arXiv:2606.14556v1 Announce Type: new Abstract: Remanufacturing large white goods is essential for a circular economy, yet visual quality assessment remains a manual bottleneck for training and pricing. Conventional detection methods require extensive annotation and struggle with small defects in high-resolution multi-view data. We present a multi-view framework based on Deformable-DETR for automated quality scoring that aggregates information across redundant views to extract fine-grained features. To enhance robustness with limited labels, we employ self-supervised pretraining followed by supervised fine-tuning on expert-annotated scores. Additionally, a linear projection over frozen feature maps identifies regions of interest to explain model decisions. Evaluated on an industrial multi-view dataset, our approach delivers precise quality assessments while reducing reliance on manual annotation and per-part customization, enabling scalable and transparent inspection for remanufacturing lines.
Science Journals
arXiv:2606.14561v1 Announce Type: new Abstract: Robotics manipulation research increasingly focuses on two-finger parallel grippers for their effectiveness, affordability, and ease of teleoperation. Grippers are nonetheless limited by their form factor, often requiring bimanual setups even for simple reorientation tasks. Anthropomorphic hands are a more natural platform for dexterous robot learning -- closer to the human hand, and capable of learning from human video -- yet they remain hard to use in learning research: even where open and accessible hand hardware exists, the software for control, simulation, teleoperation, and retargeting is scattered in one-off code bases, and largely disconnected from the robot-learning ecosystem. In this work, we introduce the \orca~learning stack, an open-source research stack for dexterity as a first-class robot learning domain. Our \orca~stack unifies low-level control, simulation, teleoperation from a range of consumer platforms, and hand retargeting, behind a single interface, and integrates natively with popular robot-learning frameworks such as \lerobot, so dexterous hand researchers can leverage the same data, training, and evaluation pipelines used for non-dexterous robot learning. We demonstrate a complete end-to-end workflow, collecting expert demonstrations of an in-hand reorientation task by teleoperation with a consumer-grade VR headset, training an autonomous policy with \lerobot, and evaluating the learned policy in a fully reproducible and observable setup. We open-source the entire stack as a shared, reproducible foundation for dexterous-manipulation research.
arXiv:2606.14574v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as planners for autonomous agents in household environments. While existing benchmarks evaluate whether LLM-generated plans execute successfully, they overlook a critical type of failure: latent failures. Unlike immediate failures that trigger instant feedback at execution time and enable timely correction, latent failures do not immediately halt plan execution but silently compromise goal achievement. In severe cases, they cause irreversible harm. To address this gap, we introduce SIMMER, a benchmark for evaluating latent failures in LLM planning through a human-curated symbolic world model grounded in the kitchen domain. SIMMER defines a world model comprising 77 actions, 262 unique objects, and approximately 46,800 possible interactions that are semantically realistic, derived from real-world cooking scripts. It then leverages a state machine executor that validates plans against the world model and detects immediate precondition violations, latent hazards, and irreversible failures. Experiments across six LLMs show that even frontier models achieve at most 17% error-free plans. Moreover, up to 56% of plans contain latent failures, the majority of which lead to irreversible consequences. We further demonstrate that explicit state reasoning via counterfactual foresight simulation can reduce latent failures by up to 72% and irreversible cases by up to 75%, suggesting a promising direction for more robust LLM planners.
arXiv:2606.14577v1 Announce Type: new Abstract: Dual-species atom interferometry in space promises precise tests of the Universality of Free Fall (UFF), with a sensitivity that grows quadratically with the extended interrogation time accessible in weightlessness. These tests demand exquisite control over the expansion energies of both condensed sources as well as over their differential center-of-mass dynamics. We propose a trap-quenched collimation technique featuring in-trap excitations of collective modes compatible with state-of-the-art atom-chip setups. Using NASA's Cold Atom Laboratory aboard the International Space Station, we demonstrate it on a single-species $^{87}$Rb condensate. By controlling the center-of-mass release dynamics we observe free expansion times up to 700 ms and measure a two-dimensional expansion energy of $k_B \cdot 78\pm 9 \;\mathrm{pK}$ in the imaging plane. A detailed model of the magnetically-induced dynamics indicates that this corresponds to a two-dimensional expansion energy of about $k_B \cdot 15^{+12}_{-5}\; \mathrm{pK}$ along two of the condensate's eigenaxes. Finally, we theoretically study this trap-quenched collimation scheme for a $^{41}$K-$^{87}$Rb mixture, predicting a simultaneous collimation that meets the expansion energy requirements for a state-of-the-art UFF test at the $10^{-15}$ accuracy level.
