Marine biodiversity monitoring requires scalability and reliability across complex underwater environments to support conservation and invasive-species management. Yet existing detection solutions often exhibit a pronounced deployment gap, with performance degrading sharply when transferred to new sites. This work establishes the foundational detection layer for a multi-year invasive species monitoring initiative targeting Arctic and Atlantic marine ecosystems. We address this challenge by developing a Unified Information Pipeline that standardises heterogeneous datasets into a comparable information flow and evaluates a fixed, deployment-relevant detector under controlled cross-domain protocols. Across multiple domains, we find that structural factors, such as scene composition, object density, and contextual redundancy, explain cross-domain performance loss more strongly than visual degradation such as turbidity, with sparse scenes inducing a characteristic "Context Collapse" failure mode. We further validate operational feasibility by benchmarking inference on low-cost edge hardware, showing that runtime optimisation enables practical sampling rates for remote monitoring. The results shift emphasis from image enhancement toward structure-aware reliability, providing a democratised tool for consistent marine ecosystem assessment.

Frame sampling is a fundamental component in video understanding and video--language model pipelines, yet evaluating the quality of sampled frames remains challenging. Existing evaluation metrics primarily focus on perceptual quality or reconstruction fidelity, and are not designed to assess whether a set of sampled frames adequately captures informative and representative video content. We propose Spatio-Temporal Entropy Coverage (STEC), a simple and non-reference metric for evaluating the effectiveness of video frame sampling. STEC builds upon Spatio-Temporal Frame Entropy (STFE), which measures per-frame spatial information via entropy-based structural complexity, and evaluates sampled frames based on their temporal coverage and redundancy. By jointly modeling spatial information strength, temporal dispersion, and non-redundancy, STEC provides a principled and lightweight measure of sampling quality. Experiments on the MSR-VTT test-1k benchmark demonstrate that STEC clearly differentiates common sampling strategies, including random, uniform, and content-aware methods. We further show that STEC reveals robustness patterns across individual videos that are not captured by average performance alone, highlighting its practical value as a general-purpose evaluation tool for efficient video understanding. We emphasize that STEC is not designed to predict downstream task accuracy, but to provide a task-agnostic diagnostic signal for analyzing frame sampling behavior under constrained budgets.

Detecting anatomical landmarks in medical imaging is essential for diagnosis and intervention guidance. However, object detection models rely on costly bounding box annotations, limiting scalability. Weakly Semi-Supervised Object Detection (WSSOD) with point annotations proposes annotating each instance with a single point, minimizing annotation time while preserving localization signals. A Point-to-Box teacher model, trained on a small box-labeled subset, converts these point annotations into pseudo-box labels to train a student detector. Yet, medical imagery presents unique challenges, including overlapping anatomy, variable object sizes, and elusive structures, which hinder accurate bounding box inference. To overcome these challenges, we introduce DExTeR (DETR with Experts), a transformer-based Point-to-Box regressor tailored for medical imaging. Built upon Point-DETR, DExTeR encodes single-point annotations as object queries, refining feature extraction with the proposed class-guided deformable attention, which guides attention sampling using point coordinates and class labels to capture class-specific characteristics. To improve discrimination in complex structures, it introduces CLICK-MoE (CLass, Instance, and Common Knowledge Mixture of Experts), decoupling class and instance representations to reduce confusion among adjacent or overlapping instances. Finally, we implement a multi-point training strategy which promotes prediction consistency across different point placements, improving robustness to annotation variability. DExTeR achieves state-of-the-art performance across three datasets spanning different medical domains (endoscopy, chest X-rays, and endoscopic ultrasound) highlighting its potential to reduce annotation costs while maintaining high detection accuracy.

With the rapid advancement of generative AI, virtual try-on (VTON) systems are becoming increasingly common in e-commerce and digital entertainment. However, the growing realism of AI-generated try-on content raises pressing concerns about authenticity and responsible use. To address this, we present VTONGuard, a large-scale benchmark dataset containing over 775,000 real and synthetic try-on images. The dataset covers diverse real-world conditions, including variations in pose, background, and garment styles, and provides both authentic and manipulated examples. Based on this benchmark, we conduct a systematic evaluation of multiple detection paradigms under unified training and testing protocols. Our results reveal each method's strengths and weaknesses and highlight the persistent challenge of cross-paradigm generalization. To further advance detection, we design a multi-task framework that integrates auxiliary segmentation to enhance boundary-aware feature learning, achieving the best overall performance on VTONGuard. We expect this benchmark to enable fair comparisons, facilitate the development of more robust detection models, and promote the safe and responsible deployment of VTON technologies in practice.

