We study outlier (a.k.a., anomaly) detection for single-pass non-stationary streaming data. In the well-studied offline or batch outlier detection problem, traditional methods such as kernel One-Class SVM (OCSVM) are both computationally heavy and prone to large false-negative (Type II) errors under non-stationarity. To remedy this, we introduce SONAR, an efficient SGD-based OCSVM solver with strongly convex regularization. We show novel theoretical guarantees on the Type I/II errors of SONAR, superior to those known for OCSVM, and further prove that SONAR ensures favorable lifelong learning guarantees under benign distribution shifts. In the more challenging problem of adversarial non-stationary data, we show that SONAR can be used within an ensemble method and equipped with changepoint detection to achieve adaptive guarantees, ensuring small Type I/II errors on each phase of data. We validate our theoretical findings on synthetic and real-world datasets.

Abstract--This paper introduces SENSE (Shared Embedding for N-lingual Speech and tExt), an open-source solution inspired by the SAMU-XLSR framework and conceptually similar to Meta AI's SONAR models. These approaches rely on a teacher-student framework to align a self-supervised speech encoder with the language-agnostic continuous representations of a text encoder at the utterance level. We describe how the original SAMU-XLSR method has been updated by selecting a stronger teacher text model and a better initial speech encoder . The source code for training and using SENSE models has been integrated into the SpeechBrain toolkit, and the first SENSE model we trained has been publicly released. We report experimental results on multilingual and multimodal semantic tasks, where our SENSE model achieves highly competitive performance. Finally, this study offers new insights into how semantics are captured in such semantically aligned speech encoders. Speech foundation models based on self-supervised learning (SSL) have brought significant advances in speech processing. These models, such as wav2vec 2.0 [1], HuBERT [2], and WavLM [3], generate learned speech representations that can be applied to a wide range of downstream speech processing tasks. By training on large amounts of unlabelled speech data, SSL models have demonstrated the ability to capture crucial speech features, such as phonemes and other acoustic units [4]. This capability has led to significant progress in multiple downstream tasks, including speech recognition [1], speech translation [5], speech separation, speaker verification, speaker diarization [3], and emotion detection [6]. Different approaches have been proposed to pretrain model by aligning speech and text, like mSLAM [7], a Massively multilingual joint pre-training for speech and text.

Real-time imaging sonar is crucial for underwater monitoring where optical sensing fails, but its use is limited by low uplink bandwidth and severe sonar-specific artifacts (speckle, motion blur, reverberation, acoustic shadows) affecting up to 98% of frames. W e present SCOPE, a self-supervised framework that jointly performs compression and artifact correction without clean-noise pairs or synthetic assumptions. SCOPE combines (i) Adaptive Code-book Compression (ACC), which learns frequency-encoded latent representations tailored to imaging sonar, with (ii) Frequency-Aware Multiscale Segmentation (F AMS), which decomposes frames into low-frequency structure and sparse high-frequency dynamics while suppressing rapidly fluctuating artifacts. A hedging training strategy further guides frequency-aware learning using low-pass proxy pairs generated without labels. Evaluated on months of in-situ ARIS sonar data, SCOPE achieves a structural similarity index (SSIM) of 0.77, representing a 40% improvement over prior self-supervised denoising baselines, at bitrates down to 0.0118 bpp. It reduces uplink bandwidth by more than 80% while improving downstream detection. The system runs in real time, with 3.1 ms encoding on an embedded GPU and 97 ms full multi-layer decoding on the server end. SCOPE has been deployed for months in three Pacific Northwest rivers to support real-time salmon enumeration and environmental monitoring in the wild. Results demonstrate that learning frequency-structured latents enables practical, low-bitrate sonar streaming with preserved signal details under real-world deployment conditions.

Deepfake (DF) audio detectors still struggle to generalize to out of distribution inputs. A central reason is spectral bias, the tendency of neural networks to learn low-frequency structure before high-frequency (HF) details, which both causes DF generators to leave HF artifacts and leaves those same artifacts under-exploited by common detectors. To address this gap, we propose Spectral-cONtrastive Audio Residuals (SONAR), a frequency-guided framework that explicitly disentangles an audio signal into complementary representations. An XLSR encoder captures the dominant low-frequency content, while the same cloned path, preceded by learnable SRM, value-constrained high-pass filters, distills faint HF residuals. Frequency cross-attention reunites the two views for long-and short-range frequency dependencies, and a frequency-aware Jensen-Shannon contrastive loss pulls real content-noise pairs together while pushing fake embeddings apart, accelerating optimization and sharpening decision boundaries. By elevating faint high-frequency residuals to first-class learning signals, SONAR unveils a fully data-driven, frequency-guided contrastive framework that splits the latent space into two disjoint manifolds: natural-HF for genuine audio and distorted-HF for synthetic audio, thereby sharpening decision boundaries. Because the scheme operates purely at the representation level, it is architecture-agnostic and, in future work, can be seamlessly integrated into any model or modality where subtle high-frequency cues are decisive. Generative AI now enables the creation of photorealistic images, video, and speech. In 2024, political deepfakes flooded social media during global elections, while voice-cloning scams caused multimillion-dollar losses, including a 25M$ transfer [1, 2].