arXiv:2506.17255v2 Announce Type: replace Abstract: Large language models (LLMs) require larger GPU memory size these days, necessitating efficient and extreme weight compression methods. Existing compression methods are either theoretically limited by 1 bit per weight or face severe performance degradation and inefficiency. To deploy LLMs in resource-constrained scenarios, we introduce UltraSketchLLM, compressing LLMs with data sketch. It reduces peak GPU memory footprint with a high compression rate down to 0.5 bit per weight. Combined with hardware-friendly implementation, UltraSketchLLM keeps tolerable performance degradation and extremely low latency overhead with 14.9x speedup compared to naive sketch solution.
arXiv:2606.14578v1 Announce Type: new Abstract: AI-driven computer vision applications require a profound database to ensure predictable behaviors and performance. Such predictable behaviors are especially important for industrial applications in gaining trust from users. However, such a database is not readily available in industrial applications, and its acquisition is not trivial either. Active learning methods can be applied to ramp up data within a project deployment to iteratively increase the database, and thus the application predictability. Unfortunately, we observe that this often leads to a loss of user trust in the application, which is difficult to regain once lost. This leads to a "chicken-and-egg" dilemma in which neither the database nor the application is developed. In this work, we review state-of-the-art methods and approaches to further boost the database the initial active data ramp-up phase. Here, we focus on recent advancements in GenAI-based data generation and augmentation methods and review their adaptability on an industrial computer vision classification use case. Although we observe a potential for automatic data ramp-up, we also see a domain miss match in between the source (training environment) and target (industrial use-case) - regarding context defined in natural language and object characteristics.
arXiv:2606.14580v1 Announce Type: new Abstract: Identifying persuasive rhetorical cues is critical across domains, from detecting information manipulation and improving AI safety to advancing public health communication. We propose Persuasion Index (PI), a taxonomy of 15 dimensions grounded in persuasion theories from psychology and communication, and one transparent implementation using 55 sub-features built from lexicons and rule-based detectors. The taxonomy is modular: individual detectors can be replaced while preserving the theoretical structure. By evaluating PI on four public datasets varying in domain, style, and outcome measures, we show that PI provides a shared feature space for interpreting rhetorical patterns associated with persuasion-related outcomes. Linear models show that PI features carry meaningful predictive signal while remaining computationally lightweight. Dimension-level analyses reveal recurring associations between PI dimensions and persuasion outcomes across datasets, while also highlighting topic- and stance-specific variation. We release PI as an open-source package and web interface for principled and auditable analysis of human and AI-mediated communication.
arXiv:2606.14582v1 Announce Type: new Abstract: Efficient route optimization play a vital role in ensuring both safety and punctuality in railway operations. It is very crucial particularly in heterogeneous multi-gauge railway networks with varying train speed, stopping pattern, infrastructure compatibility constraints increase coordination complexity. In single-track systems these challenges are further intensify due to all trains to share the same track and requires frequent track switching.Stochastic disruptions events including blocked tracks, blocked trains, engine failure and speed slowdowns introduces additional unpredictability in operations and deviate the timetable. However, existing studies predominantly focuses on high-level timetabling, omitting operational details such as track switching coordination. As a result leaving decision to human operators, increasing safety risks into railway operations. This study proposes a framework based on temporal planning for dynamic route optimization and disruption management in heterogeneous railway systems. The framework formulates railway operations as a temporal planning problem using PDDL 2.1 with explicitly modeling gauge compatibility constraints and diverse disruption scenarios. It generates conflict-free timestamped operational plans specifying both optimized schedules and executable action sequences. To evaluate the proposed framework, we developed a benchmark problem set with 200 instances using up to 1,000 track points and 120 trains. Two state-of-the-art temporal planners and a plan validator were employed to assessed the framework. The experimental results demonstrate that the framework effectively generates temporal operational plans for heterogeneous railway systems and handles multi-gauge constraints, disruptions, and reduces dependence on manual decision making.
