We present FHAvatar, a novel framework for reconstructing 3D Gaussian avatars with composable face and hair components from an arbitrary number of views. Unlike previous approaches that couple facial and hair representations within a unified modeling process, we explicitly decouple two components in texture space by representing the face with planar Gaussians and the hair with strand-based Gaussians. To overcome the limitations of existing methods that rely on dense multi-view captures or costly per-identity optimization, we propose an aggregated transformer backbone to learn geometry-aware cross-view priors and head-hair structural coherence from multi-view datasets, enabling effective and efficient feature extraction and fusion from few casual captures. Extensive quantitative and qualitative experiments demonstrate that FHAvatar achieves state-of-the-art reconstruction quality from only a few observations of new identities within minutes, while supporting real-time animation, convenient hairstyle transfer, and stylized editing, broadening the accessibility and applicability of digital avatar creation.

Computer-aided segmentation of brain tumors from MRI data is of crucial significance to clinical decision-making in diagnosis, treatment planning, and follow-up disease monitoring. Gliomas, owing to their high malignancy and heterogeneity, represent a very challenging task for accurate and reliable segmentation into intra-tumoral sub-regions. Manual segmentation is typically time-consuming and not reliable, which justifies the need for robust automated techniques.This research resolves this problem by leveraging the BraTS 2020 dataset, where we have labeled MRI scans of glioma patients with four significant classes: background/healthy tissue, necrotic/non-enhancing core, edema, and enhancing tumor. In this work, we present a new segmentation technique based on a U-Net model augmented with executed attention gates to focus on the most significant regions of images. To counter class imbalance, we employ manually designed loss functions like Dice Loss and Categorical Dice Loss, in conjunction with standard categorical cross-entropy. Other evaluation metrics, like sensitivity and specificity, were used to measure discriminability of the model between tumor classes. Besides, we introduce Grad-CAM-based explainable AI to enable visualizing attention regions and improve model interpretability, together with a smooth heatmap generation technique through Gaussian filtering. Our approach achieved superior performance with accuracy of 0.9919, Dice coefficient of 0.9901, mean IoU of 0.9873, sensitivity of 0.9908, and specificity of 0.9974. This study demonstrates that the use of attention mechanisms, personalized loss functions, and explainable AI significantly improves highly complex tumor structure segmentation precision in MRI scans, providing a reliable and explainable method for clinical applications.

Material awareness can improve robotic navigation and interaction, particularly in conditions where cameras and LiDAR degrade. We present a lightweight mmWave radar material classification pipeline designed for ultra-low-power edge devices (TI IWRL6432), using compact range-bin intensity descriptors and a Multilayer Perceptron (MLP) for real-time inference. While the classifier reaches a macro-F1 of 94.2\% under the nominal training geometry, we observe a pronounced performance drop under realistic geometry shifts, including sensor height changes and small tilt angles. These perturbations induce systematic intensity scaling and angle-dependent radar cross section (RCS) effects, pushing features out of distribution and reducing macro-F1 to around 68.5\%. We analyze these failure modes and outline practical directions for improving robustness with normalization, geometry augmentation, and motion-aware features.

Tendon-driven aerial continuum manipulators (TD-ACMs) combine the maneuverability of uncrewed aerial vehicles (UAVs) with the compliance of lightweight continuum robots (CRs). Existing coupled dynamic modeling approaches for TD-ACMs incur high computational costs and do not explicitly account for aerial platform underactuation. To address these limitations, this paper presents a generalized dynamic formulation of a coupled TD-ACM with an underactuated base. The proposed approach integrates a strain-parameterized Cosserat rod model with a rigid-body model of the UAV into a unified Lagrangian ordinary differential equation (ODE) framework on $\mathrm{SE}(3)$, thereby eliminating computationally intensive symbolic derivations. Building upon the developed model, a robust dual-camera image-based visual servoing (IBVS) scheme is introduced. The proposed controller mitigates the field-of-view (FoV) limitations of conventional IBVS, compensates for attitude-induced image motion caused by UAV lateral dynamics, and incorporates a low-level adaptive controller to address modeling uncertainties with formal stability guarantees. Extensive simulations and experimental validation on a compact custom-built prototype demonstrate the effectiveness and robustness of the proposed framework in real-world scenarios.

