Abstract

Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike keypoint matching, which focuses on localized features, segment matching captures structured regions, offering greater robustness to occlusions, lighting variations, and viewpoint changes. In this paper, we leverage the spatial understanding of 3D foundation models to tackle wide-baseline segment matching, a challenging setting involving extreme viewpoint shifts. We propose an architecture that uses the inductive bias of these 3D foundation models to match segments across image pairs with up to 180 degree view-point change rotation. Extensive experiments show that our approach outperforms state-of-the-art methods, including the SAM2 video propagator and local feature matching methods, by up to 30% on the AUPRC metric, on ScanNet++ and Replica datasets. We further demonstrate benefits of the proposed model on relevant downstream tasks, including 3D instance mapping and object-relative navigation. Project Page: https://segmast3r.github.io/

Abstract

We propose an alignment-free, end-to-end Non-Audible Murmur (NAM)-to-Speech conversion model. Existing methods rely on large NAM-text pairs per speaker to generate high-quality alignments for training non-autoregressive models. However, alignment quality deteriorates when trained on multispeaker data, limiting their ability to generalize and effectively utilize the available training data. To address this, we introduce a streamlined autoregressive approach that eliminates the need for explicit alignment learning. By leveraging multi-speaker samples, synthetic training pairs, and multitask character recognition training, our method reduces the word error rate (WER) by 59.19% compared to the state-of-the-art (SOTA) on two public datasets. We demonstrate the model’s zero-shot capability and validate the effectiveness of multitask training through ablation studies. Speech samples are available at https: //noalignnam.github.io/autoregressiveNAM/

Abstract

We use the spin-boson model to describe the dynamics of a two-level atom interacting with Fabry-Pérot cavity modes. We solve the Schrödinger equation for the system-bath model without the Born-Markov approximation to derive the non-Markovian reduced dynamics of the qubit. We further construct an exact Lindblad-type master equation for it. Similar to the quantum Otto cycle, we construct a non-Markovian quasicyclic process based on the atom-cavity interactions, which we call the quasi-Otto cycle. For judicious choices of input state and parameters, the quasicycle can be more efficient as a quantum engine than the Otto cycle. We also show that if the quasicycle is repeated multiple times, the efficiency of the quasi-Otto engine asymptotically approaches that of the Otto engine.

Abstract

Water scarcity and inefficient resource management present critical challenges, with conventional flow measurement techniques often relying on expensive and invasive methods. This work evaluates the performance of three low-cost pressure sensors (HK3022, MBS3000, and Series 21Y) for internet of things (IoT) and machine learning (ML) based water flow estimation. Tests were conducted in a closed-loop experimental setup across pressure ranges from 1.0 to 2.0 bar, generating over 8,640 pressure readings and 2,160 flow measurements. Sensor performance was assessed through pressure measurement accuracy metrics (RMSE and CV), and flow estimation reliability was assessed using five ML algorithms. Results demonstrate that all sensors achieve comparable flow estimation accuracy. While calibration improves absolute pressure measurement accuracy, it provides minimal advantage for flow estimation tasks. This low-cost, non-invasive approach offers a promising water monitoring solution that is accessible and economically viable.

Abstract

We present a unified approach for constraint displacement problems in which a robot finds a feasible path by displacing constraints or obstacles. To this end, we propose a two stage process that returns locally optimal obstacle displacements to enable a feasible path for the robot. The first stage proceeds by computing a trajectory through the obstacles while minimizing an appropriate objective function. In the second stage, these obstacles are displaced to make the computed robot trajectory feasible, that is, collision-free. Several examples are provided that successfully demonstrate our approach on two distinct classes of constraint displacement problems.

Abstract

Deep thermalization refers to the emergence of Haar-like randomness from quantum systems upon partial measurements. As a generalization of quantum thermalization, it is often associated with high complexity and entanglement. Here, we introduce computational deep thermalization and construct the fastest possible dynamics exhibiting it at infinite effective temperature. Our circuit dynamics produce quantum states with low entanglement in polylogarithmic depth that are indistinguishable from Haar random states to any computationally bounded observer. Importantly, the observer is allowed to request many copies of the same residual state obtained from partial projective measurements on the state—this condition is beyond the standard settings of quantum pseudorandomness but natural for deep thermalization. In cryptographic terms, these states are pseudorandom and pseudoentangled, and crucially, they retain these properties under local measurements. Our results demonstrate a new form of computational thermalization in which thermal-like behavior arises from structured quantum states endowed with cryptographic properties instead of from highly unstructured ensembles. The low resource complexity of preparing these states suggests scalable simulations of deep thermalization using quantum computers. Our Letter also motivates the study of computational quantum pseudorandomness beyond BQP observers.