arXiv:2606.14586v1 Announce Type: new Abstract: Current representation learning paradigms force a fundamental compromise: self-supervised methods scale to massive datasets but yield opaque features, whereas interpretable models remain bottlenecked by the need for dense human annotation. We introduce Self-Supervised Concept discOvery via Preference lEarning (\model), a label-free framework that resolves this dilemma. Instead of treating Vision-Large-Language Models (VLLMs) as static feature extractors, \model leverages them as active participants in a self-supervised preference optimization loop. By autonomously hypothesizing, validating, and reinforcing candidate visual attributes directly from raw imagery, our framework discovers novel, structured concepts without a single label. Extensive experiments across natural, medical, and physics domains demonstrate that \model successfully extracts domain-specific concepts where standard VLLMs often fail to generate. By amortizing concept discovery directly into the VLLM backbone through our self-supervised preference objective -- rather than relying on static generation and disjoint filtering -- we achieve up to a 24-point absolute improvement in downstream top-1 classification accuracy on unseen data. Our work suggest that interpretability can emerge through a model's autonomous interaction with incidental visual structures, without any human supervision.
arXiv:2606.14591v1 Announce Type: new Abstract: Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning. A practical way to improve such capabilities is post-training, whose effectiveness critically depends on the quality and diversity of training data. However, existing audio-language datasets often contain substantial redundancy, where many samples are highly similar in acoustic content and thus provide overlapping supervisory signals. Such redundancy not only increases annotation cost, but also limits corpus diversity and reduces the effectiveness of post-training. To address this issue, we propose a redundancy-aware data construction pipeline for building reasoning-oriented supervision for LALMs. Specifically, we first perform acoustic similarity-based deduplication across raw audio datasets to improve corpus diversity. We then integrate existing audio captions and question-answer pairs into a unified multiple-choice format. Based on these unified annotations, we leverage Qwen3-30B to generate chain-of-thought (CoT) rationales for reasoning-oriented supervision. Based on this pipeline, we construct AudioDER, a reasoning-oriented post-training dataset containing approximately 191k samples spanning sound, speech, and music. Each sample consists of an audio clip, a multiple-choice question, four answer candidates, an audio caption, and a CoT rationale. Extensive experiments show that post-training on AudioDER consistently improves the performance of Qwen2-Audio-7B-Instruct on multiple audio reasoning benchmarks, including MMAU-mini, MMSU, and MMAR. We hope AudioDER can serve as a valuable resource for advancing audio reasoning research and the development of more capable LALMs.
arXiv:2606.14594v1 Announce Type: new Abstract: AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI contributors strain those assumptions, and the 2025-2026 record of agent-driven incidents, AI-generated nuisance volume, and platform-level shutdowns shows that the gap is operationally consequential. Several open-source organisations have responded with contribution policies, but the result is fragmented, and its alignment with emerging AI governance frameworks (EU AI Act, NIST AI RMF with the UC Berkeley Agentic AI Profile, ISO/IEC 42001 and 23894) is unmapped at the contribution level. We compare policies across six organisations (SymPy, LLVM, matplotlib, OpenInfra, the Apache Software Foundation, and the Linux Foundation) using Most-Similar Systems Design with indicator-based coding and process tracing for SymPy and LLVM. From this we derive a six-dimensional taxonomy (disclosure, responsibility, human oversight, licensing, enforcement, maintainer workload), an ordinal Policy Maturity Score, and a mapping of documented agent incidents onto the dimensions each policy fails to govern. Aligning the dimensions with the regulatory frameworks above identifies overlapping gaps neither side currently closes, and we close by sketching the shape of a harmonised tiered framework and the empirical evaluation needed to calibrate it.
arXiv:2606.14595v1 Announce Type: new Abstract: Mid-infrared (mid-IR) spectroscopy enables label-free molecular detection and is widely employed in biomedical, environmental, and chemical sensing; however, its broader deployment remains limited by bulky instrumentation and insufficient analytical sensitivity. Photonic metasurfaces supporting strong mid-IR resonances provide a promising route toward compact on-chip spectrometers and enhanced molecular sensing, yet their practical implementation is often constrained by limited spectral coverage and fabrication complexity. Here, we present a scalable, resist-free stencil lithography approach for fabricating arrays of Ge pillar metasurfaces on CaF2 substrates that support polarization-insensitive Mie resonances dominated by electric dipole modes. By varying the geometric design parameters during fabrication, we engineered metasurface arrays with discrete resonances spanning the 950-1700 cm^-1 molecular fingerprint region. Furthermore, leveraging the thermo-optic response of Ge, we achieved dynamic tuning of these discrete resonances, demonstrating continuous and reversible resonance shifts of approximately 36 cm^-1 per metasurface over 300-500 K, corresponding to a tuning rate of 0.18 cm^-1/K. The thermally induced spectral sweeping enables multiplexed detection of poly(methyl methacrylate) vibrational modes and continuous reconstruction of its absorbance spectrum across 1100-1215 cm^-1. These results establish a scalable dielectric metasurface platform with spectrally reconfigurable mid - IR modes for molecular sensing across the fingerprint region and compact infrared sensor technologies.
