Systems and Control · Cross-listed from math.OC
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Saturday 15 August
This paper presents an iterative model predictive control algorithm that stabilizes constrained nonlinear systems without evaluating a single plant derivative. By factoring the exact nonlinear dynamics into a pseudo-linear form using state- and control-dependent coefficients (SCDCs), we replace the standard nonconvex optimization with a sequence of constrained linear-quadratic programs. Refreezing the coefficient matrices along the previously predicted trajectory drives the iteration. Near the origin, we prove this sequence contracts to a unique fixed point. We explicitly bound the number of iterations required to reach any stopping tolerance, and we quantify the distance from the fixed point to a true Karush-Kuhn-Tucker point, showing this optimality gap vanishes quadratically as the state approaches the origin. Inflating the discrete algebraic Riccati equation generates terminal ingredients that guarantee recursive feasibility and asymptotic stability, even when the solver terminates early. We adapt the terminal penalty online, proving it remains uniformly bounded, and we secure output feedback through the block-observable canonical form, which extracts the exact system state directly from past inputs and outputs. Retaining the block-banded structure of the subproblem forces the computational cost to scale linearly with the horizon length $\ell$. This $O(\ell)$ complexity matches the iterative linear quadratic regulator (iLQR) but sharply undercuts the $O(\ell^3)$ scaling of dense sequential quadratic programming (SQP). Numerical studies on a saturated quadrotor, a nonholonomic integrator, and a nonminimum-phase plant illustrate the theoretical bounds and map how the algorithm compares with iLQR, SQP, and linear-parameter-varying MPC.
Information Theory · Cross-listed from stat.ME
CORAL: Constrained Oblique Rotation with Anchored Loadings for Fidelity-Constrained Decorrelation
Decorrelating a multivariate system need not destroy source-variable identity. We introduce Constrained Oblique Rotation with Anchored Loadings (CORAL), which minimizes residual cross-correlation while guaranteeing a declared minimum correlation between each transformed variable and its designated source. For a p-variable correlation matrix $R$, we show that every exact decorrelator can be written as $R^{-1/2}Q$ for some orthogonal matrix $Q$, and define $\rho_\star(R)$ as the maximum common source fidelity compatible with exact decorrelation. Constructive lower bounds and rigorous analytical upper bounds tightly bracket $\rho_\star$ at [0.972,0.976], [0.959,0.962], and [0.949,0.950] in simulations with p={6,18,50}, respectively, compared with PCA's largest achievable minimum correlation between distinct principal components and matched source variables of 0.358, 0.329, and 0.172. Corresponding intervals are [0.751,0.758] for World Development Indicators and [0.826,0.835] for wine chemistry data sets. Thus, loss of source-variable identity is not inherent to exact decorrelation but depends on the decorrelator selected. CORAL uses constrained Riemannian optimization and extends to exact support restrictions.
Read the full abstract
Computer Vision
LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization
Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent works improve training efficiency by decoupling SCR into a scene-agnostic backbone and scene-specific prediction heads, where the backbone is pretrained on source datasets and frozen for new scenes, and only lightweight heads are optimized. However, we find that this paradigm heavily depends on the pretrained backbone. Existing decoupled methods can match conventional SCR methods fully optimized for each new scene when LiDAR configurations are similar to those used during backbone pretraining, but their accuracy drops noticeably on datasets collected with different LiDAR sensors. This suggests that efficient LiDAR localization requires representations that capture stable scene geometry across LiDAR configurations. Motivated by this observation, we propose LightLoc++, a sensor-robust and efficient outdoor LiDAR localization framework. To support sensor-robust representation learning, we introduce SULID, a synchronized urban multi-LiDAR dataset with representative 32-, 64-, and 128-beam rotating LiDARs, extensive cross-sensor overlap, and diverse urban scenes. Using SULID, we pretrain a sensor-robust backbone through cross-sensor consistency learning. LightLoc++ further preserves efficient new-scene learning by incorporating sample classification guidance and redundant sample downsampling, which reduce regression ambiguity and computational redundancy in large-scale outdoor scenes. Extensive experiments on multiple outdoor LiDAR localization benchmarks demonstrate that LightLoc++ achieves state-of-the-art localization performance with the lowest new-scene training cost among compared methods. Code and dataset will be made available at https://github.com/liw95/LightLoc-PlusPlus.