Abstract

Certain types of quantum computing platforms, such as those realized using Rydberg atoms or Kerr-cat qubits, are natively more susceptible to Pauli-Z noise than Pauli-X noise, or vice versa. On such hardware, it is useful to ensure that computations use only gates that maintain the Z-bias (or X-bias) in the noise. This is so that quantum error-correcting codes tailored for biased-noise models can be used to provide fault-tolerance on these platforms. In this paper, we follow up on the recent work of Fellous-Asiani et al. (npj Quantum Inf., 2025) in studying the structure and properties of bias-preserving gates. Our main contributions are threefold: (1) We give a novel characterization of Z-bias-preserving gates based on their decomposition as a linear combination of Pauli operators. (2) We show that any Z-bias-preserving gate can be approximated arbitrarily well using only gates from the set {X,R_z(theta),CNOT,CCNOT}, where theta is any irrational multiple of 2pi. (3) We prove, by drawing a connection with coherence resource theory, that any Z-bias-preserving logical operator acting on the logical qubits of a Calderbank-Shor-Steane (CSS) code can be realized by applying Z-bias-preserving gates on the physical qubits. Along the way, we also demonstrate that Z-bias-preserving gates are far from being universal for quantum computation.

Abstract

Air pollution represents one of the most critical environmental and public health challenges globally, with traditional sensor-based monitoring systems facing significant scalability and economic constraints. Image-based air quality estimation has emerged as a promising alternative, leveraging the visual characteristics of atmospheric pollutants in traffic scenes. However, existing methods suffer from limited cross-city generalization and inadequate exploitation of multi-view perspectives. We present AQIFormer, a novel transformer-based ensemble architecture that addresses these fundamental limitations through innovative dual-view integration, weather-aware attention mechanisms, and comprehensive multi-task learning. Our approach uniquely combines front and rear traffic imagery with meteorological parameters to achieve robust air quality classification across diverse urban environments. Extensive evaluation on a dataset of 26,678 synchronized front–rear image pairs demonstrates 89.96% accuracy, representing a 14.96% improvement over state-of-the-art methods. Most importantly, our model maintains exceptional cross-city generalization capabilities, achieving 81.67% accuracy on an independent dataset collected in Nagpur, India, with only 8.29% performance degradation using few-shot adaptation and minimal training samples.

Abstract

Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer photovoltaic farms. As renewable energy is highly intermittent, building accurate solar irradiance forecasting systems that are data-efficient is essential for efficient grid management and enabling the ongoing proliferation of solar energy, which is crucial to achieve the United Nations' net zero goals. In this work, we propose SPIRIT, a novel framework leveraging foundation models for solar irradiance forecasting, making it applicable to newer solar installations. Our approach outperforms state-of-the-art models in zero-shot transfer learning by upto 70%, enabling effective performance at new locations without relying on any past data. Further improvements in performance are achieved through fine-tuning, as more location-specific data becomes available. These findings are supported by statistical significance, further validating our approach. By dramatically reducing the forecasting setup timeline, SPIRIT accelerates solar farm deployment in all potential global sites, most of which lack historical data, thereby democratizing access to clean energy and enabling participation in the renewable energy transition.

Abstract

In recent times, denoising diffusion probabilistic models (DPMs) have proven to show significant success in medical image generation and denoising, while also serving as powerful representation learners for downstream tasks such as segmentation. However, their effectiveness in segmentation is limited by the need for detailed pixel-wise annotations, which are expensive, time-consuming, and require expert knowledge—a significant bottleneck in real-world clinical applications. In order to mitigate this limitation of label-efficiency, we propose a fast and efficient model named FastTextDiff, a diffusion-based segmentation model that integrates medical text annotations to enhance semantic representations. Our approach leverages ModernBERT, a transformer-based language model capable of processing long medical text sequences, to establish a strong connection between textual annotations and semantic meaning in medical imaging. ModernBERT can efficiently encode clinical knowledge for directing segmentation tasks since it has been trained on both MIMIC-III and MIMIC-IV. Label-efficient segmentation with enhanced performance is made possible by cross-modal attention processes, which enable smooth interaction between visual and textual modalities. This study validates ModernBERT as a quick and scalable substitute for Clinical BioBERT in diffusion-based segmentation pipelines and demonstrates the promise of multi-modal techniques for medical image analysis. By replacing Clinical BioBERT with ModernBERT, our model benefits from Flash Attention 2 for memory-efficient training, an alternating attention mechanism for computational efficiency, and a training corpus of 2 trillion tokens, significantly improving text-based medical image segmentation. Our experiments demonstrate that FastTextDiff achieves better segmentation performance and faster training compared to traditional diffusion-based models. We release this trained model on Hugging Face and GitHub.