arXiv:2606.14597v1 Announce Type: new Abstract: Transformer-based neural operators have shown remarkable performance for approximating solution operators of partial differential equations on complex geometries. However, existing approaches implicitly assume a fixed domain size, which limits their ability to generalize at inference. In this work, we investigate domain extension, namely zero-shot inference on spatial domains that are significantly larger than those encountered during training. We argue that this setting fundamentally requires spatial locality and translation equivariance. We propose to implement this locality via a decomposable bias in the attention logits computation, enabling finely controllable locality while remaining fully decomposable into query-key inner products and directly compatible with optimized attention kernels. Combined with rotary positional embeddings, it enables expressive embeddings with controllable spatial support without altering the transformer architecture. We empirically show that our approach substantially improves zero-shot generalization to larger domains across two PDE benchmarks and a 3D industrial atmospheric flow application. Our code and datasets are available at https://github.com/cerea-daml/domain-extension.
arXiv:2606.13807v1 Announce Type: new Abstract: In this study, we present a novel time-stepping scheme for multiscale differential equations describing oscillatory systems with well-separated scales, where the scale separation is controlled by a small parameter $\epsilon$. The time-stepping method is related to a multi-modal WKB approximation and relies on a transformation of variables derived in this work. The analysis reveals that, in the transformed formulation, the leading-order oscillations are either eliminated or appear only at higher asymptotic order. The method is applied to ordinary differential equations, including the well-known van der Pol oscillator. We investigate the accuracy of the proposed method numerically for different parameter regimes, in particular for decreasing values of $\epsilon$, and study how the parameters of the numerical scheme must be adapted as $\epsilon$ is reduced. In the presented numerical tests, the computational cost remains bounded as $\epsilon$ is decreased.
arXiv:2606.14600v1 Announce Type: new Abstract: Online group chats are social spaces with local conversational norms that are rarely stated explicitly. The ability and willingness of LLM-based agents to recognize and adapt to these norms remains mostly unexplored. We introduce LoSoNA, a benchmark for local social norm adaptation in multi-party chat. Each scenario gives a subject model a curated group-chat transcript in which non-subject participants demonstrate a hidden local norm, followed by a final elicitor turn that forces a response revealing whether the subject has inferred that norm. We evaluate eight frontier and open-weight models under four prompting conditions that vary how explicitly the model is told to treat the prior conversation as evidence for how it should answer. Naive prompting remains limited for most models; explicit norm-aware prompting helps unevenly, with Gemini 3.1 Pro reaching $84.2\%$ and Claude Fable 5 reaching $81.6\%$, while several other models show small gains or regressions. LoSoNA contributes to recent calls for evaluating LLM social capabilities by testing whether models can infer local conversational norms from precedent and use them in a one-turn group-chat response.
arXiv:2606.14602v1 Announce Type: new Abstract: Socially assistive robots (SARs) are increasingly deployed in educational and information-sharing contexts, supported by advances in large language models that enable fluent real-time interaction. Despite the growing diversity of robot embodiments, it remains unclear whether a single robot appearance is appropriate across different interaction tasks or whether trust depends primarily on contextual factors. In this study, we examine how robot appearance and task type jointly influence trust in robots. Using a within-subjects video-based experiment (N = 81), participants evaluated three robots with distinct appearances while performing three educationally relevant tasks: teaching, procedural instruction, and personal-information discussion. Results from repeated-measures analyses show a strong main effect of task on trust, with participants reporting the highest trust during instructional guidance, moderate trust during teaching activities, and significantly lower trust when robots requested personal information. In contrast, robot appearance showed no significant main effect, and the interaction between appearance and task was marginal. These findings suggest that trust in human-robot interaction is shaped more strongly by task context than by physical embodiment alone. By focusing on future educators as end users, this work contributes empirical evidence toward task-aware robot deployment in educational environments and highlights the importance of aligning robot roles and behaviors with interaction goals rather than relying solely on anthropomorphic design.