Read the full abstract
Artificial Intelligence
Physics-informed VAE-EVT for Tail Aware Radio Map Prediction
Ultra-reliable low-latency communication (URLLC) requires precise identification of spatial regions where the signal-to-noise ratio (SNR) falls below an outage threshold. In this context, an outage refers to instances in which SNR falls below a specified threshold, which, for URLLC, can be as stringent as the 0.1% quantile of the SNR distribution. Traditional generative radio map models tend to focus on reconstructing average signal levels, often overlooking the low SNR that is crucial for accurate outage prediction. To address this limitation, we introduce a physics- and tail-informed VAE-EVT (variational autoencoder-extreme value theory) framework that distinctly models both the bulk and tail distribution of SNR. Our approach begins with a physics-informed preprocessing stage that extracts deterministic features, including line-of-sight, shadowing, and distance, from the scene geometry. A dual-latent encoder then captures the bulk SNR using a Gaussian mixture and the tail using a generalized Pareto distribution (GPD). By employing a modified variational objective, the model is trained to jointly supervise both regimes, ensuring focused attention on extreme fading events. Evaluated on the RadioMapSeer dataset, our method achieves an SNR RMSE of 4.83 dB in the outage region defined by the low threshold of 0.1% SNR quantile. This significantly outperforms the state-of-the-art GAN-based model, which records an SNR RMSE of 21.90 dB, with the performance gap widening as the outage threshold becomes more stringent.
Read the full abstract
Machine Learning
Shape Operator PCA: Curvature-Aware Projections for Geometric Machine Learning
In this paper, we propose SHOPCA (Shape Operator-based Principal Component Analysis), a novel method for unsupervised metric learning and dimensionality reduction that incorporates differential geometric information into the covariance structure of classical PCA. SHOPCA regularizes the global covariance matrix using the mean shape operator, defined as the average of the absolute local shape operators estimated from the data manifold, steering principal components toward directions of both maximum variance and informative curvature. A single trace-normalized mixing coefficient $\alpha$ controls the regularization, recovering standard PCA at $\alpha = 0$ and a curvature-driven embedding as $\alpha \to \infty$. We further introduce a fully unsupervised criterion for selecting $\alpha$ based on the spectral eigengap of the regularized covariance matrix, maximizing the relative separation between the top-$d$ and remaining eigenvalues without using class labels. We evaluate SHOPCA on more than 50 real-world benchmark datasets, comparing it with PCA, ISOMAP, and UMAP using Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), Fowlkes-Mallows index (FM), and V-measure. Results show that SHOPCA consistently improves clustering quality over PCA across a broad range of datasets and surpasses UMAP on small-sample settings, where iterative neighborhood-based manifold estimation can degrade. SHOPCA is computationally tractable, parameter-efficient, and applicable to domains requiring fully unsupervised, geometry-aware dimensionality reduction.
Read the full abstract
Artificial Intelligence
MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning
Federated instruction fine-tuning enables Large Language Models (LLMs) to adapt to decentralized, privacy-sensitive data without requiring data sharing. Recent Mixture-of-Experts (MoE) LLMs are particularly attractive for federated learning because their sparse activation reduces computation and communication while scaling model capacity. However, existing federated MoE methods primarily focus on parameter aggregation and personalization, overlooking the routing behavior of MoE models as a source of information for client collaboration. Under heterogeneous instruction distributions, indiscriminate aggregation can lead to negative transfer, highlighting the need to identify which clients should collaborate during federated optimization. We propose ClientMorpher, a routing-aware, personalized federated instruction fine-tuning framework that leverages routing signatures from pretrained MoE models to organize client collaboration prior to aggregation. We investigate two complementary clustering strategies: ClientMorpher-C, which directly clusters clients using expert activation profiles, and ClientMorpher-E, which first clusters experts based on their cross-client usage signatures and then derives client collaboration groups. We evaluate ClientMorpher for federated instruction fine-tuning on the Databricks Dolly-15K dataset, using pathological and Dirichlet-based heterogeneous client distributions across multiple instruction-following tasks. Experimental results show that routing-aware collaboration consistently improves personalized performance compared to conventional federated averaging and local training, while maintaining the same communication cost. Furthermore, our study shows that client-centric and expert-centric clustering provides an effective and scalable approach for personalized federated instruction fine-tuning of sparse MoE LLMs.
Read the full abstract
Cryptography and Security
FedADB: Class Anchor-Driven Dual-Branch Federated Learning for Mitigating Forgetting
Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation. However, local training suffers from the forgetting of previously learned global knowledge under cross-client data heterogeneity, which leads to significant declines in both performance and convergence speed. Most previous studies rely on global alignment strategies to retain global knowledge, which hinder local optimization and lead to inadequate supervision of missing classes. Some studies introduce proxy datasets to supplement supervision for missing classes. However, it remains a challenge to balance class-wise global consistency and local optimization objectives without proxy datasets. In this work, we propose FedADB, a Class Anchor-Driven Dual-Branch FL framework. Specifically, the server generates class anchors optimized in a differentiable input space, which are shared across clients. These class anchors serve as global references that provide supervision for missing classes during local training. A dual-branch collaborative training mechanism is designed for clients. In this mechanism, the anchor-based global branch focuses on learning with global consistency, achieving global knowledge alignment by class-anchor balanced sampling. The local calibration branch focuses on learning discriminative local features, mitigating the degradation of local representations caused by excessive global alignment. Extensive experiments across multiple medical and natural datasets demonstrate that FedADB achieves significant improvements in both accuracy and convergence speed.