Transformer-based video diffusion models rely on 3D attention over spatial and temporal tokens, which incurs quadratic time and memory complexity and makes end-to-end training for ultra-high-resolution videos prohibitively expensive. To overcome this bottleneck, we propose a pure image adaptation framework that upgrades a video Diffusion Transformer pre-trained at its native scale to synthesize higher-resolution videos. Unfortunately, naively fine-tuning with high-resolution images alone often introduces noticeable noise due to the image-video modality gap. To address this, we decouple the learning objective to separately handle modality alignment and spatial extrapolation. At the core of our approach is Relay LoRA, a two-stage adaptation strategy. In the first stage, the video diffusion model is adapted to the image domain using low-resolution images to bridge the modality gap. In the second stage, the model is further adapted with high-resolution images to acquire spatial extrapolation capability. During inference, only the high-resolution adaptation is retained to preserve the video generation modality while enabling high-resolution video synthesis. To enhance fine-grained detail synthesis, we further propose a High-Frequency-Awareness-Training-Objective, which explicitly encourages the model to recover high-frequency components from degraded latent representations via a dedicated reconstruction loss. Extensive experiments demonstrate that our method produces ultra-high-resolution videos with rich visual details without requiring any video training data, even outperforming previous state-of-the-art models trained on high-resolution videos by 0.8 on the VBench benchmark. Code will be available at https://github.com/WillWu111/ViBe.

Temporal Relation Extraction (TRE) requires identifying how two events or temporal expressions are related in time. Existing attention-based models often highlight globally salient tokens but overlook the pair-specific cues that actually determine the temporal relation. We propose WISTERIA (Weak Implicit Signal-based Temporal Relation Extraction with Attention), a framework that examines whether the top-K attention components conditioned on each event pair truly encode interpretable evidence for temporal classification. Unlike prior works assuming explicit markers such as before, after, or when, WISTERIA considers signals as any lexical, syntactic, or morphological element implicitly expressing temporal order. By combining multi-head attention with pair-conditioned top-K pooling, the model isolates the most informative contextual tokens for each pair. We conduct extensive experiments on TimeBank-Dense, MATRES, TDDMan, and TDDAuto, including linguistic analyses of top-K tokens. Results show that WISTERIA achieves competitive accuracy and reveals pair-level rationales aligned with temporal linguistic cues, offering a localized and interpretable view of temporal reasoning.

Among the different possible strategies for evaluating the reliability of individual predictions of classifiers, robustness quantification stands out as a method that evaluates how much uncertainty a classifier could cope with before changing its prediction. However, its applicability is more limited than some of its alternatives, since it requires the use of generative models and restricts the analyses either to specific model architectures or discrete features. In this work, we propose a new robustness metric applicable to any probabilistic discriminative classifier and any type of features. We demonstrate that this new metric is capable of distinguishing between reliable and unreliable predictions, and use this observation to develop new strategies for dynamic classifier selection.

Large-scale Vision-Language Models (VLMs) such as CLIP learn powerful semantic representations but operate in Euclidean space, which fails to capture the inherent hierarchical structure of visual and linguistic concepts. Hyperbolic geometry, with its exponential volume growth, offers a principled alternative for embedding such hierarchies with low distortion. However, existing hyperbolic VLMs use entailment losses that are unstable: as parent embeddings contract toward the origin, their entailment cones widen toward a half-space, causing catastrophic cone collapse that destroys the intended hierarchy. Additionally, hierarchical evaluation of these models remains unreliable, being largely retrieval-based and correlation-based metrics and prone to taxonomy dependence and ambiguous negatives. To address these limitations, we propose an adaptive entailment loss paired with a norm regularizer that prevents cone collapse without heuristic aperture clipping. We further introduce an angle-based probabilistic entailment protocol (PEP) for evaluating hierarchical understanding, scored with AUC-ROC and Average Precision. This paper introduces a stronger hyperbolic VLM baseline ARGENT, Adaptive hieRarchical imaGe-tExt represeNTation. ARGENT improves the SOTA hyperbolic VLM by 0.7, 1.1, and 0.8 absolute points on image classification, text-to-image retrieval, and proposed hierarchical metrics, respectively.