arXiv:2606.14603v1 Announce Type: new Abstract: Agent-based modelling is gaining recognition as a powerful approach for simulating complex cellular pathways, owing to its ability to reproduce emergent biological behaviours without requiring extensive kinetic parameterisation. In this article, we present a GPU-accelerated agent-based simulator specifically designed to model and analyse signalling pathways involved in cancer progression, and to evaluate therapeutic interventions. Our approach leverages the computing capabilities of FLAME GPU 2, a GPU-accelerated agent-based modelling framework, to efficiently manage simulations involving millions of molecules interacting within a three-dimensional environment. Each molecule is represented as an autonomous agent with defined physical properties, capable of binding, releasing reaction products, migrating between compartments, and interacting based on spatial proximity. An intuitive graphical interface supports model construction, parameter setup, and real-time modification of treatment strategies. As the primary focus of this paper, we validate the simulator on the MAPK/ERK cascade affected by the BRAFV600E mutation, demonstrating that it accurately reproduces dose-response trends observed in clinical data and outperforms both deterministic models and our prior agent-based implementations. A second case study extends the approach to nuclear signalling by reproducing the dynamics of cFos expression and phosphorylation. This demonstrates the simulator's ability to capture compartmentalised regulation, reproducing transient mRNA responses and protein accumulation, including the effect of an unresolved negative transcriptional regulator. Together, these results show that GPU-accelerated ABM can faithfully replicate both drug response and emergent gene expression dynamics, providing a scalable and biologically grounded computational tool for supporting precision oncology.
Empowering Student Debugging in Parallel Programming with Execution Traces and Large Language Models
arXiv:2606.14607v1 Announce Type: new Abstract: Concurrent programming is a core component of Computer Science curricula, yet remains notoriously difficult for students to master due to its inherent complexity and the nondeterministic nature of concurrency bugs such as deadlocks and race conditions. In this work, we present ParaView, an educational tool designed to help students understand, debug, and correct concurrency issues in parallel programs written in C/C++. ParaView provides transparent execution recording and visualization to make parallel execution observable and comprehensible. We evaluated ParaView through a series of debugging and implementation tasks, with 17 students participating. Results showed a significant improvement in debugging and implementation successes compared to previous course iterations. A student survey confirmed that most participants found ParaView helpful. To further support learning outside the classroom, we explored using Large Language Models (LLMs) to analyze concurrency bugs and suggest fixes. While LLMs were highly effective in identifying bugs and explaining execution traces, the correctness of their bug fixes varied, especially for more complex synchronization patterns. Our findings suggest that recording-visualization tools like ParaView, complemented by artificial intelligence (AI), can improve teaching and learning of concurrent programming.
arXiv:2606.14610v1 Announce Type: new Abstract: We study the data-to-solution value map for quasistatic nonlinear elasticity in the linearized-kinematics regime, allowing both generalized loads and variable Dirichlet data. Under standard direct-method hypotheses, the negative minimum potential energy is finite and locally Lipschitz, convex in the load variable, and concave in the Dirichlet datum. Its supporting slopes, and its first variations at differentiability points, are the equilibrium displacement and the Dirichlet reaction. This convex--concave structure leads to a mechanics-preserving saddle minmax architecture in which displacement atoms generate load slopes, reaction atoms generate Dirichlet slopes, and the coupling coefficients are the corresponding trace-reaction pairings. Manufactured samples are produced by prescribing displacement--reaction pairs and computing the associated ambient data and exact value labels. The resulting architecture directly approximates the negative minimum-potential-energy value map and provides mechanical subgradient readouts. Immersed representations and cell-center quadrature make the construction implementable on background grids and geometry-rich domains. We prove uniform convergence on compact data sets with respect to atom enrichment and quadrature refinement, and illustrate the method on elementary examples.
arXiv:2606.14618v1 Announce Type: new Abstract: Machine learning (ML) and Artificial Intelligence (AI) components are increasingly embedded in software products, yet undergraduate software engineering (SE) curricula rarely provide systematic preparation for building, testing, deploying, and maintaining AI/ML-based software systems. This paper aims to provide evidence-based guidance for integrating AI/MLrelevant content into core SE education. We compile and define a structured inventory of topics relevant to SE practice in AI/MLbased software, then map these topics against required courses in a set of representative SE curricula to identify coverage gaps. To assess educational priorities and feasibility, we survey SE instructors on topic importance and integration constraints. Based on the crosswalk between topic definitions, curriculum coverage, and instructor prioritization, we derive a guideline that recommends where and how high-priority topics can be embedded within existing SE courses.