Read the full abstract
Artificial Intelligence
Physiological World Models for Human State Transitions
Continuous multimodal sensing now allows human physiology to be observed throughout daily life rather than only during occasional clinical visits. However, most health artificial intelligence systems are designed to recognize current states, estimate risks or analyse individual biomarkers. They do not directly model how physiological states change in response to real-world events, behaviours, contexts and interventions. Here we propose the Physiological World Model (PWM), an event-conditioned framework for learning these changes at the level of the whole person. We introduce the HumanState Transition Token, a structured, quality-scored unit that connects the physiological state before an event with the event or action, relevant context and intervention information, the physiological trajectory after the event, observed outcomes and data quality. We describe four capability levels, from state representation to bounded intervention planning, together with four data acquisition and validation protocols. We also propose six benchmark tasks covering HumanState representation, forecasting across multiple timescales, individualized response prediction, simulation of alternative interventions, bounded planning and reliability under distribution shift. Together, this framework provides a practical path towards personalized health management, behavioural intervention design and clinician-supervised decision support, while clearly separating prediction from causal inference and making uncertainty, safety, governance and limits of use explicit.
Read the full abstract
Systems and Control
Stabilization Limits of Payoff-Based Higher-Order Replicator Dynamics
Replicator dynamics (RD) is a fundamental model in learning in games, connecting evolutionary game theory and online learning. This paper studies payoff-based higher-order variants of RD represented as a cascade interconnection between an integrator in parallel with an auxiliary linear time-invariant (LTI) system and the softmax mapping. We investigate learnability of Nash equilibria under this Nash-stationary learning rule. First, we revisit recent results that establish convergence to Nash Equilibrium whenever the auxiliary LTI system is strictly passive and prove a converse passivity result: if the auxiliary LTI system is not passive, then there exists a static strictly contractive game whose interior Nash equilibrium is unstable under the closed-loop learning dynamics. Second, we show that there exists a class of games with isolated interior Nash equilibria that cannot be locally asymptotically stabilized by any payoff-based higher-order RD whose auxiliary LTI system is asymptotically stable and strictly proper. Finally, we show that if Nash stationarity (i.e., all Nash equilibria are stationary points of the learning dynamics) is relaxed, then generalized exponential RD (Ex-RD) can locally asymptotically stabilize a logit equilibrium for any continuously differentiable game. The stabilized equilibrium can be viewed as an entropy-regularized approximate Nash equilibrium.
Read the full abstract
Human-Computer Interaction
Vibes on Demand: Adding Vibrotactile Encoding to Line Charts Shows Experiential Benefits Without Performance Costs
Details on demand is a common design pattern in visualization design, especially useful when interacting with visually-saturated or small displays. Beyond visualization, another common approach for saturated displays is to incorporate other modalities, such as haptic feedback. While haptic rendering in visualization has primarily targeted accessibility needs, with haptics as a substitute for visual feedback, studies using haptics outside of a visualization context have shown value in experiential factors, such as increased confidence in ambiguous contexts and higher engagement. We explore vibrotactile feedback as a reinforcing information channel for communicating trends in details-on-demand tooltips on touchscreens. We identify preferred parameter configurations for our haptic encoding, informed by a study where participants identified parameter configurations that they perceived to most accurately reflect the dynamics of line charts appearing in tooltips. In a second study, we evaluated participant performance in a pairwise comparison task, finding that incorporating vibrotactile encoding improves involvement without affecting accuracy. We discuss the implications of these findings for future visualization design, and propose directions for applications and future studies.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
A Unified Geometric Framework for Developmental Analysis of Spatial Transcriptomic Data
High-throughput single-cell and spatial transcriptomic technologies provide high-resolution snapshots of heterogeneous cellular states, but their destructive nature prevents repeated measurements of the same cells over time. Consequently, temporal and spatial dynamics must be inferred from independently sampled, unaligned cell populations, making it challenging to reconstruct developmental trajectories. Optimal transport (OT) offers a geometric framework for aligning cell populations and inferring developmental trajectories, but many existing approaches focus on modeling the evolution of distributions of cells in gene expression space rather than the relational structure encoded by gene expression networks. To address this limitation, we introduce a geometric framework for analyzing the spatiotemporal evolution of gene expression networks through embeddings in Gromov–Wasserstein (GW) space. By representing each developmental stage as a graph combining gene expression and spatial proximity, our approach enables comparisons of network structure across time, continuous interpolation between developmental stages via GW geodesics, and quantification of network-level changes using Ollivier-Ricci curvature. We evaluate our framework on a spatiotemporal transcriptomic Drosophila dataset and show that GW geodesic interpolations reproduce main trends in curvature dynamics observed in empirical gene expression networks. Agreement with higher-order Co-Optimal Transport (COOT) distances, which jointly represent spatial and temporal information, further validates the framework and suggests that hypernetwork representations successfully record salient biological changes across time. In general, our approach provides a unified geometric approach to study dynamically evolving biological networks.
