Search

There is a growing need for diverse, high-quality stuttered speech data, particularly in the context of Indian languages. This paper introduces Project Boli, a multi-lingual stuttered speech dataset designed to advance scientific understanding and technology development for individuals who stutter, particularly in India. The dataset constitutes (a) anonymized metadata (gender, age, country, mother tongue) and responses to a questionnaire about how stuttering affects their daily lives, (b) captures both read speech (using the Rainbow Passage) and spontaneous speech (through image description tasks) for each participant and (c) includes detailed annotations of five stutter types: blocks, prolongations, interjections, sound repetitions and word repetitions. We present a comprehensive analysis of the dataset, including the data collection procedure, experience summarization of people who stutter, severity assessment of stuttering events and technical validation of the collected data. The dataset is released as an open access to further speech technology development.

We propose a KSVZ-type axion framework in which vector-like quarks (VLQ) and colored scalars generate Dirac neutrino masses radiatively. The global Peccei-Quinn symmetry (under which the exotic fermions are charged) addresses the strong CP problem and ensures the Dirac nature of neutrinos. The axion also accounts for the observed cosmological dark matter. We systematically explore all viable VLQ representations. Depending on the specific scenario, the framework predicts distinct axion-to-photon couplings, testable through haloscope and helioscope experiments, as well as potentially significant flavor-violating quark-axion interactions., Comment: 27 LaTeX pages; 3 figures

We provide a taxonomy of a dozen enabling network architectures, protocols, and technologies that will define the evolution from 5G to 6G. These technologies span the network protocol stack, different target deployment environments, and various perceived levels of technical maturity. We outline four areas of societal focus that will be impacted by these technologies, and overview several research directions that hold the potential to address the problems in these important focus areas., Comment: This paper has been accepted for publication in the IEEE Communications Magazine. Portions were released online as a report titled 6G Roadmap: A Global Taxonomy in November 2023

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.

Many upper bounds for the moduli of polynomial roots have been proposed but reportedly assessed on selected examples or restricted classes only. Regarding quality measured in terms of worst-case relative overestimation of the maximum root-modulus we establish a simple, nearly optimal result., Comment: 7 pages plus 16-item bibliography

Non-intrusive load monitoring (NILM) focuses on disaggregating total household power consumption into appliance-specific usage. Many advanced NILM methods are based on neural networks that typically require substantial amounts of labeled appliance data, which can be challenging and costly to collect in real-world settings. We hypothesize that appliance data from all households does not uniformly contribute to NILM model improvements. Thus, we propose an active learning approach to selectively install appliance monitors in a limited number of houses. This work is the first to benchmark the use of active learning for strategically selecting appliance-level data to optimize NILM performance. We first develop uncertainty-aware neural networks for NILM and then install sensors in homes where disaggregation uncertainty is highest. Benchmarking our method on the publicly available Pecan Street Dataport dataset, we demonstrate that our approach significantly outperforms a standard random baseline and achieves performance comparable to models trained on the entire dataset. Using this approach, we achieve comparable NILM accuracy with approximately 30% of the data, and for a fixed number of sensors, we observe up to a 2x reduction in disaggregation errors compared to random sampling.

Nearly 6.7 million lives are lost due to air pollution every year. While policymakers are working on the mitigation strategies, public awareness can help reduce the exposure to air pollution. Air pollution data from government-installed sensors is often publicly available in raw format, but there is a non-trivial barrier for various stakeholders in deriving meaningful insights from that data. In this work, we present VayuBuddy, a Large Language Model (LLM)-powered chatbot system to reduce the barrier between the stakeholders and air quality sensor data. VayuBuddy receives the questions in natural language, analyses the structured sensory data with a LLM-generated Python code and provides answers in natural language. We use the data from Indian government air quality sensors. We benchmark the capabilities of 7 LLMs on 45 diverse question-answer pairs prepared by us. Additionally, VayuBuddy can also generate visual analysis such as line-plots, map plot, bar charts and many others from the sensory data as we demonstrate in this work.