As Embodied AI systems move from research prototypes to real world deployments, they tend to evolve rapidly while remaining reliable under workload changes and partial failures. In practice, many deployments are only partially decoupled: middleware moves messages, but shared context and feedback semantics are implicit, causing interface drift, cross-module interference, and brittle recovery at scale. We present ANCHOR, a modular framework that makes decoupling and robustness explicit system-level primitives. ANCHOR separates (i) Canonical Records, an evolvable contract for the standardized shared state, from (ii) a communication bus for many-to-many dissemination and feedback-oriented coordination, forming an inspectable end-to-end loop. We validate closed-loop feasibility on a de-identified workflow instantiation, characterize latency distributions under varying payload sizes and publish rates, and demonstrate automatic stream resumption after hard crashes and restarts even with shared-memory loss. Overall, ANCHOR turns ad-hoc integration glue into explicit contracts, enabling controlled degradation under load and self-healing recovery for scalable deployment of closed-loop AI systems.

White Matter Tract Segmentation is imperative for studying brain structural connectivity, neurological disorders and neurosurgery. This task remains complex, as tracts differ among themselves, across subjects and conditions, yet have similar 3D structure across hemispheres and subjects. To address these challenges, we propose TrackletGPT, a language-like GPT framework which reintroduces sequential information in tokens using tracklets. TrackletGPT generalises seamlessly across datasets, is fully automatic, and encodes granular sub-streamline segments, Tracklets, scaling and refining GPT models in Tractography Segmentation. Based on our experiments, TrackletGPT outperforms state-of-the-art methods on average DICE, Overlap and Overreach scores on TractoInferno and HCP datasets, even on inter-dataset experiments.

Joint audio-text models are widely used for music retrieval, yet they struggle with semantic phenomena such as negation. Negation is fundamental for distinguishing the absence (or presence) of musical elements (e.g., "with vocals" vs. "without vocals"), but current systems fail to represent this reliably. In this work, we investigate and mitigate this limitation by training CLAP models from scratch on the Million Song Dataset with LP-MusicCaps-MSD captions. We introduce negation through text augmentation and a dissimilarity-based contrastive loss, designed to explicitly separate original and negated captions in the joint embedding space. To evaluate progress, we propose two protocols that frame negation modeling as retrieval and binary classification tasks. Experiments demonstrate that both methods, individually and combined, improve negation handling while largely preserving retrieval performance.

Feature extraction from unstructured text is a critical step in many downstream classification pipelines, yet current approaches largely rely on hand-crafted prompts or fixed feature schemas. We formulate feature discovery as a dataset-level prompt optimization problem: given a labelled text corpus, the goal is to induce a global set of interpretable and discriminative feature definitions whose realizations optimize a downstream supervised learning objective. To this end, we propose a multi-agent prompt optimization framework in which language-model agents jointly propose feature definitions, extract feature values, and evaluate feature quality using dataset-level performance and interpretability feedback. Instruction prompts are iteratively refined based on this structured feedback, enabling optimization over prompts that induce shared feature sets rather than per-example predictions. This formulation departs from prior prompt optimization methods that rely on per-sample supervision and provides a principled mechanism for automatic feature discovery from unstructured text.