Read the full abstract
Information Theory
Study of Multiuser Scheduling Based on User Satisfaction for MU-MIMO Systems
Scheduling in multiuser multiple input multiple output (MU-MIMO) systems is essential for efficient resource allocation and overall performance enhancement. In this work, a multiuser scheduling problem is formulated to maximize the product of user equipments' (UEs) aggregate satisfactions, which maintains user fairness. Solving such a combinatorial problem using exhaustive search (EX), which requires evaluating all possible multiuser groups within a massive number of resource blocks (RBs), is prohibitive. Instead, we propose an efficient users' satisfaction based scheduling approach (US-SA). In our US-SA, a low dimension sub-grouping matrix is constructed {at each frame}, which is used to schedule the best multiuser group in each time slot; satisfied users are eliminated from the scheduling process. Our US-SA performs close to the optimal EX method in terms of satisfaction, transmitted data amount, spectral efficiency, latency, and fairness with lower computational cost. Moreover, our experiments demonstrate that the proposed scheme outperforms competing techniques.
Read the full abstract
Artificial Intelligence
Understanding Cognition-Induced Risks in Agentic AI Systems
Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different domains, their cognitive engagement raises critical concerns for human society that remain insufficiently studied. To address this gap, we systematically analyze risks induced by expanding cognitive capabilities, following a three-level framework defined by their cognitive scope, from physical cognition to social cognition, and finally to self-referential cognition. We study their potential risks to human agency, autonomy, and control capability, corresponding to each cognitive level. We finally propose strategies to mitigate these risks and enhance the controllability of agentic AI systems, ensuring their long-term safe development.
Read the full abstract
Artificial Intelligence
Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly understood. We study Divergent-Convergent Reasoning (DCR), a simple two-phase primitive consisting of an exploration phase that generates multiple candidate solutions followed by a convergent reconciliation phase. We present three core results. First, we show that even a single reconciliation step can reliably amplify correct minority reports: across datasets, DCR often recovers the correct answer when correct exploration outputs are in the minority, a regime where majority voting fails. Second, we introduce recursive DCR, an autoregressive reconciliation system that iteratively analyzes disagreements and allocates additional test-time compute. Recursive DCR achieves higher accuracy than fixed-compute baselines-reaching 93.3% on AIME 2024 and 92.0% on AIME 2025-while using roughly 27% less compute on average, demonstrating that attentive resource allocation is superior to uniform scaling. Third, we analyze disagreement among exploration outputs via a simple, training-free dispersion metric. Dispersion reveals a structured relationship between disagreement and test-time gains: in regimes where DCR is effective, higher disagreement among exploration outputs is associated with larger accuracy improvements from reconciliation. Together, these results show that disagreement, often viewed as noise, can be systematically exploited to improve test-time reasoning and reveal emerging scaling laws for agentic LLM systems.
Read the full abstract
Human-Computer Interaction
Resize, Remix, Regen: Frankensteining IoT Design Methods
There are numerous IoT design methods. Previous research shows that all of them have their strengths, but also their limitations. None of them is a universal, all-purpose method. However, experts often view these methods as more versatile than their creators intended. Therefore, analyzing existing methods and tools, as well as rearranging and combining their approaches and components - just as Frankenstein did with his creature - offers the possibility of new creations that may be better than any single method previously. We present the idea and concept of Frankensteining, which is based on the repeated application of IoT design methods in various contexts. We present a practical Frankensteining creation that was used in a workshop, our own methods, and a serial Frankensteining approach that was tested in an educational context. We conclude with a discussion on Frankensteining and invite other experts and practitioners to share their perspectives and experiences.