Accurate 3D reconstruction in visually-degraded underwater environments remains a formidable challenge. Single-modality approaches are insufficient: vision-based methods fail due to poor visibility and geometric constraints, while sonar is crippled by inherent elevation ambiguity and low resolution. Consequently, prior fusion technique relies on heuristics and flawed geometric assumptions, leading to significant artifacts and an inability to model complex scenes. In this paper, we introduce SonarSweep, a novel, end-to-end deep learning framework that overcomes these limitations by adapting the principled plane sweep algorithm for cross-modal fusion between sonar and visual data. Extensive experiments in both high-fidelity simulation and real-world environments demonstrate that SonarSweep consistently generates dense and accurate depth maps, significantly outperforming state-of-the-art methods across challenging conditions, particularly in high turbidity. To foster further research, we will publicly release our code and a novel dataset featuring synchronized stereo-camera and sonar data, the first of its kind.

Sentence embeddings can be decoded to give approximations of the original texts used to create them. We explore this effect in the context of text simplification, demonstrating that reconstructed text embeddings preserve complexity levels. We experiment with a small feed forward neural network to effectively learn a transformation between sentence embeddings representing high-complexity and low-complexity texts. We provide comparison to a Seq2Seq and LLM-based approach, showing encouraging results in our much smaller learning setting. Finally, we demonstrate the applicability of our transformation to an unseen simplification dataset (MedEASI), as well as datasets from languages outside the training data (ES,DE). We conclude that learning transformations in sentence embedding space is a promising direction for future research and has potential to unlock the ability to develop small, but powerful models for text simplification and other natural language generation tasks.

Autonomous navigation in 3D is a fundamental problem for autonomy. Despite major advancements in terrestrial and aerial settings due to improved range sensors including LiDAR, compact sensors with similar capabilities for underwater robots have only recently become available, in the form of 3D sonars. This paper introduces a novel underwater 3D navigation pipeline, called SHRUMS (Sensor Hallucination for Robust Underwater Motion planning with 3D Sonar). To the best of the authors' knowledge, SHRUMS is the first underwater autonomous navigation stack to integrate a 3D sonar. The proposed pipeline exhibits strong robustness while operating in complex 3D environments in spite of extremely poor visibility conditions. To accommodate the intricacies of the novel sensor data stream while achieving real-time locally optimal performance, SHRUMS introduces the concept of hallucinating sensor measurements from non-existent sensors with convenient arbitrary parameters, tailored to application specific requirements. The proposed concepts are validated with real 3D sonar sensor data, utilizing real inputs in challenging settings and local maps constructed in real-time. Field deployments validating the proposed approach in full are planned in the very near future.

Noname manuscript No. (will be inserted by the editor) Abstract Understanding human instructions and accomplishing Vision-Language Navigation tasks in unknown environments is essential for robots. However, existing modular approaches heavily rely on the quality of training data and often exhibit poor generalization. Vision-Language Model based methods, while demonstrating strong generalization capabilities, tend to perform unsatisfactorily when semantic cues are weak. To address these issues, this paper proposes SONAR, an aggregated reasoning approach through a cross modal paradigm. The proposed method integrates a semantic map based target prediction module with a Vision-Language Model based value map module, enabling more robust navigation in unknown environments with varying levels of semantic cues, and effectively balancing generalization ability with scene adaptability. In terms of target localization, we propose a strategy that integrates multi-scale semantic maps with confidence maps, aiming to mitigate false detections of target objects. We conducted an evaluation of the SONAR within the Gazebo simulator, leveraging the most challenging Mat-null Jiankun Wang E-mail: wangjk@sustech.edu.cn Experimental results demonstrate that SONAR achieves a success rate of 38.4% and an SPL of 17.7%. Keywords Object Goal Navigation Vision-Language Model Aggregated Reasoning 1 Introduction In an unknown environment, for a robot to accurately understand human instructions and complete vision language navigation tasks, it needs to rely on limited visual and linguistic cues to develop efficient exploration strategies while achieving precise identification of target objects[1].

-- In this paper, we address stereo acoustic data fusion for marine robotics and propose a geometry-based method for projecting observed features from one sonar to another for a cross-modal stereo sonar setup that consists of both a forward-looking and a sidescan sonar . Our acoustic geometry for sidescan and forward-looking sonar is inspired by the epipolar geometry for stereo cameras, and we leverage relative pose information to project where an observed feature in one sonar image will be found in the image of another sonar . Additionally, we analyze how both the feature location relative to the sonar and the relative pose between the two sonars impact the projection. From simulated results, we identify desirable stereo configurations for applications in field robotics like feature correspondence and recovery of the 3D information of the feature. Field robotic applications, such as localization and mapping, in underwater environments face significant challenges due to the complex and dynamic nature of the marine domain.

Accurate relative state observation of Unmanned Underwater Vehicles (UUVs) for tracking uncooperative targets remains a significant challenge due to the absence of GPS, complex underwater dynamics, and sensor limitations. Existing localization approaches rely on either global positioning infrastructure or multi-UUV collaboration, both of which are impractical for a single UUV operating in large or unknown environments. To address this, we propose a novel persistent relative 6D state estimation framework that enables a single UUV to estimate its relative motion to a non-cooperative target using only successive noisy range measurements from two monostatic sonar sensors. Our key contribution is an observability-enhanced attitude control strategy, which optimally adjusts the UUV's orientation to improve the observability of relative state estimation using a Kalman filter, effectively mitigating the impact of sensor noise and drift accumulation. Additionally, we introduce a rigorously proven Lyapunov-based tracking control strategy that guarantees long-term stability by ensuring that the UUV maintains an optimal measurement range, preventing localization errors from diverging over time. Through theoretical analysis and simulations, we demonstrate that our method significantly improves 6D relative state estimation accuracy and robustness compared to conventional approaches. This work provides a scalable, infrastructure-free solution for UUVs tracking uncooperative targets underwater.