Automated clinical diagnosis remains a core challenge in medical AI, which usually requires models to integrate multi-modal data and reason across complex, case-specific contexts. Although recent methods have advanced medical report generation (MRG) and visual question answering (VQA) with medical vision-language models (VLMs), these methods, however, predominantly operate under a sample-isolated inference paradigm, as such processing cases independently without access to longitudinal electronic health records (EHRs) or structurally related patient examples. This paradigm limits reasoning to image-derived information alone, which ignores external complementary medical evidence for potentially more accurate diagnosis. To overcome this limitation, we propose \textbf{HyperWalker}, a \textit{Deep Diagnosis} framework that reformulates clinical reasoning via dynamic hypergraphs and test-time training. First, we construct a dynamic hypergraph, termed \textbf{iBrochure}, to model the structural heterogeneity of EHR data and implicit high-order associations among multimodal clinical information. Within this hypergraph, a reinforcement learning agent, \textbf{Walker}, navigates to and identifies optimal diagnostic paths. To ensure comprehensive coverage of diverse clinical characteristics in test samples, we incorporate a \textit{linger mechanism}, a multi-hop orthogonal retrieval strategy that iteratively selects clinically complementary neighborhood cases reflecting distinct clinical attributes. Experiments on MRG with MIMIC and medical VQA on EHRXQA demonstrate that HyperWalker achieves state-of-the-art performance. Code is available at: https://github.com/Bean-Young/HyperWalker

Large Language Models have demonstrated profound utility in the medical domain. However, their application to autonomous Electronic Health Records~(EHRs) navigation remains constrained by a reliance on curated inputs and simplified retrieval tasks. To bridge the gap between idealized experimental settings and realistic clinical environments, we present AgentEHR. This benchmark challenges agents to execute complex decision-making tasks, such as diagnosis and treatment planning, requiring long-range interactive reasoning directly within raw and high-noise databases. In tackling these tasks, we identify that existing summarization methods inevitably suffer from critical information loss and fractured reasoning continuity. To address this, we propose RetroSum, a novel framework that unifies a retrospective summarization mechanism with an evolving experience strategy. By dynamically re-evaluating interaction history, the retrospective mechanism prevents long-context information loss and ensures unbroken logical coherence. Additionally, the evolving strategy bridges the domain gap by retrieving accumulated experience from a memory bank. Extensive empirical evaluations demonstrate that RetroSum achieves performance gains of up to 29.16% over competitive baselines, while significantly decreasing total interaction errors by up to 92.3%.

Estimating 3D from 2D is one of the central tasks in computer vision. In this work, we consider the monocular setting, i.e. single-view input, for 3D human pose estimation (HPE). Here, the task is to predict a 3D point set of human skeletal joints from a single 2D input image. While by definition this is an ill-posed problem, recent work has presented methods that solve it with up to several-centimetre error. Typically, these methods employ a two-step approach, where the first step is to detect the 2D skeletal joints in the input image, followed by the step of 2D-to-3D lifting. We find that common lifting models fail when encountering a rotated input. We argue that learning a single human pose along with its in-plane rotations is considerably easier and more geometrically grounded than directly learning a point-to-point mapping. Furthermore, our intuition is that endowing the model with the notion of rotation equivariance without explicitly constraining its parameter space should lead to a more straightforward learning process than one with equivariance by design. Utilising the common HPE benchmarks, we confirm that the 2D rotation equivariance per se improves the model performance on human poses akin to rotations in the image plane, and can be efficiently and straightforwardly learned by augmentation, outperforming state-of-the-art equivariant-by-design methods.

Tractography plays a pivotal role in the non-invasive reconstruction of white matter fiber pathways, providing vital information on brain connectivity and supporting precise neurosurgical planning. Although traditional methods relied mainly on classical deterministic and probabilistic approaches, recent progress has benefited from supervised deep learning (DL) and deep reinforcement learning (DRL) to improve tract reconstruction. A persistent challenge in tractography is accurately reconstructing white matter tracts while minimizing spurious connections. To address this, we propose TractRLFusion, a novel GPT-based policy fusion framework that integrates multiple RL policies through a data-driven fusion strategy. Our method employs a two-stage training data selection process for effective policy fusion, followed by a multi-critic fine-tuning phase to enhance robustness and generalization. Experiments on HCP, ISMRM, and TractoInferno datasets demonstrate that TractRLFusion outperforms individual RL policies as well as state-of-the-art classical and DRL methods in accuracy and anatomical reliability.