Read the full abstract
Machine Learning
MAPLE: MoE Adaptive Plug-and-play Layer-wise Expert allocation
Sparsely-activated Mixture-of-Experts (MoE) Transformers universally fix the same number of routed experts across all layers, a convention that ignores the well-documented heterogeneity in layer-wise redundancy. We demonstrate that this uniformity is systematically suboptimal and propose MAPLE, a plug-and-play framework that reallocates the routed-expert budget heterogeneously across layers of any pretrained MoE LLM, without modifying weights or requiring retraining. Our core contribution is a closed-form sensitivity-guided allocation: we probe each layer's response to variation in expert count, quantify sensitivity using three measures, and derive an analytically optimal budget assignment that directs capacity towards sensitive layers and absorbs reductions in redundant layers. This closed-form solution is further refined by a sensitivity-constrained genetic search that uses layer-wise sensitivity as a prior to guide exploration, yielding faster convergence and superior allocation quality. On four MoE models spanning different scales and architectures, MAPLE outperforms uniform and pruning-based baselines under a 75% routed-expert budget. Notably, on DeepSeek-MoE-16B, MAPLE uses only 75% of the experts yet surpasses the original 100% expert-uniform baseline on ARC-E, ARC-C, and BoolQ, improving accuracy from 65.09 to 71.40, 48.49 to 51.50, and 80.03 to 82.38, respectively. These accuracy gains translate into measured deployment efficiency: implementing MAPLE in SGLang reduces single-GPU end-to-end serving latency by 32.2% and improves throughput by 47.4%. These results show that well-designed heterogeneous allocation can be more effective than simply activating more experts, establishing it as a principled and practical axis for improving MoE efficiency.
Read the full abstract
Computer Vision
Image Denoising via the Adaptive Rank-Cluster Filter
A spatial-local image-denoising filter is proposed, and its performance metrics are evaluated in comparison with baseline filtering algorithms, including the median, adaptive median, Gaussian, bilateral, Wiener, anisotropic diffusion, and non-local means. The developed filter is based on aligning the intensity value of the central pixel in a 3x3 window with the statistical majority intensity of one of the two clusters formed by optimal Otsu's partitioning of a pixel set sorted by intensity and trimmed to seven elements. This is followed by a fuzzy fusion of the calculated value with the median intensity of the pixels within the window. The proposed filter demonstrates the highest robustness to variations in image noise levels, particularly when processing mixed noise consisting of salt-and-pepper impulse noise and additive Gaussian noise in various proportions
Read the full abstract
Computer Vision
TinyDETR-Pose: Towards End-to-End Real-Time Single-Stage 6DoF Object Pose Estimation with Lightweight Transformers
Real-time 6DoF object pose estimation on resource-constrained hardware remains challenging, as accurate correspondence-based and refinement pipelines typically rely on non-differentiable PnP/RANSAC stages or costly iterative refinement, while recent foundation-model-based approaches incur inference costs that are prohibitive for edge deployment. We present TinyDETR-Pose, a lightweight, end-to-end, single-stage framework that jointly detects objects and regresses their full 6D pose in a single forward pass. Built on the efficient LW-DETR architecture, TinyDETR-Pose formulates detection and pose estimation as a set-prediction problem and attaches dedicated MLP heads for rotation, monocular depth, and projected object center regression to each decoder query, eliminating the need for PnP, NMS (non-maximum suppression), or iterative pose refinement. Object symmetries are handled through a ADD-S loss applied uniformly to all objects, without the need for object-specific loss schedules or separate geodesic/ADD supervision. In addition, predictions are assigned to ground truth using a symmetry-safe Hungarian matcher based on class and 2D spatial cues, yielding stable assignment under symmetry and depth ambiguity. On YCB-V, TinyDETR-Pose achieves a comparable ADD-S AUC of 85.9, while requiring up to 72.7% fewer parameters than other DETR-based single-stage pose-estimation approaches. Due to its compact design, TinyDETR-Pose runs in real time and achieves an inference latency of only ~4.5 ms per frame on an NVIDIA Jetson Nano using TensorRT, demonstrating that accurate end-to-end transformer-based 6D pose estimation can be made practical for edge deployment.
Read the full abstract
Computer Vision
FMReward: Aligning and Evaluating Audio-Driven 3D Facial Animation with Human Preferences
Audio-driven 3D facial animation is essential for advancing immersion and interactivity in virtual experiences. Although recent advances have shown promising capabilities, the training and evaluation of existing methods typically rely on ground-truth-based errors, which fall short of aligning with human preferences. To address this, we present a comprehensive framework that learns an automatic perceptual model from human preference data and leverages it to improve and evaluate the perceptual quality of audio-driven 3D facial animation. To begin with, we construct FMPair (Facial Motion Pairwise preference), the first human preference dataset for audio-driven 3D facial animation, which is built through a systematic annotation pipeline and comprises 65,574 annotated 3D facial motion pairs from 8,834 distinct in-the-wild audio clips. Based on the pairwise comparison dataset, we propose a Facial Motion Reward model, termed FMReward, which takes audio and 3D facial motion as inputs and predicts a perceptual quality score aligned with human preferences. Building upon FMReward, we further introduce Facial Motion reward Feedback Learning (FMFL), a direct fine-tuning algorithm that leverages a pretrained reward model to optimize diffusion-based audio-driven 3D facial animation models for better alignment with human preferences. Extensive experiments demonstrate the superiority of FMReward over other metrics in aligning with human preferences and the effectiveness of FMFL in improving the perceptual quality of audio-driven 3D facial animation.