As tools for designing and manufacturing hardware become more accessible, smaller producers can develop and distribute novel hardware. However, there aren't established tools to support end-user hardware troubleshooting or routine maintenance. As a result, technical support for hardware remains ad-hoc and challenging to scale. Inspired by software troubleshooting workflows like StackOverflow, we propose a workflow for asynchronous hardware troubleshooting: SplatOverflow. SplatOverflow creates a novel boundary object, the SplatOverflow scene, that users reference to communicate about hardware. The scene comprises a 3D Gaussian Splat of the user's hardware registered onto the hardware's CAD model. The splat captures the current state of the hardware, and the registered CAD model acts as a referential anchor for troubleshooting instructions. With SplatOverflow, maintainers can directly address issues and author instructions in the user's workspace. The instructions define workflows that can easily be shared between users and recontextualized in new environments. In this paper, we describe the design of SplatOverflow, detail the workflows it enables, and illustrate its utility to different kinds of users. We also validate that non-experts can use SplatOverflow to troubleshoot common problems with a 3D printer in a user study., Comment: Our accompanying video figure is available at: https://youtu.be/m4TKeBDuZkU

Beyond the well-known fermions and bosons, anyons-an exotic class of particles-emerge in the fractional quantum Hall effect and exhibit fractional quantum statistics. Anyons can be categorized by their charge, with extensive research focused on those carrying fractional charge, while charge-neutral anyons in 2D electron liquids remain largely unexplored. Here, we introduce bilayer excitons as a new pathway to realizing charge-neutral anyons. By pairing quasiparticles and quasiholes from Laughlin states, we report bilayer excitons that obey fractional quantum statistics. Through layer-asymmetric field-effect doping, we achieve precise control of the anyon population, stabilizing anyonic dipoles at temperatures below the charge gap. Furthermore, we investigate neutral anyons in even-denominator FQHE states, which are likely described by non-Abelian wavefunctions. These findings open the door to exploring non-Abelian statistics in neutral anyons, with the potential to reshape future research in topological quantum phases., Comment: 9 pages for main text, 4 main figures, total of 16 pages, total of 6 figures

Respiratory illnesses are a significant global health burden. Respiratory illnesses, primarily Chronic obstructive pulmonary disease (COPD), is the seventh leading cause of poor health worldwide and the third leading cause of death worldwide, causing 3.23 million deaths in 2019, necessitating early identification and diagnosis for effective mitigation. Among the diagnostic tools employed, spirometry plays a crucial role in detecting respiratory abnormalities. However, conventional clinical spirometry methods often entail considerable costs and practical limitations like the need for specialized equipment, trained personnel, and a dedicated clinical setting, making them less accessible. To address these challenges, wearable spirometry technologies have emerged as promising alternatives, offering accurate, cost-effective, and convenient solutions. The development of machine learning models for wearable spirometry heavily relies on the availability of high-quality ground truth spirometry data, which is a laborious and expensive endeavor. In this research, we propose using active learning, a sub-field of machine learning, to mitigate the challenges associated with data collection and labeling. By strategically selecting samples from the ground truth spirometer, we can mitigate the need for resource-intensive data collection. We present evidence that models trained on small subsets obtained through active learning achieve comparable/better results than models trained on the complete dataset.

Designers of physical objects make assumptions on the material and fabrication workflow early in the design process. Recovering from bad assumptions is hard, because the design and resulting CAD model are locked-in to those assumptions. We present CAMeleon, a software tool to interactively explore fabrication workflows at any stage of the CAD process. CAMeleon's modular architecture allows users to execute their design with different workflows, and preview results. Users can freely explore alternative workflows. CAMeleon's architecture, can be extended with new workflows, increasing the richness of workflows available. We implemented five fabrication workflows in CAMeleon. We demonstrate CAMeleon's extensibility through collaboration with six craftsmen whose workflows we replicated. We also implemented workflows of three papers and reflect on the process of these nine extensions. A usability study (n=12) showed that CAMeleon allowed participants to explore and select workflows for their design which they did not know before.