Despite their widespread adoption in various domains, especially due to their powerful reasoning capabilities, Large Language Models (LLMs) are not the off-the-shelf choice to drive multi-objective optimization yet. Conventional strategies rank high in benchmarks due to their intrinsic capabilities to handle numerical inputs and careful modelling choices that balance exploration and Pareto-front exploitation, as well as handle multiple (conflicting) objectives. In this paper, we close this gap by leveraging LLMs as surrogate models and candidate samplers inside a structured hierarchical search strategy. By adaptively partitioning the input space into disjoint hyperrectangular regions and ranking them with a composite score function, we restrict the generative process of the LLM to specific, high-potential sub-spaces, hence making the problem easier to solve as the LLM doesn't have to reason about the global structure of the problem, but only locally instead. We show that under standard regularity assumptions, our algorithm generates candidate solutions that converge to the true Pareto set in Hausdorff distance. Empirically, it consistently outperforms the global LLM-based multi-objective optimizer and is on par with standard evolutionary and Bayesian optimization algorithm on synthetic and real-world benchmarks.

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures yet struggle with high-level semantic context. We argue that these paradigms are fundamentally complementary and can be integrated into a principled multi-task framework, further enhanced by dense spatial supervision. We introduce MTV, a multi-task visual pretraining framework that jointly optimizes a shared backbone across vision-language contrastive, self-supervised, and dense spatial objectives. To mitigate the need for manual annotations, we leverage high-capacity "expert" models -- such as Depth Anything V2 and OWLv2 -- to synthesize dense, structured pseudo-labels at scale. Beyond the framework, we provide a systematic investigation into the mechanics of multi-task visual learning, analyzing: (i) the marginal gain of each objective, (ii) task synergies versus interference, and (iii) scaling behavior across varying data and model scales. Our results demonstrate that MTV achieves "best-of-both-worlds" performance, significantly enhancing fine-grained spatial reasoning without compromising global semantic understanding. Our findings suggest that multi-task learning, fueled by high-quality pseudo-supervision, is a scalable path toward more general visual encoders.

Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked correct/incorrect. We present a principled extension of IRT-based adaptive testing to continuous bounded scores (ROUGE, BLEU, LLM-as-a-Judge) by replacing the Bernoulli response distribution with a heteroskedastic normal distribution. Building on this, we introduce an uncertainty aware ranker with adaptive stopping criteria that achieves reliable model ranking while testing as few items and as cheaply as possible. We validate our method on five benchmarks spanning n-gram-based, embedding-based, and LLM-as-judge metrics. Our method uses 2% of the items while improving ranking correlation by 0.12 τ over random sampling, with 95% accuracy on confident predictions.

Large Language Models are increasingly deployed as educational tools, yet existing benchmarks focus on narrow skills and lack grounding in learning sciences. We introduce OpenLearnLM Benchmark, a theory-grounded framework evaluating LLMs across three dimensions derived from educational assessment theory: Knowledge (curriculum-aligned content and pedagogical understanding), Skills (scenario-based competencies organized through a four-level center-role-scenario-subscenario hierarchy), and Attitude (alignment consistency and deception resistance). Our benchmark comprises 124K+ items spanning multiple subjects, educational roles, and difficulty levels based on Bloom's taxonomy. The Knowledge domain prioritizes authentic assessment items from established benchmarks, while the Attitude domain adapts Anthropic's Alignment Faking methodology to detect behavioral inconsistency under varying monitoring conditions. Evaluation of seven frontier models reveals distinct capability profiles: Claude-Opus-4.5 excels in practical skills despite lower content knowledge, while Grok-4.1-fast leads in knowledge but shows alignment concerns. Notably, no single model dominates all dimensions, validating the necessity of multi-axis evaluation. OpenLearnLM provides an open, comprehensive framework for advancing LLM readiness in authentic educational contexts.