Read the full abstract
Computer Vision
SOS! : A Streamlined Object-Conditional Transformer for Model-free Segmentation
Foundation segmentation models excel at generating high-quality, class-agnostic masks, but they struggle to associate these proposals with specific target objects. This semantic gap severely hinders their deployment in downstream applications like robotic manipulation, which demand precise unseen objects segmentation. Existing approaches attempt to resolve this by relying on exhaustive 3D object model priors, inherently introducing prohibitive computational overhead and complex, multi-stage pipelines. To address these limitations, we propose SOS (Streamlined Object-conditional Transformer for model-free Segmentation). SOS completely eliminates the reliance on 3D models, requiring only a single reference image per target object. Central to our framework is a novel Object-Conditional Transformer that learns identity-anchored queries, unifying mask generation and target identification into a single feed-forward pass. This streamlined design drastically improves both structural and computational efficiency. Extensive evaluations across multiple benchmarks demonstrate that SOS establishes a new state-of-the-art for model-free unseen objects segmentation, delivering accurate and high-efficiency performance. The project page and code are available at https://sos-seg.github.io/.
Read the full abstract
Numerical Analysis
Space-Time Galerkin Boundary Element Method for the Wave Equation
The space-time Galerkin discretization of retarded layer potentials leads to a linear system where the coefficients are expressed in terms of integrals over the ansatz and test elements. They require carefully designed quadrature schemes because the kernel is singular in the origin and is discontinuous across the hyperbolicity cone. This paper introduces a new integration approach that leads to a scheme that converges exponentially with the number of quadrature points. The key here is to consider the integration domain as a convex polytope and to devise a decomposition into the convex hulls of simpler polytopes which are parameterized such that the singularity and discontinuity occurs in a single variable. The method is implemented for piecewise constant elements and tested on a scattering problem with known analytic solution.
Read the full abstract
Artificial Intelligence
ReasonCast: Agentic Demand Forecasting with Selective Semantic Reasoning
Demand forecasting increasingly requires combining two complementary sources of information: historical sales reveal recurring numerical dynamics, while future promotions, holidays, price changes, and platform interventions provide forward-looking knowledge. Existing text-enhanced forecasting methods often encode such context into generic representations and fuse it uniformly with time-series features, without explicitly distinguishing which semantic effects are forecast-relevant or how they should modify future dynamics. We introduce ReasonCast, a structured semantic intervention framework that translates event knowledge into forecast-specific operations. An agent examines the event context, the no-text forecast, and its uncertainty to determine whether textual reasoning is needed. Rather than injecting free-form text, ReasonCast represents event knowledge through structured fields describing event relevance, demand direction, temporal shape, amplitude, and peak intensity. These fields interact selectively with temporal components of a time-series foundation model. An additive path corrects local trends and temporal shapes, while a multiplicative path captures event-driven level shifts. ReasonCast introduces a forecast-grounded post-training curriculum. Schema SFT establishes semantic fields; semantic-field RL calibrates direction, shape, amplitude, and peak judgments; and forecast-utility RL evaluates semantic interventions through a frozen forecaster, aligning reasoning outputs with marginal forecast improvement. ReasonCast lowers WMAPE by 3.29, 1.25, and 0.47 percentage points on holiday-sensitive categories, mega-sale-sensitive categories, and M5 event windows, respectively. On stable-sales periods, indiscriminate semantic intervention increases WMAPE by 1.68 percentage points, whereas suppressing unnecessary intervention preserves the numerical backbone.
Read the full abstract
Machine Learning · Cross-listed from stat.ML
Convolution Smoothed Quantile Regression for XGBoost
The increasing availability of large and complex datasets across many scientific disciplines has led to widespread adoption of machine learning (ML) for prediction. However, most ML algorithms focus on point estimation and provide limited information about predictive uncertainty or the conditional distribution of the response, restricting their ability to characterize rare or extreme outcomes. We develop QXGB, a quantile-based gradient boosting framework, and introduce a convolution smoothed loss within it that estimates conditional quantiles for constructing dense cumulative distribution functions (CDFs), exceedance probabilities, and tail behaviour relevant to extreme outcomes. This approach preserves the computational efficiency of extreme gradient boosting while restoring the Hessian information XGBoost relies on for tree splitting, in turn providing interpretable measures of extreme value and exceedance probability predictions. We derive the gradients and Hessians needed to integrate convolution smoothed quantile loss with different kernel specifications into XGBoost, and with simulated data, benchmark this approach against alternative smoothed quantile regression losses, the native quantile objective in the XGBoost Python package, and independent versus multi-output tree estimation. The practical relevance is illustrated in an application predicting fine particulate matter (PM$_{2.5}$) in northern California, including periods where levels were elevated due to wildfire smoke. Our results show that convolution smoothed QXGB, particularly when paired with multi-output trees, delivers accurate predictions with near-zero quantile crossing, well-calibrated CDF and exceedance probability estimates, and useful tail characterization for extreme values. Interval estimation is also evaluated as a measure of data spread.