Generalizing vision-based reinforcement learning (RL) agents to novel environments remains a difficult and open challenge. Current trends are to collect large-scale datasets or use data augmentation techniques to prevent overfitting and improve downstream generalization. However, the computational and data collection costs increase exponentially with the number of task variations and can destabilize the already difficult task of training RL agents. In this work, we take inspiration from recent advances in computational neuroscience and propose a model, Associative Latent DisentAnglement (ALDA), that builds on standard off-policy RL towards zero-shot generalization. Specifically, we revisit the role of latent disentanglement in RL and show how combining it with a model of associative memory achieves zero-shot generalization on difficult task variations without relying on data augmentation. Finally, we formally show that data augmentation techniques are a form of weak disentanglement and discuss the implications of this insight.

In this paper, we study the irreducible objects of the category Cf in of integrable representations for Map full Toroidal Lie algebras with finite dimensional weight spaces. These representations turn out to be single point evaluation modules and hence are irreducible-integrable modules for the underlying full toroidal algebras.

Intelligent embodied agents need to quickly adapt to new scenarios by integrating long histories of experience into decision-making. For instance, a robot in an unfamiliar house initially wouldn't know the locations of objects needed for tasks and might perform inefficiently. However, as it gathers more experience, it should learn the layout of its environment and remember where objects are, allowing it to complete new tasks more efficiently. To enable such rapid adaptation to new tasks, we present ReLIC, a new approach for in-context reinforcement learning (RL) for embodied agents. With ReLIC, agents are capable of adapting to new environments using 64,000 steps of in-context experience with full attention while being trained through self-generated experience via RL. We achieve this by proposing a novel policy update scheme for on-policy RL called "partial updates'' as well as a Sink-KV mechanism that enables effective utilization of a long observation history for embodied agents. Our method outperforms a variety of meta-RL baselines in adapting to unseen houses in an embodied multi-object navigation task. In addition, we find that ReLIC is capable of few-shot imitation learning despite never being trained with expert demonstrations. We also provide a comprehensive analysis of ReLIC, highlighting that the combination of large-scale RL training, the proposed partial updates scheme, and the Sink-KV are essential for effective in-context learning. The code for ReLIC and all our experiments is at https://github.com/aielawady/relic

We present the Habitat-Matterport 3D Open Vocabulary Object Goal Navigation dataset (HM3D-OVON), a large-scale benchmark that broadens the scope and semantic range of prior Object Goal Navigation (ObjectNav) benchmarks. Leveraging the HM3DSem dataset, HM3D-OVON incorporates over 15k annotated instances of household objects across 379 distinct categories, derived from photo-realistic 3D scans of real-world environments. In contrast to earlier ObjectNav datasets, which limit goal objects to a predefined set of 6-20 categories, HM3D-OVON facilitates the training and evaluation of models with an open-set of goals defined through free-form language at test-time. Through this open-vocabulary formulation, HM3D-OVON encourages progress towards learning visuo-semantic navigation behaviors that are capable of searching for any object specified by text in an open-vocabulary manner. Additionally, we systematically evaluate and compare several different types of approaches on HM3D-OVON. We find that HM3D-OVON can be used to train an open-vocabulary ObjectNav agent that achieves both higher performance and is more robust to localization and actuation noise than the state-of-the-art ObjectNav approach. We hope that our benchmark and baseline results will drive interest in developing embodied agents that can navigate real-world spaces to find household objects specified through free-form language, taking a step towards more flexible and human-like semantic visual navigation. Code and videos available at: naoki.io/ovon.

Vision Language Models (VLMs) are typically evaluated with Visual Question Answering (VQA) tasks which assess a model's understanding of scenes. Good VQA performance is taken as evidence that the model will perform well on a broader range of tasks that require both visual and language inputs. However, scene-aware VQA does not fully capture input biases or assess hallucinations caused by a misalignment between modalities. To address this, we propose a Cross-modal Alignment Similarity Test (CAST) to probe VLMs for self-consistency across modalities. This test involves asking the models to identify similarities between two scenes through text-only, image-only, or both and then assess the truthfulness of the similarities they generate. Since there is no ground-truth to compare against, this evaluation does not focus on objective accuracy but rather on whether VLMs are internally consistent in their outputs. We argue that while not all self-consistent models are capable or accurate, all capable VLMs must be self-consistent.

Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent 3D reconstruction of interacting objects and people from a single image. Our contributions include: 1) an optimization framework, featuring a collision loss, tailored to handle human-object and human-human interactions, ensuring spatially coherent scene reconstruction; and 2) a novel technique to robustly estimate 6 degrees of freedom (DOF) poses, specifically for heavily occluded objects, exploiting image inpainting. Notably, our proposed method operates effectively on images from real-world scenarios, without necessitating scene or object-level 3D supervision. Extensive qualitative and quantitative evaluation against existing methods demonstrates a significant reduction in collisions in the final reconstructions of scenes with multiple interacting humans and objects and a more coherent scene reconstruction., Comment: Accepted at AI for 3D Generation, CVPR Workshop

Ocean salinity is known to dramatically affect the climates of Earth-like planets orbiting Sun-like stars, with high salinity leading to less ice and higher surface temperature. However, how ocean composition impacts climate under different conditions, such as around different types of stars or at different positions within the habitable zone, has not been investigated. We used ROCKE-3D, an ocean-atmosphere general circulation model, to simulate how planetary climate responds to ocean salinities for planets with G-star vs. M-dwarf hosts at several stellar fluxes. We find that increasing ocean salinity from 20 to 100 g/kg in our model results in non-linear ice reduction and warming on G-star planets, sometimes causing abrupt transitions to different climate states. Conversely, sea ice on M-dwarf planets responds more gradually and linearly to increasing salinity. Moreover, reductions in sea ice on M-dwarf planets are not accompanied by significant surface warming as on G-star planets. High salinity can modestly bolster the resilience of M-dwarf planets against snowball glaciation and allow these planets to retain surface liquid water further from their host star, but the effects are muted compared to G-star planets that experience snowball bifurcation and climate hysteresis due to the ice-albedo feedback., Comment: 11 pages, 5 figures

In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the Transformer architecture, such as interleaving local-global attentions (Beltagy et al., 2020a) and group-query attention (Ainslie et al., 2023). We also train the 2B and 9B models with knowledge distillation (Hinton et al., 2015) instead of next token prediction. The resulting models deliver the best performance for their size, and even offer competitive alternatives to models that are 2-3 times bigger. We release all our models to the community.

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Excitons, Coulomb-driven bound states of electrons and holes, are typically composed of integer charges. However, in bilayer systems influenced by charge fractionalization, a more exotic form of interlayer exciton can emerge, where pairing occurs between constituents that carry fractional charges. Despite numerous theoretical predictions for such fractional excitons, their experimental observation has remained elusive. Here, we report transport signatures of excitonic pairing within fractional quantum Hall effect states. By probing the composition of these excitons and their impact on the underlying wavefunction, we uncover two novel quantum phases of matter. One of these orders can be viewed as the fractional counterpart of the exciton condensate at a total filling of one, while the other involves a more unusual type of exciton that obeys fermionic and anyonic quantum statistics, challenging the standard paradigm of bosonic excitons., Comment: 9 pages for main text with 4 figures. In total of 24 pages and 15 figures

A striking general bound on the energy gap in topological matter was recently discovered in Ref. [Onishi and Fu, Phys. Rev. X {\bf 14}, 011052 (2024)]. A non-trivial indirect derivation builds on the properties of optical conductivity at an arbitrary frequency. We propose a simpler derivation, allowing multiple generalizations, such as a universal bound on a gap in anisotropic systems, systems with multiple charge carrier types, and topological systems with zero Hall conductance. The derivation builds on the observation that the bound equals $\hbar$ times the ratio of the force by the external electric field on the charge carriers and their total kinematic momentum in the direction perpendicular to the force., Comment: 5 pages