Automated radiology report generation from 3D computed tomography (CT) volumes is challenging due to extreme sequence lengths, severe class imbalance, and the tendency of large language models (LLMs) to ignore visual tokens in favor of linguistic priors. We present Ker-VLJEPA-3B, a four-phase curriculum learning framework for free-text report generation from thoracic CT volumes. A phased training curriculum progressively adapts a Llama 3.2 3B decoder to ground its output in visual features from a frozen, self-supervised encoder. Our visual backbone (LeJEPA ViT-Large) is trained via self-supervised joint-embedding prediction on unlabeled CTs, without text supervision. Unlike contrastive models (CLIP, BiomedCLIP), this language-free backbone yields modality-pure representations. Vision-language alignment is deferred to the curriculum's bridge and generation phases. This modality-agnostic design can integrate any self-supervised encoder into an LLM without paired text during foundation training. Methodological innovations include: (1) zone-constrained cross-attention compressing slice embeddings into 32 spatially-grounded visual tokens; (2) PCA whitening of anisotropic LLM embeddings; (3) a positive-findings-only strategy eliminating posterior collapse; (4) warm bridge initialization transferring projection weights; and (5) selective cross-attention freezing with elastic weight consolidation to prevent catastrophic forgetting. Evaluated on the CT-RATE benchmark (2,984 validation volumes, 18 classes), Ker-VLJEPA-3B achieves a macro F1 of 0.429, surpassing the state-of-the-art (U-VLM, macro F1 = 0.414) by 3.6%, and reaching 0.448 (+8.2%) with threshold optimization. Ablation studies confirm 56.6% of generation quality derives from patient-specific visual content. Code and weights are available.

LLMs are deployed globally, yet produce responses biased towards cultures with abundant training data. Existing cultural localization approaches such as prompting or post-training alignment are black-box, hard to control, and do not reveal whether failures reflect missing knowledge or poor elicitation. In this paper, we address these gaps using mechanistic interpretability to uncover and manipulate cultural representations in LLMs. Leveraging sparse autoencoders, we identify interpretable features that encode culturally salient information and aggregate them into Cultural Embeddings (CuE). We use CuE both to analyze implicit cultural biases under underspecified prompts and to construct white-box steering interventions. Across multiple models, we show that CuE-based steering increases cultural faithfulness and elicits significantly rarer, long-tail cultural concepts than prompting alone. Notably, CuE-based steering is complementary to black-box localization methods, offering gains when applied on top of prompt-augmented inputs. This also suggests that models do benefit from better elicitation strategies, and don't necessarily lack long-tail knowledge representation, though this varies across cultures. Our results provide both diagnostic insight into cultural representations in LLMs and a controllable method to steer towards desired cultures.

The rapid growth in the volume, variety, and velocity of geospatial data has created data ecosystems that are highly distributed, heterogeneous, and semantically inconsistent. Existing data catalogs, portals, and infrastructures still rely largely on keyword-based search with limited semantic support, which often fails to capture user intent and leads to weak retrieval performance. To address these challenges, this study proposes a knowledge graph-driven multi-agent framework for intelligent geospatial data discovery, powered by large language models. The framework introduces a unified geospatial metadata ontology as a semantic mediation layer to align heterogeneous metadata standards across platforms and constructs a geospatial metadata knowledge graph to explicitly model datasets and their multidimensional relationships. Building on the structured representation, the framework adopts a multi-agent collaborative architecture to perform intent parsing, knowledge graph retrieval, and answer synthesis, forming an interpretable and closed-loop discovery process from user queries to results. Results from representative use cases and performance evaluation show that the framework substantially improves intent matching accuracy, ranking quality, recall, and discovery transparency compared with traditional systems. This study advances geospatial data discovery toward a more semantic, intent-aware, and intelligent paradigm, providing a practical foundation for next-generation intelligent and autonomous spatial data infrastructures and contributing to the broader vision of Autonomous GIS.