Personalized digital health support requires long-horizon, cross-dimensional reasoning over heterogeneous lifestyle signals, and recent advances in mobile sensing and large language models (LLMs) make such support increasingly feasible. However, the capabilities of current LLMs in this setting remain unclear due to the lack of systematic benchmarks. In this paper, we introduce LifeAgentBench, a large-scale QA benchmark for long-horizon, cross-dimensional, and multi-user lifestyle health reasoning, containing 22,573 questions spanning from basic retrieval to complex reasoning. We release an extensible benchmark construction pipeline and a standardized evaluation protocol to enable reliable and scalable assessment of LLM-based health assistants. We then systematically evaluate 11 leading LLMs on LifeAgentBench and identify key bottlenecks in long-horizon aggregation and cross-dimensional reasoning. Motivated by these findings, we propose LifeAgent as a strong baseline agent for health assistant that integrates multi-step evidence retrieval with deterministic aggregation, achieving significant improvements compared with two widely used baselines. Case studies further demonstrate its potential in realistic daily-life scenarios. The benchmark is publicly available at https://anonymous.4open.science/r/LifeAgentBench-CE7B.

Science demonstrations are important for effective STEM education, yet teachers face challenges in conducting them safely and consistently across multiple occasions, where robotics can be helpful. However, current Vision-Language-Action (VLA) models require substantial computational resources and sacrifice language generation capabilities to maximize efficiency, making them unsuitable for resource-constrained educational settings that require interpretable, explanation-generating systems. We present \textit{Pedagogical VLA Framework}, a framework that applies pedagogical alignment to lightweight VLA models through four components: text healing to restore language generation capabilities, large language model (LLM) distillation to transfer pedagogical knowledge, safety training for educational environments, and pedagogical evaluation adjusted to science education contexts. We evaluate Pedagogical VLA Framework across five science demonstrations spanning physics, chemistry, biology, and earth science, using an evaluation framework developed in collaboration with science education experts. Our evaluation assesses both task performance (success rate, protocol compliance, efficiency, safety) and pedagogical quality through teacher surveys and LLM-as-Judge assessment. We additionally provide qualitative analysis of generated texts. Experimental results demonstrate that Pedagogical VLA Framework achieves comparable task performance to baseline models while producing contextually appropriate educational explanations.

Class-Agnostic object Counting (CAC) involves counting instances of objects from arbitrary classes within an image. Due to its practical importance, CAC has received increasing attention in recent years. Most existing methods assume a single object class per image, rely on extensive training of large deep learning models and address the problem by incorporating additional information, such as visual exemplars or text prompts. In this paper, we present OCCAM, the first training-free approach to CAC that operates without the need of any supplementary information. Moreover, our approach addresses the multi-class variant of the problem, as it is capable of counting the object instances in each and every class among arbitrary object classes within an image. We leverage Segment Anything Model 2 (SAM2), a foundation model, and a custom threshold-based variant of the First Integer Neighbor Clustering Hierarchy (FINCH) algorithm to achieve competitive performance on widely used benchmark datasets, FSC-147 and CARPK. We propose a synthetic multi-class dataset and F1 score as a more suitable evaluation metric. The code for our method and the proposed synthetic dataset will be made publicly available at https://mikespanak.github.io/OCCAM_counter.

Linear discriminant analysis improves class separability but struggles with non-linearly separable data. To overcome this, we introduce Deep Discriminant Analysis (DDA), which directly optimizes the Fisher criterion utilizing deep networks. To ensure stable training and avoid computational instabilities, we incorporate signed between-class variance, bound outputs with a sigmoid function, and convert multiplicative relationships into additive ones. We present two stable DDA loss functions and augment them with a probability loss, resulting in Probabilistic DDA (PDDA). PDDA effectively minimizes class overlap in output distributions, producing highly confident predictions with reduced within-class variance. When applied to wind blade segmentation, PDDA showcases notable advances in performance and consistency, critical for wind energy maintenance. To our knowledge, this is the first application of DDA to image segmentation.

Audio Deepfake Detection (ADD) aims to detect spoof speech from bonafide speech. Most prior studies assume that stronger correlations within or across acoustic and emotional features imply authenticity, and thus focus on enhancing or measuring such correlations. However, existing methods often treat acoustic and emotional features in isolation or rely on correlation metrics, which overlook subtle desynchronization between them and smooth out abrupt discontinuities. To address these issues, we propose EAI-ADD, which treats cross level emotion acoustic inconsistency as the primary detection signal. We first project emotional and acoustic representations into a comparable space. Then we progressively integrate frame level and utterance level emotion features with acoustic features to capture cross level emotion acoustic inconsistencies across different temporal granularities. Experimental results on the ASVspoof 2019LA and 2021LA datasets demonstrate that the proposed EAI-ADD outperforms baselines, providing a more effective solution for audio anti spoofing detection.