Consider a non-uniform Euler-Bernoulli beam with a tip-mass at one end and a cantilever joint at the other end. The cantilever joint is not fixed and can itself be moved along an axis perpendicular to the beam. The position of the cantilever joint is the control input to the beam. The dynamics of the beam is governed by a coupled PDE-ODE model with boundary input. On a natural state-space, there exists a unique state trajectory for this beam model for every initial state and each smooth control input which is compatible with the initial state. In this paper, we study the motion planning problem of transferring the beam from an initial state to a final state over a prescribed time interval. We address this problem by extending the generating functions approach to flatness-based control, originally proposed in the literature for motion planning of parabolic PDEs, to the beam model. We prove that such a transfer is possible if the initial and final states belong to a certain set, which also contains steady-states of the beam. We illustrate our theoretical results using simulations and experiments., Comment: 6 pages, 4 figures

The Gao-Wald theorem says that de Sitter spacetime reacts to a positive energy perturbation by getting "taller." How does this change in the presence of timelike boundaries? We study this question in two-dimensional de Sitter JT gravity coupled to conformal matter. The effect of the boundaries has its roots in quantum corrections to the vacuum energy of the CFT due to Casimir-like effects. We consider two different kinds of timelike boundaries, either at locations where the coordinate $\varphi$ is constant or at locations where the dilaton is constant. For each kind we compute the vacuum expectation value of the matter CFT stress tensor. The stress tensor violates the null energy condition in the first case and saturates it in the second case, with each case exhibiting a negative energy density in the vacuum state. We then compute the semiclassical backreaction of this energy density and show how it can make the spacetime "fatter" or "taller" or a combination of both, depending on the regime. The spacetime getting fatter corresponds to an increase in the value of the dilaton at the horizon and hence also in the static patch horizon area in the higher-dimensional solution. We comment on the implications of our results for the quantum theories living on the timelike boundaries., Comment: 19 pages, 10 figures plus appendices. v2: added references, minor revisions and one figure

Recognition and interpretation of bird vocalizations are pivotal in ornithological research and ecological conservation efforts due to their significance in understanding avian behaviour, performing habitat assessment and judging ecological health. This paper presents an audio spectrogram-guided classification framework called ASGIR for improved bird sound recognition and information retrieval. Our work is accompanied by a simple-to-use, two-step information retrieval system that uses geographical location and bird sounds to localize and retrieve relevant bird information by scraping Wikipedia page information of recognized birds. ASGIR offers a substantial performance on a random subset of 51 classes of Xeno-Canto dataset Bird sounds from European countries with a median of 100\% performance on F1, Precision and Sensitivity metrics. Our code is available as follows: https://github.com/MainSample1234/AS-GIR ., Comment: Accepted to INTERSPEECH'24

Quality Diversity (QD) has shown great success in discovering high-performing, diverse policies for robot skill learning. While current benchmarks have led to the development of powerful QD methods, we argue that new paradigms must be developed to facilitate open-ended search and generalizability. In particular, many methods focus on learning diverse agents that each move to a different xy position in MAP-Elites-style bounded archives. Here, we show that such tasks can be accomplished with a single, goal-conditioned policy paired with a classical planner, achieving O(1) space complexity w.r.t. the number of policies and generalization to task variants. We hypothesize that this approach is successful because it extracts task-invariant structural knowledge by modeling a relational graph between adjacent cells in the archive. We motivate this view with emerging evidence from computational neuroscience and explore connections between QD and models of cognitive maps in human and other animal brains. We conclude with a discussion exploring the relationships between QD and cognitive maps, and propose future research directions inspired by cognitive maps towards future generalizable algorithms capable of truly open-ended search., Comment: Accepted to GECCO 2024

In order to develop robots that can effectively serve as versatile and capable home assistants, it is crucial for them to reliably perceive and interact with a wide variety of objects across diverse environments. To this end, we proposed Open Vocabulary Mobile Manipulation as a key benchmark task for robotics: finding any object in a novel environment and placing it on any receptacle surface within that environment. We organized a NeurIPS 2023 competition featuring both simulation and real-world components to evaluate solutions to this task. Our baselines on the most challenging version of this task, using real perception in simulation, achieved only an 0.8% success rate; by the end of the competition, the best participants achieved an 10.8\% success rate, a 13x improvement. We observed that the most successful teams employed a variety of methods, yet two common threads emerged among the best solutions: enhancing error detection and recovery, and improving the integration of perception with decision-making processes. In this paper, we detail the results and methodologies used, both in simulation and real-world settings. We discuss the lessons learned and their implications for future research. Additionally, we compare performance in real and simulated environments, emphasizing the necessity for robust generalization to novel settings.