Hierarchical predictive processing explains adaptive behaviour through precision-weighted inference. Explicit belief revision often fails to produce corresponding changes in stress reactivity or autonomic regulation. This asymmetry suggests the framework leaves under-specified a governance-level constraint concerning which identity-level hypotheses regulate autonomic and behavioural control under uncertainty. We introduce Authority-Level Priors (ALPs) as meta-structural constraints defining a regulatory-admissible subset (Hauth, a subset of H) of identity-level hypotheses. ALPs are not additional representational states nor hyperpriors over precision; they constrain which hypotheses are admissible for regulatory control. Precision determines influence conditional on admissibility; ALPs determine admissibility itself. This explains why explicit belief updating modifies representational beliefs while autonomic threat responses remain stable. A computational formalisation restricts policy optimisation to policies generated by authorised hypotheses, yielding testable predictions concerning stress-reactivity dynamics, recovery time constants, compensatory control engagement, and behavioural persistence. Neurobiologically, ALPs manifest through distributed prefrontal arbitration and control networks. The proposal is compatible with variational active inference and introduces no additional inferential operators, instead formalising a boundary condition required for determinate identity-regulation mapping. The model generates falsifiable predictions: governance shifts should produce measurable changes in stress-reactivity curves, recovery dynamics, compensatory cognitive effort, and behavioural change durability. ALPs are advanced as an architectural hypothesis to be evaluated through computational modelling and longitudinal stress-induction paradigms.

Standard attention mechanisms in transformers are limited by their pairwise formulation, which hinders the modeling of higher-order dependencies among tokens. We introduce the NeuroGame Transformer (NGT) to overcome this by reconceptualizing attention through a dual perspective: tokens are treated simultaneously as players in a cooperative game and as interacting spins in a statistical physics system. Token importance is quantified using two complementary game-theoretic concepts -- Shapley values for global, permutation-based attribution and Banzhaf indices for local, coalition-level influence. These are combined via a learnable gating parameter to form an external magnetic field, while pairwise interaction potentials capture synergistic relationships. The system's energy follows an Ising Hamiltonian, with attention weights emerging as marginal probabilities under the Gibbs distribution, efficiently computed via mean-field equations. To ensure scalability despite the exponential coalition space, we develop importance-weighted Monte Carlo estimators with Gibbs-distributed weights. This approach avoids explicit exponential factors, ensuring numerical stability for long sequences. We provide theoretical convergence guarantees and characterize the fairness-sensitivity trade-off governed by the interpolation parameter. Experimental results demonstrate that the NeuroGame Transformer achieves strong performance across SNLI, and MNLI-matched, outperforming some major efficient transformer baselines. On SNLI, it attains a test accuracy of 86.4\% (with a peak validation accuracy of 86.6\%), surpassing ALBERT-Base and remaining highly competitive with RoBERTa-Base. Code is available at https://github.com/dbouchaffra/NeuroGame-Transformer.

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM) converts the generated frames into executable robot actions. However, current video world models lack explicit executability constraints. As a result, visually coherent rollouts may still violate rigid-body and kinematic consistency, producing unstable or infeasible control commands when decoded by an IDM. We refer to this mismatch between visual generation and physically executable control as the executability gap. While this gap can be mitigated at inference time using techniques such as rejection sampling, such approaches are inefficient due to the high cost of video generation. In this paper, we leverage the executability gap as a training signal and introduce Executable Video Alignment (EVA), a reinforcement-learning post-training framework for aligning video world models. EVA trains an inverse dynamics model on real robot trajectories and repurposes it as a reward model that evaluates generated videos through the action sequences they induce, encouraging smooth motions measured by velocity, acceleration, and jerk while penalizing actions that violate embodiment constraints. Importantly, the reward remains informative even when generated videos contain severe visual artifacts, since such artifacts typically translate into unstable or out-of-bound actions. Experiments on the RoboTwin benchmark and a real bimanual robot show that EVA reduces embodiment-specific artifacts in generated rollouts and improves downstream task execution success.