Read the full abstract
Robotics
SCORE: Shape-Conforming Regions for Flight in Enclosed, Degraded Environments
Autonomous UAVs enter enclosed environments such as caves and collapsed structures that confine the vehicle and degrade perception. Conformal prediction provides a distribution-free guarantee by calibrating how far an obstacle keep-out must expand to absorb perception error at a target coverage level. However, existing keep-out regions use convex primitives whose bulges consume narrow passages and grow as perception degrades. Our main contribution defines the nonconformity score on a signed distance field (SDF). This produces a non-convex keep-out that tightly follows obstacle geometry and avoids the unnecessary bulging of equal-margin convex regions. Two supporting components keep this geometry usable as perception degrades. First, a voxelwise union of complementary sensor observations certifies voxels that any single sensor misses. Second, the margin around the obstacle adapts to measured visibility without weather labels or the online ground-truth feedback that single-pass flight cannot provide. Results on real subterranean data show that the resulting distribution-free, shape-conforming keep-out retains more usable free space than convex baselines at the same certified coverage, and produces safer closed-loop flight.
Read the full abstract
Artificial Intelligence
D2R2: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction
Predicting single-cell transcriptomic responses to genetic perturbations is central to functional genomics and virtual-cell modeling. Existing approaches, however, typically predict an entire expression profile as a whole, leaving the order in which individual gene responses are generated unmodeled. To address this problem, we introduce \textbf{$D^{2}R^{2}$} (Discrete Diffusion with Regulation Reinforcement), which reformulates perturbation prediction as regulation-guided gene-wise progressive generation. A Masked Discrete Diffusion Model represents expression as ordinal tokens and reconstructs a fully masked profile step by step, allowing generated gene responses to condition those that remain masked. A Regulatory Policy Module initializes the generation policy from a gene regulatory network inferred from control cells and adapts it to the perturbation and current partially generated state. Then, group-relative policy optimization refines only the ordering policy using final perturbation-effect agreement as reward. Across Norman19 and VCC-H1, $D^{2}R^{2}$ achieves the best performance on all five metrics on Norman19 and remains competitive on H1. Controlled ablations holding the generator and generation budget fixed show that biological-prior ordering improves over random ordering and is more reliable than uncertainty-based heuristics, whereas reversing the biological-prior ordering degrades every metric. Biological analyses further show that the refined policy prioritizes regulatory genes early while promoting perturbation-specific transcription factors and responsive genes. These results establish gene generation order as an effective, controllable, and biologically interpretable dimension of single-cell perturbation prediction.
Read the full abstract
Machine Learning
No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage
We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated runs, with no LLM in the measurement path, demonstrated on EnterpriseOps-Gym. Across 2,128 evaluation runs spanning nine models in six families (four development, three pre-registered held-out, plus a frontier pass on two frontier-tier models that the pre-registration designates exploratory), we find: (1) damage on irreversible actions is universal across the families we measured and stochastic within them on pinned, single-provider stacks. (2) No task damaged on every run: zero always-fail cells across 42 confirmatory held-out damage events. A single clean run misses a damage-producing (model, task) pair 0.80 of the time on the development pool (13 pairs); the held-out pool is descriptively consistent (0.575 over 5 pairs, pair-weighted) but sits below our pre-registered power floor and is reported as underpowered, not as confirmation. (3) Damage-producing task count falls with model capability, from 7 of 20 tasks for an 8B model to 1 of 20 for the most capable; capability is confounded with family and training, so this is an observed gradient, not a causal claim. The residual damage does not change in character: in the exploratory frontier pass, the most capable model's one damaging task damages at $\hat{p} = 0.16$ per run, inside the same demonstrably-stochastic band, and a single audit misses it 84% of the time. (4) One model family committed the gated irreversible change while declaring it had refused: transcript- and judge-based grading scores those runs as safe refusals, only state diffs as damage. All confirmatory findings were pre-registered with per-claim demote criteria; one demoted our own initially favored finding, which we report.