This paper introduces Virtual Urbanism (VU), a multimodal AI-driven analytical framework for quantifying urban identity through the medium of synthetic urban replicas. The framework aims to advance computationally tractable urban identity metrics. To demonstrate feasibility, the pilot study Virtual Urbanism and Tokyo Microcosms is presented. A pipeline integrating Stable Diffusion and LoRA models was used to produce synthetic replicas of nine Tokyo areas rendered as dynamic synthetic urban sequences, excluding existing orientation markers to elicit core identity-forming elements. Human-evaluation experiments (I) assessed perceptual legitimacy of replicas; (II) quantified area-level identity; (III) derived core identity-forming elements. Results showed a mean identification accuracy of ~81%, confirming the validity of the replicas. Urban Identity Level (UIL) metric enabled assessment of identity levels across areas, while semantic analysis revealed culturally embedded typologies as core identity-forming elements, positioning VU as a viable framework for AI-augmented urban analysis, outlining a path toward automated, multi-parameter identity metrics.

Fluid turn-taking remains a key challenge in human-robot interaction. Self-supervised speech representations (S3Rs) have driven many advances, but it remains unclear whether S3R-based turn-taking models rely on prosodic cues, lexical cues or both. We introduce a vocoder-based approach to control prosody and lexical cues in speech more cleanly than prior work. This allows us to probe the voice-activity projection model, an S3R-based turn-taking model. We find that prediction on prosody-matched, unintelligible noise is similar to accuracy on clean speech. This reveals both prosodic and lexical cues support turn-taking, but either can be used in isolation. Hence, future models may only require prosody, providing privacy and potential performance benefits. When either prosodic or lexical information is disrupted, the model exploits the other without further training, indicating they are encoded in S3Rs with limited interdependence. Results are consistent in CPC-based and wav2vec2.0 S3Rs. We discuss our findings and highlight a number of directions for future work. All code is available to support future research.

Suboptimal color representation often hinders accurate image segmentation, yet many modern algorithms neglect this critical preprocessing step. This work presents a novel multidimensional nonlinear discriminant analysis algorithm, Colorspace Discriminant Analysis (CSDA), for improved segmentation. Extending Linear Discriminant Analysis into a deep learning context, CSDA customizes color representation by maximizing multidimensional signed inter-class separability while minimizing intra-class variability through a generalized discriminative loss. To ensure stable training, we introduce three alternative losses that enable end-to-end optimization of both the discriminative colorspace and segmentation process. Experiments on wind turbine blade data demonstrate significant accuracy gains, emphasizing the importance of tailored preprocessing in domain-specific segmentation.

LLM post-training has primarily relied on large text corpora and human feedback, without capturing the structure of domain knowledge. This has caused models to struggle dealing with complex reasoning tasks, especially for high-stakes professional domains. In Law, reasoning requires deep understanding of the relations between various legal concepts, a key component missing in current LLM post-training. In this paper, we propose a knowledge graph (KG)-assisted approach for enhancing LLMs' reasoning capability in Legal that is generalizable to other high-stakes domains. We model key legal concepts by following the \textbf{IRAC} (Issue, Rule, Analysis and Conclusion) framework, and construct a KG with 12K legal cases. We then produce training data using our IRAC KG, and conduct both Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) with three state-of-the-art (SOTA) LLMs (30B, 49B and 70B), varying architecture and base model family. Our post-trained models obtained better average performance on 4/5 diverse legal benchmarks (14 tasks) than baselines. In particular, our 70B DPO model achieved the best score on 4/6 reasoning tasks, among baselines and a 141B SOTA legal LLM, demonstrating the effectiveness of our KG for enhancing LLMs' legal reasoning capability.