Occupations form and evolve faster than classification systems can track. We propose that a genuine occupation is a self-reinforcing structure (a bipartite co-attractor) in which a shared professional vocabulary makes practitioners cohesive as a group, and the cohesive group sustains the vocabulary. This co-attractor concept enables a zero-assumption method for detecting occupational emergence from resume data, requiring no predefined taxonomy or job titles: we test vocabulary cohesion and population cohesion independently, with ablation to test whether the vocabulary is the mechanism binding the population. Applied to 8.2 million US resumes (2022-2026), the method correctly identifies established occupations and reveals a striking asymmetry for AI: a cohesive professional vocabulary formed rapidly in early 2024, but the practitioner population never cohered. The pre-existing AI community dissolved as the tools went mainstream, and the new vocabulary was absorbed into existing careers rather than binding a new occupation. AI appears to be a diffusing technology, not an emerging occupation. We discuss whether introducing an "AI Engineer" occupational category could catalyze population cohesion around the already-formed vocabulary, completing the co-attractor.

Gaze estimation is instrumental in modern virtual reality (VR) systems. Despite significant progress in remote-camera gaze estimation, VR gaze research remains constrained by data scarcity, particularly the lack of large-scale, accurately labeled datasets captured with the off-axis camera configurations typical of modern headsets. Gaze annotation is difficult since fixation on intended targets cannot be guaranteed. To address these challenges, we introduce VRGaze, the first large-scale off-axis gaze estimation dataset for VR, comprising 2.1 million near-eye infrared images collected from 68 participants. We further propose GazeShift, an attention-guided unsupervised framework for learning gaze representations without labeled data. Unlike prior redirection-based methods that rely on multi-view or 3D geometry, GazeShift is tailored to near-eye imagery, achieving effective gaze-appearance disentanglement in a compact, real-time model. GazeShift embeddings can be optionally adapted to individual users via lightweight few-shot calibration, achieving a 1.84° mean error on VRGaze. On the remote-camera MPIIGaze dataset, the model achieves a 7.15° person-agnostic error, doing so with 10x fewer parameters and 35x fewer FLOPs than baseline methods. Deployed natively on a VR headset GPU, inference takes only 5 ms. Combined with demonstrated robustness to illumination changes, these results highlight GazeShift as a label-efficient, real-time solution for VR gaze tracking. Project code and the VRGaze dataset are released at https://github.com/gazeshift3/gazeshift

Robots operating in dynamic and shared environments benefit from anticipating contact before it occurs. We present GenTact-Prox, a fully 3D-printed artificial skin that integrates tactile and proximity sensing for contact detection and anticipation. The artificial skin platform is modular in design, procedurally generated to fit any robot morphology, and can cover the whole body of a robot. The skin achieved detection ranges of up to 18 cm during evaluation. To characterize how robots perceive nearby space through this skin, we introduce a data-driven framework for mapping the Perisensory Space -- the body-centric volume of space around the robot where sensors provide actionable information for contact anticipation. We demonstrate this approach on a Franka Research 3 robot equipped with five GenTact-Prox units, enabling online object-aware operation and contact prediction.

Pathology report generation remains a relatively under-explored downstream task, primarily due to the gigapixel scale and complex morphological heterogeneity of Whole Slide Images (WSIs). Existing pathology report generation frameworks typically employ transformer architectures, relying on a homogeneous decoder architecture and static knowledge retrieval integration. Such architectures limit generative specialization and may introduce noisy external guidance during the report generation process. To address these limitations, we propose RANGER, a sparsely-gated Mixture-of-Experts (MoE) framework with adaptive retrieval re-ranking for pathology report generation. Specifically, we integrate a sparsely gated MoE into the decoder, along with noisy top-$k$ routing and load-balancing regularization, to enable dynamic expert specialization across various diagnostic patterns. Additionally, we introduce an adaptive retrieval re-ranking module that selectively refines retrieved memory from a knowledge base before integration, reducing noise and improving semantic alignment based on visual feature representations. We perform extensive experiments on the PathText-BRCA dataset and demonstrate consistent improvements over existing approaches across standard natural language generation metrics. Our full RANGER model achieves optimal performance on PathText dataset, reaching BLEU-1 to BLEU-4 scores of 0.4598, 0.3044, 0.2036, and 0.1435, respectively, with METEOR of 0.1883, and ROUGE-L of 0.3038, validating the effectiveness of dynamic expert routing and adaptive knowledge refinement for semantically grounded pathology report generation.