Classical and quantum machine learning are being increasingly applied to various tasks in quantum information technologies. Here, we present an experimental demonstration of quantum control using a physics-informed neural network (PINN). PINN's salient feature is how it encodes the entire control sequence in terms of its network parameters. This feature enables the control sequence to be later adopted to any hardware with optimal time discretization, which contrasts with conventional methods involving a priory time discretization. Here, we discuss two important quantum information tasks: gate synthesis and state preparation. First, we demonstrate quantum gate synthesis by designing a two-qubit CNOT gate and experimentally implementing it on a heteronuclear two-spin NMR register. Second, we demonstrate quantum state preparation by designing a control sequence to efficiently transfer the thermal state into the long-lived singlet state and experimentally implement it on a homonuclear two-spin NMR register. We present a detailed numerical analysis of the PINN control sequences regarding bandwidth, discretization levels, control field errors, and external noise.

Recent studies have shown promising results in utilizing multimodal large language models (MLLMs) for computer vision tasks such as object detection and semantic segmentation. However, many challenging video tasks remain under-explored. Video-language tasks necessitate spatial and temporal comprehension and require significant compute. Therefore, prior works have developed complex, highly specialized architectures or leveraged additional input signals such as video transcripts to best encode contextual and temporal information, which limits their generality and can be impractical. One particularly challenging task is video moment retrieval, which requires precise temporal and contextual grounding. This work demonstrates the surprising effectiveness of leveraging image-text pretrained MLLMs for moment retrieval. We introduce Mr. BLIP (Mr. as in Moment Retrieval), a multimodal, single-stage model that requires no expensive video-language pretraining, no additional input signal (e.g., no transcript or audio), and has a simpler and more versatile design than prior state-of-the-art methods. We achieve a new state-of-the-art in moment retrieval on the widely used benchmarks Charades-STA, QVHighlights, and ActivityNet Captions. Notably, we attain over 9% (absolute) higher Recall (at 0.5 and 0.7 IoU) on the challenging long-video multi-moment QVHighlights benchmark. Our code is publicly available., Comment: Code: https://github.com/sudo-Boris/mr-Blip

Continual learning aims to allow models to learn new tasks without forgetting what has been learned before. This work introduces Elastic Variational Continual Learning with Weight Consolidation (EVCL), a novel hybrid model that integrates the variational posterior approximation mechanism of Variational Continual Learning (VCL) with the regularization-based parameter-protection strategy of Elastic Weight Consolidation (EWC). By combining the strengths of both methods, EVCL effectively mitigates catastrophic forgetting and enables better capture of dependencies between model parameters and task-specific data. Evaluated on five discriminative tasks, EVCL consistently outperforms existing baselines in both domain-incremental and task-incremental learning scenarios for deep discriminative models., Comment: Accepted at ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling

Air pollution kills 7 million people annually. The brick manufacturing industry accounts for 8%-14% of air pollution in the densely populated Indo-Gangetic plain. Due to the unorganized nature of brick kilns, policy violation detection, such as proximity to human habitats, remains challenging. While previous studies have utilized computer vision-based machine learning methods for brick kiln detection from satellite imagery, they utilize proprietary satellite data and rarely focus on compliance with government policies. In this research, we introduce a scalable framework for brick kiln detection and automatic compliance monitoring. We use Google Maps Static API to download the satellite imagery followed by the YOLOv8x model for detection. We identified and hand-verified 19579 new brick kilns across 9 states within the Indo-Gangetic plain. Furthermore, we automate and test the compliance to the policies affecting human habitats, rivers and hospitals. Our results show that a substantial number of brick kilns do not meet the compliance requirements. Our framework offers a valuable tool for governments worldwide to automate and enforce policy regulations for brick kilns, addressing critical environmental and public health concerns., Comment: The PI was not in favor of making the work public on arXiv as the content is not yet ready to be released