Read the full abstract
Robotics
PhaseLoRA: Control-Regime-Conditioned Low-Rank Adaptation for Continuous-Action Vision-Language-Action Policies
Parameter-efficient fine-tuning (PEFT) is a natural way to adapt pretrained vision-language-action (VLA) policies, but most adapter designs apply temporally static updates throughout a control rollout, overlooking the phase-dependent nature of continuous-action manipulation. Such policies traverse distinct regimes, including approach, contact transition, grasping, transport, and placement, each requiring different adaptation behaviors. We propose PhaseLoRA, a lightweight LoRA parameterization that conditions adaptation at each action-chunk prediction step using two weakly supervised descriptors: fine-control tendency and event/boundary intensity. PhaseLoRA modulates the LoRA left factor in the action expert, allowing the effective low-rank update direction to vary over time while keeping the backbone largely frozen. On LIBERO, PhaseLoRA improves average success rate by 12.2 points over a matched-parameter high-rank LoRA baseline and outperforms stronger LoRA variants. Ablations show that random temporal modulation and scalar gating do not reproduce the performance of the full model, while update-direction analyses reveal structured temporal variation associated with the predicted control descriptors. These results establish within-trajectory conditioning as an effective lightweight PEFT axis for continuous-action VLA policies.
Read the full abstract
Robotics
VTInstructor: Visual Trajectory Prompting for Navigation Instruction Generation in Continuous Environments
Navigation instruction generation from ego-centric RGB video in continuous environments is an important yet challenging task for human-robot interaction and scalable dataset construction. Prior instruction generators assume discrete viewpoint graphs with panoramic observations, where trajectory structure is explicit; in continuous environments, however, the agent receives only a dense RGB stream, making trajectory cues difficult to recover. We propose VTInstructor, the first VLN instruction generation framework for continuous environments. Our key idea is to convert implicit trajectory geometry into explicit visual trajectory prompts: EDTC condenses long RGB trajectories into navigation-critical keyframes, VTP overlays path, turn, and goal cues onto these anchors, VTMod injects the resulting trajectory signals into the visual encoder, and VT-GRPO further calibrates this spatial injection during training, all without requiring a navigation graph, pre-built map, or scene reconstruction. On the challenging R2R-CE and RxR-CE Val Unseen benchmarks, VTInstructor sets a new state of the art across all standard NLG metrics, surpassing the strongest baseline by +0.357 CIDEr and +0.109 CIDEr, respectively. Beyond automatic metrics, VTInstructor-generated instructions raise a frozen follower's success rate to 63.3%, a +14.7 percentage-point gain over the best competing instruction source, and provide consistent data augmentation gains of +3 SR points on downstream navigation tasks.
Read the full abstract
Networking
ISAC in 3GPP: Evolution Toward 6G
Integrated sensing and communication (ISAC) is emerging as an important direction in the Third Generation Partnership Project (3GPP) evolution toward 6G because it allows cellular networks to provide environmental awareness in addition to connectivity. This paper surveys the current 3GPP trajectory from Release~19 feasibility studies to Release~20 radio, protocol, and architecture studies, while distinguishing established requirements, ongoing study assumptions, and possible forward directions. The survey covers service requirements, sensing topologies, channel model evolution beyond 3GPP Technical Report (TR)~38.901, Radio Access Network Working Group~1 (RAN1) physical layer design, Radio Access Network Working Groups~2 and~3 (RAN2 and RAN3) system implications, and the role of sensing-assisted communication. It also synthesizes the main unresolved issues in waveform and reference signal design, multi-node coordination, sensing data reporting, service exposure, privacy, and implementation constraints. By connecting service-level motivations to physical layer, protocol, and architecture implications, the paper provides a standards-centric reading of how 3GPP may evolve toward practical 6G ISAC support.
Read the full abstract
Machine Learning
Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference
Earth observation foundation models (EOFMs) are emerging as reusable representation frameworks for data-driven retrieval, prediction and process modelling within ecohydrology, which integrate EO, meteorological forcing and process models to characterise coupled water, energy and carbon dynamics in vegetation and soil across scales. However, there is yet to be an ecohydrology-specific synthesis assessing the EOFM relevance, application evidence or evaluation requirements under uncertain reference data, scale mismatch and temporal dependence. Here, we develop a framework for determining when EOFMs support interpretable inference and identify a mismatch between EOFMs and ecohydrological requirements. Firstly, an observation-to-inference hierarchy shows that relevance depends on target-specific sensing pathways, spatial-temporal support and traceable uncertainty. Secondly, a meta-analysis shows that pretraining is dominated by reflected optical and active-microwave data, with sparse thermal coverage and no passive-microwave-emission sources. Thirdly, our synthesis of ecohydrological applications finds strongest support for spatial context, label-efficient adaptation and hybrid workflows. Evidence declines with inference depth; independent validation of fluxes, coupled dynamics, event trajectories, calibrated uncertainty and decision benefits remains sparse. Fourthly, our benchmark audit finds stronger coverage of fair adaptation and reproducibility in general EOFM suites, and of process targets, direct reference evidence and distribution shifts in ecohydrological evaluations; physical consistency and uncertainty remain weakly assessed. These findings motivate a process-aware framework aligning EOFM design and evaluation with the target variable, observation pathway and process timescale, supporting trustworthy monitoring and interpretation of coupled water, energy and carbon dynamics.