Compositional generalization-the ability to interpret novel combinations of familiar components-remains a persistent challenge for neural networks. Behavioral evaluations reveal \emph{when} models fail but offer limited insight into \emph{why} failures arise at the representational level. We introduce \textit{Homomorphism Error} (HE), a structural metric that measures the inconsistency between a set of established rules for which words combine to form new meaning (linguistic syntax) and model's learned rules for which hidden states combine to form new states (semantic syntax). We formulate this inconsistency as deviations from approximate homomorphisms between the linguistic expression algebra and a model's hidden-state space. We designed experiments to test if i) HE predicts compositional generalization performance, and ii) will regularizing for low HE during training improve such performance. To avoid the effect of data spoilage, we train small decoder-only Transformers from scratch using an adapted version of established dataset, SCAN, for testing compositional generalization. Across controlled experiments, HE predicts out-of-distribution (OOD) compositional generalization under noise injection, achieving $R^2=0.73$ correlation between HE and OOD accuracy. Ablations show that model depth has minimal effect on either HE or OOD accuracy, training data coverage exhibits threshold effects, and randomly inserted noise tokens increase HE. Intervention experiment shows that HE-regularized training significantly reduces HE ($p=1.1\times10^{-4}$) and yields a statistically significant improvement in OOD accuracy ($p=0.023$). Together, these results indicate the potential of HE to be both a diagnostic and an actionable training signal for improving compositional generalization.

Marked Temporal Point Processes (MTPPs) arise naturally in medical, social, commercial, and financial domains. However, existing Transformer-based methods mostly inject temporal information only via positional encodings, relying on shared or parametric decay structures, which limits their ability to capture heterogeneous and type-specific temporal effects. Inspired by this observation, we derive a novel attention operator called Hawkes Attention from the multivariate Hawkes process theory for MTPP, using learnable per-type neural kernels to modulate query, key and value projections, thereby replacing the corresponding parts in the traditional attention. Benefited from the design, Hawkes Attention unifies event timing and content interaction, learning both the time-relevant behavior and type-specific excitation patterns from the data. The experimental results show that our method achieves better performance compared to the baselines. In addition to the general MTPP, our attention mechanism can also be easily applied to specific temporal structures, such as time series forecasting.

With the rapid progress of controllable generation, training data synthesis has become a promising way to expand labeled datasets and alleviate manual annotation in remote sensing (RS). However, the complexity of semantic mask control and the uncertainty of sampling quality often limit the utility of synthetic data in downstream semantic segmentation tasks. To address these challenges, we propose a task-oriented data synthesis framework (TODSynth), including a Multimodal Diffusion Transformer (MM-DiT) with unified triple attention and a plug-and-play sampling strategy guided by task feedback. Built upon the powerful DiT-based generative foundation model, we systematically evaluate different control schemes, showing that a text-image-mask joint attention scheme combined with full fine-tuning of the image and mask branches significantly enhances the effectiveness of RS semantic segmentation data synthesis, particularly in few-shot and complex-scene scenarios. Furthermore, we propose a control-rectify flow matching (CRFM) method, which dynamically adjusts sampling directions guided by semantic loss during the early high-plasticity stage, mitigating the instability of generated images and bridging the gap between synthetic data and downstream segmentation tasks. Extensive experiments demonstrate that our approach consistently outperforms state-of-the-art controllable generation methods, producing more stable and task-oriented synthetic data for RS semantic segmentation.