arXiv:2606.14623v1 Announce Type: new Abstract: Magnetic Navigation (MagNav) has emerged as a vital alternative Positioning, Navigation, and Timing (PNT) solution, leveraging Earth's magnetic field for robust navigation in GPS/GNSS-degraded or denied environments. Despite its potential, the successful deployment of MagNav is currently hindered by the lack of standardized, high-fidelity geomagnetic reference maps. Existing datasets, primarily designed for geological exploration or academic research, do not meet the distinct operational requirements of navigation systems regarding spatial resolution, error quantification, and global accessibility. This paper initiates a community-focused dialogue on future geophysical data requirements for MagNav, grounded in extensive real-world flight trials. We distinguish between two primary use cases with divergent data needs: Operational MagNav, which requires globally consistent, queryable, and uncertainty-aware datasets for field deployment, and MagNav R&D, which demands comprehensive access to raw survey data to foster innovation. We provide a prioritized set of recommendations for future data requirements, including the development of cohesive, merged datasets, the inclusion of localized 3D uncertainty estimates, and the expansion of the World Magnetic Model (WMM) core field model to spherical harmonic degree 13 to improve consistency. Finally, we emphasize the strategic necessity of designated test ranges to validate these requirements and ensure the operational robustness of MagNav infrastructure.
arXiv:2606.14626v1 Announce Type: new Abstract: The global use of artificial intelligence has increased interest in assessing the ability to generate culturally localized content, including stories. Cultural localization in stories often occurs through either templated localization -- the use of cultural markers (e.g., names, locations) in a generic narrative -- or holistic localization -- the variation of plots, values, and themes, in addition to cultural markers. We propose a method to measure the degree to which content was generated through templated localization. Specifically, we identify the lexical tokens that distinguish stories across nationalities and measure the similarity of the narratives that remain after removing them. In stories generated by five models on 125 topics for 193 nationalities, our method is able to detect that only a small subset (9-17%) of the vocabulary accounts for the variation across nationalities and that the narratives that remain after removing them contain repeated multi-word sequences, suggesting the presence of a shared culturally-agnostic narrative template. Finally, we characterize the cultural markers for their stereotypicality and offensiveness, finding that markers from 19 countries, mostly located in the Global South, are on average offensive.
arXiv:2606.14627v1 Announce Type: new Abstract: The tensor train (TT) model is widely used to approximate high-dimensional tensors, enabling efficient handling of data that may exceed available memory. TT helps address the curse of dimensionality in applications such as system identification and dynamic programming. In some applications, TT is known as a ``matrix product state" (MPS). This paper introduces algorithms that facilitate the summation, Hadamard (elementwise) product, and matrix--vector product of matrices and vectors (tensors) represented in the tensor train (TT) format. The last product is also known under the acronym MPO--MPS. The proposed algorithms achieve an improved tradeoff between computational efficiency and accuracy compared to state-of-the-art methods.
arXiv:2606.14631v1 Announce Type: new Abstract: Event-based saliency prediction has gained attention recently, as combining event cameras with saliency estimation can act as an upstream stage that naturally improves the efficiency of downstream eventbased perception at the edge. However, current approaches are either neuromorphic, underperforming on event-based saliency benchmarks, or too heavy for resource-constrained edge applications due to their reliance on transformers or 3D convolutions. Drawing inspiration from efficient convolutional modules, SED and aiming to exploit the temporal information in event data, we propose a lightweight network, trained through knowledge distillation, built on a Depthwise Spatio-Temporal Block (DSTconv) -- a factorization of the 3D depthwise separable convolution. Relative to its teacher, our model reduces the model size from 180 MB to 0.32 MB (562x) and the parameter count from 45M to 81k (554x), while matching or outperforming it on the N-DHF1K and N-UCF Sports datasets. Moreover, it generalizes strongly beyond its training distribution, transferring from synthetic to real event data where a model trained from scratch fails.
arXiv:2606.14639v1 Announce Type: new Abstract: Recent advances in speech generation have significantly improved the naturalness of synthetic speech, making spoofing detection increasingly challenging. A key limitation of current anti-spoofing systems is their limited robustness to unseen synthesis methods. In this work, we transform a self-supervised speech representation model into a Mixture-of-Experts (MoE) architecture to improve generalization. Feed-forward blocks in selected encoder layers are replaced by multiple expert networks controlled by a layer-wise gating mechanism, allowing experts to capture complementary acoustic patterns while preserving the representations learned during self-supervised pretraining. We further analyze the architectural choices affecting the performance of this MoE conversion and investigate the activation behavior of the experts. The proposed approach is evaluated on 14 spoofing datasets and reduces the macro EER from 5.46% to 4.81%, corresponding to 11.9% relative improvement over the baseline.