Drones operating in human-occupied spaces suffer from insufficient communication mechanisms that create uncertainty about their intentions. We present HoverAI, an embodied aerial agent that integrates drone mobility, infrastructure-independent visual projection, and real-time conversational AI into a unified platform. Equipped with a MEMS laser projector, onboard semi-rigid screen, and RGB camera, HoverAI perceives users through vision and voice, responding via lip-synced avatars that adapt appearance to user demographics. The system employs a multimodal pipeline combining VAD, ASR (Whisper), LLM-based intent classification, RAG for dialogue, face analysis for personalization, and voice synthesis (XTTS v2). Evaluation demonstrates high accuracy in command recognition (F1: 0.90), demographic estimation (gender F1: 0.89, age MAE: 5.14 years), and speech transcription (WER: 0.181). By uniting aerial robotics with adaptive conversational AI and self-contained visual output, HoverAI introduces a new class of spatially-aware, socially responsive embodied agents for applications in guidance, assistance, and human-centered interaction.

Composed Video Retrieval (CoVR) aims to retrieve a video based on a query video and a modifying text. Current CoVR methods fail to fully exploit modern Vision-Language Models (VLMs), either using outdated architectures or requiring computationally expensive fine-tuning and slow caption generation. We introduce PREGEN (PRE GENeration extraction), an efficient and powerful CoVR framework that overcomes these limitations. Our approach uniquely pairs a frozen, pre-trained VLM with a lightweight encoding model, eliminating the need for any VLM fine-tuning. We feed the query video and modifying text into the VLM and extract the hidden state of the final token from each layer. A simple encoder is then trained on these pooled representations, creating a semantically rich and compact embedding for retrieval. PREGEN significantly advances the state of the art, surpassing all prior methods on standard CoVR benchmarks with substantial gains in Recall@1 of +27.23 and +69.59. Our method demonstrates robustness across different VLM backbones and exhibits strong zero-shot generalization to more complex textual modifications, highlighting its effectiveness and semantic capabilities.

In this paper, we propose an ETA model (Estimated Time of Arrival) that leverages an attention mechanism over historical road speed patterns. As autonomous driving and intelligent transportation systems become increasingly prevalent, the need for accurate and reliable ETA estimation has grown, playing a vital role in navigation, mobility planning, and traffic management. However, predicting ETA remains a challenging task due to the dynamic and complex nature of traffic flow. Traditional methods often combine real-time and historical traffic data in simplistic ways, or rely on complex rule-based computations. While recent deep learning models have shown potential, they often require high computational costs and do not effectively capture the spatio-temporal patterns crucial for ETA prediction. ETA prediction inherently involves spatio-temporal causality, and our proposed model addresses this by leveraging attention mechanisms to extract and utilize temporal features accumulated at each spatio-temporal point along a route. This architecture enables efficient and accurate ETA estimation while keeping the model lightweight and scalable. We validate our approach using real-world driving datasets and demonstrate that our approach outperforms existing baselines by effectively integrating road characteristics, real-time traffic conditions, and historical speed patterns in a task-aware manner.

Geometric mechanics provides valuable insights into how biological and robotic systems use changes in shape to move by mechanically interacting with their environment. In high-friction environments it provides that the entire interaction is captured by the ``motility map''. Here we compare methods for learning the motility map from motion tracking data of a physical robot created specifically to test these methods by having under-actuated degrees of freedom and a hard to model interaction with its substrate. We compared four modeling approaches in terms of their ability to predict body velocity from shape change within the same gait, across gaits, and across speeds. Our results show a trade-off between simpler methods which are superior on small training datasets, and more sophisticated methods, which are superior when more training data is available.

Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generative models, and reliable recurrent networks. Despite significant advancements, existing implementations remain fragmented, limited, and computationally demanding. To address these issues, we introduce Orthogonium , a unified, efficient, and comprehensive PyTorch library providing orthogonal and 1-Lipschitz layers. Orthogonium provides access to standard convolution features-including support for strides, dilation, grouping, and transposed-while maintaining strict mathematical guarantees. Its optimized implementations reduce overhead on large scale benchmarks such as ImageNet. Moreover, rigorous testing within the library has uncovered critical errors in existing implementations, emphasizing the importance of standardized and reliable tools. Orthogonium thus significantly lowers adoption barriers, enabling scalable experimentation and integration across diverse applications requiring orthogonality and robust Lipschitz constraints. Orthogonium is available at https://github.com/deel-ai/orthogonium.