Monocular depth estimation (MDE) provides a useful tool for robotic perception, but its predictions are often uncertain and inaccurate in challenging environments such as surgical scenes where textureless surfaces, specular reflections, and occlusions are common. To address this, we propose ProbeMDE, a cost-aware active sensing framework that combines RGB images with sparse proprioceptive measurements for MDE. Our approach utilizes an ensemble of MDE models to predict dense depth maps conditioned on both RGB images and on a sparse set of known depth measurements obtained via proprioception, where the robot has touched the environment in a known configuration. We quantify predictive uncertainty via the ensemble's variance and measure the gradient of the uncertainty with respect to candidate measurement locations. To prevent mode collapse while selecting maximally informative locations to propriocept (touch), we leverage Stein Variational Gradient Descent (SVGD) over this gradient map. We validate our method in both simulated and physical experiments on central airway obstruction surgical phantoms. Our results demonstrate that our approach outperforms baseline methods across standard depth estimation metrics, achieving higher accuracy while minimizing the number of required proprioceptive measurements. Project page: https://brittonjordan.github.io/probe_mde/

As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization from zero delay to measured delay during training and inference. We introduce Delay-Aware Diffusion Policy (DA-DP), a framework for explicitly incorporating inference delays into policy learning. DA-DP corrects zero-delay trajectories to their delay-compensated counterparts, and augments the policy with delay conditioning. We empirically validate DA-DP on a variety of tasks, robots, and delays and find its success rate more robust to delay than delay-unaware methods. DA-DP is architecture agnostic and transfers beyond diffusion policies, offering a general pattern for delay-aware imitation learning. More broadly, DA-DP encourages evaluation protocols that report performance as a function of measured latency, not just task difficulty.

Haptic interfaces play a critical role in medical teleoperation by enabling surgeons to interact with remote environments through realistic force and motion feedback. Achieving high fidelity in such systems requires balancing the trade-offs among workspace, dexterity, stiffness, inertia, and bandwidth, particularly in applications demanding pure rotational motion. This paper presents the design methodology and kinematic analysis of a Cable-Driven Coaxial Spherical Parallel Mechanism (CDC-SPM) developed to address these challenges. The proposed approach focuses on the mechanical design and parametric synthesis of the mechanism to meet task-specific requirements in medical applications. In particular, the design enables the relocation of the center of rotation to an external point corresponding to the tool-tissue interaction, while ensuring appropriate workspace coverage and collision avoidance. The proposed cable-driven interface design allows for reducing the mass placed at the robot arm end-effector, thereby minimizing inertial loads, enhancing stiffness, and improving dynamic responsiveness. Through parallel and coaxial actuation, the mechanism achieves decoupled rotational degrees of freedom with isotropic force and torque transmission. A prototype is developed to validate the mechanical feasibility and kinematic behavior of the proposed mechanism. These results demonstrate the suitability of the proposed mechanism design for future integration into haptic interfaces for medical applications such as ultrasound imaging.

Retrieval-Augmented Generation (RAG) enhances factual grounding in large language models (LLMs) by incorporating retrieved evidence, but LLM accuracy declines when long or noisy contexts exceed the model's effective attention span. Existing pre-generation filters rely on heuristics or uncalibrated LLM confidence scores, offering no statistical control over retained evidence. We evaluate and demonstrate context engineering through conformal prediction, a coverage-controlled filtering framework that removes irrelevant content while preserving recall of supporting evidence. Using both embedding- and LLM-based scoring functions, we test this approach on the NeuCLIR and RAGTIME collections. Conformal filtering consistently meets its target coverage, ensuring that a specified fraction of relevant snippets are retained, and reduces retained context by 2-3x relative to unfiltered retrieval. On NeuCLIR, downstream factual accuracy measured by ARGUE F1 improves under strict filtering and remains stable at moderate coverage, indicating that most discarded material is redundant or irrelevant. These results demonstrate that conformal prediction enables reliable, coverage-controlled context reduction in RAG, offering a model-agnostic and principled approach to context engineering.

