses to natural images, they do not capture subtle but important brain-like emergent properties. To resolve this issue, we report several well-known perceptual and neural emergent properties that can be tested on deep networks. To evaluate how various design factors impact brain-like properties, we systematically evaluated over 30 state-of-the-art networks with varying network architectures, training datasets and training regimes. Our main findings are as follows. First, network architecture had the strongest impact on brain-like properties compared to dataset and training regime variations. Second, networks varied widely in their alignment to the brain with no single network outperforming all others. Taken together, our results complement existing benchmarks by revealing brain-like properties that are either emergent or lacking in state-of-the-art deep networks.

Normalizing Flows (NFs) are likelihood-based models for continuous inputs. They have demonstrated promising results on both density estimation and generative modeling tasks, but have received relatively little attention in recent years. In this work, we demonstrate that NFs are more powerful than previously believed. We present TarFlow: a simple and scalable architecture that enables highly performant NF models. TarFlow can be thought of as a Transformer-based variant of Masked Autoregressive Flows (MAFs): it consists of a stack of autoregressive Transformer blocks on image patches, alternating the autoregression direction between layers. TarFlow is straightforward to train end-to-end, and capable of directly modeling and generating pixels. We also propose three key techniques to improve sample quality: Gaussian noise augmentation during training, a post training denoising procedure, and an effective guidance method for both class-conditional and unconditional settings. Putting these together, TarFlow sets new state-of-the-art results on likelihood estimation for images, beating the previous best methods by a large margin, and generates samples with quality and diversity comparable to diffusion models, for the first time with a stand-alone NF model. We make our code available at https://github.com/apple/ml-tarflow.

Diabetic macular edema (DME) is a severe complication of diabetes, characterized by thickening of the central portion of the retina due to accumulation of fluid. DME is a significant and common cause of visual impairment in diabetic patients. Center-involved DME (ci-DME) is the highest risk form of disease because fluid extends close to the fovea which is responsible for sharp central vision. Earlier diagnosis or prediction of ci-DME may improve treatment outcomes. Here, we propose an ensemble method to predict ci-DME onset within a year, after using synthetic ultra-wide field color fundus photography (UWF-CFP) images provided by the DIAMOND Challenge during development. We adopted a variety of baseline state-of-the-art classification networks including ResNet, DenseNet, EfficientNet, and VGG with the aim of enhancing model robustness. The best performing models were Densenet-121, Resnet-152 and EfficientNet-b7, and these were assembled into a definitive predictive model. The final ensemble model demonstrates a strong performance with an Area Under Curve (AUC) of 0.7017, an F1 score of 0.6512, and an Expected Calibration Error (ECE) of 0.2057 when deployed on the synthetic test dataset. Results from our ensemble model were superior/comparable to previous recorded results in highly curated settings using conventional fundus photography/ultra-wide field fundus photography. Optimal sensitivity in previous studies (using humans or computers to diagnose) ranges from 67.3%-98%, specificity from 47.8%-80%. Therefore, our method can be used safely and effectively in a range of settings may facilitate earlier diagnosis, better treatment decisions, and improved prognostication in ci-DME.

Deep learning has made significant strides in automated brain tumor segmentation from magnetic resonance imaging (MRI) scans in recent years. However, the reliability of these tools is hampered by the presence of poor-quality segmentation outliers, particularly in out-of-distribution samples, making their implementation in clinical practice difficult. Therefore, there is a need for quality control (QC) to screen the quality of the segmentation results. Although numerous automatic QC methods have been developed for segmentation quality screening, most were designed for cardiac MRI segmentation, which involves a single modality and a single tissue type. Furthermore, most prior works only provided subject-level predictions of segmentation quality and did not identify erroneous parts segmentation that may require refinement. To address these limitations, we proposed a novel multi-task deep learning architecture, termed QCResUNet, which produces subject-level segmentation-quality measures as well as voxel-level segmentation error maps for each available tissue class. To validate the effectiveness of the proposed method, we conducted experiments on assessing its performance on evaluating the quality of two distinct segmentation tasks. First, we aimed to assess the quality of brain tumor segmentation results. For this task, we performed experiments on one internal and two external datasets. Second, we aimed to evaluate the segmentation quality of cardiac Magnetic Resonance Imaging (MRI) data from the Automated Cardiac Diagnosis Challenge. The proposed method achieved high performance in predicting subject-level segmentation-quality metrics and accurately identifying segmentation errors on a voxel basis. This has the potential to be used to guide human-in-the-loop feedback to improve segmentations in clinical settings.