Refusal refers to the functional behavior enabling safety-aligned language models to reject harmful or unethical prompts. Following the growing scientific interest in mechanistic interpretability, recent work encoded refusal behavior as a single direction in the model's latent space; e.g., computed as the difference between the centroids of harmful and harmless prompt representations. However, emerging evidence suggests that concepts in LLMs often appear to be encoded as a low-dimensional manifold embedded in the high-dimensional latent space. Motivated by these findings, we propose a novel method leveraging Self-Organizing Maps (SOMs) to extract multiple refusal directions. To this end, we first prove that SOMs generalize the prior work's difference-in-means technique. We then train SOMs on harmful prompt representations to identify multiple neurons. By subtracting the centroid of harmless representations from each neuron, we derive a set of multiple directions expressing the refusal concept. We validate our method on an extensive experimental setup, demonstrating that ablating multiple directions from models' internals outperforms not only the single-direction baseline but also specialized jailbreak algorithms, leading to an effective suppression of refusal. Finally, we conclude by analyzing the mechanistic implications of our approach.

Natural disasters demand rapid damage assessment to guide humanitarian response. Here, we investigate whether medium-resolution Earth observation images from the Copernicus program can support building damage assessment, complementing very-high resolution imagery with often limited availability. We introduce xBD-S12, a dataset of 10,315 pre- and post-disaster image pairs from both Sentinel-1 and Sentinel-2, spatially and temporally aligned with the established xBD benchmark. In a series of experiments, we demonstrate that building damage can be detected and mapped rather well in many disaster scenarios, despite the moderate 10$\,$m ground sampling distance. We also find that, for damage mapping at that resolution, architectural sophistication does not seem to bring much advantage: more complex model architectures tend to struggle with generalization to unseen disasters, and geospatial foundation models bring little practical benefit. Our results suggest that Copernicus images are a viable data source for rapid, wide-area damage assessment and could play an important role alongside VHR imagery. We release the xBD-S12 dataset, code, and trained models to support further research at https://github.com/prs-eth/xbd-s12 .

Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this limitation by enabling collaborative reasoning among multiple models in a round-table debate manner. While effective, MAD introduces substantial computational overhead due to the number of agents involved and the frequent communication required. In this paper, we propose MARS (Multi-Agent Review System), a role-based collaboration framework inspired by the review process. In MARS, an author agent generates an initial solution, reviewer agents provide decisions and comments independently, and a meta-reviewer integrates the feedback to make the final decision and guide further revision. This design enhances reasoning quality while avoiding costly reviewer-to-reviewer interactions, thereby controlling token consumption and inference time. We compared MARS with both MAD and other state-of-the-art reasoning strategies across multiple benchmarks. Extensive experiments with different LLMs show that MARS matches the accuracy of MAD while reducing both token usage and inference time by approximately 50\%. Code is available at https://github.com/xwang97/MARS.

Modelling dynamically evolving spatio-temporal signals is a prominent challenge in the Graph Neural Network (GNN) literature. Notably, GNNs assume an existing underlying graph structure. While this underlying structure may not always exist or is derived independently from the signal, a temporally evolving functional network can always be constructed from multi-channel data. Graph Variate Signal Analysis (GVSA) defines a unified framework consisting of a network tensor of instantaneous connectivity profiles against a stable support usually constructed from the signal itself. Building on GVSA and tools from graph signal processing, we introduce Graph-Variate Neural Networks (GVNNs): layers that convolve spatio-temporal signals with a signal-dependent connectivity tensor combining a stable long-term support with instantaneous, data-driven interactions. This design captures dynamic statistical interdependencies at each time step without ad hoc sliding windows and admits an efficient implementation with linear complexity in sequence length. Across forecasting benchmarks, GVNNs consistently outperform strong graph-based baselines and are competitive with widely used sequence models such as LSTMs and Transformers. On EEG motor-imagery classification, GVNNs achieve strong accuracy highlighting their potential for brain-computer interface applications.

Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines -- not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers ~76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25x token reduction (25 Hz to 1 Hz). Across 10 benchmarks -- with and without filtering -- audio yields clear gains on tasks requiring speech comprehension or cross-modal grounding, while vision-centric suites remain largely unaffected. Our results show that speech encoders play a larger role in video understanding than current benchmarks suggest. We will fully open-source our work at https://github.com/naver-ai/LLaVA-AV-SSM.