arXiv:2606.12008v1 Announce Type: new Abstract: Thematic maps visually communicate statistical information about spatial units such as countries or states. They must balance the individual readability of those map elements that carry the statistical information and the overall cartographic context. Nowadays, most maps are not static images, but must flexibly respond to a range of device types and display sizes. Current approaches to responsive thematic mapping are limited: they are labor-intensive for practitioners and often rely on combining disjointed visual encodings to cover different device types. In this paper we introduce the first algorithmic framework to efficiently compute responsive thematic maps that smoothly adapt to different display sizes. A key component of our framework is the layout guide: a combinatorial structure which encodes the two essential aspects of a thematic map. The first aspect are the visual requirements of each statistical map element (at least their desired width and height), the second aspect is the cartographic context in the form of relative positions of map elements. Our main algorithmic contribution is the map arranger which takes a visual container as input and returns a suitable layout guide. The map arranger does so in a stable and consistent manner: if the container changes only a little, then so does the layout guide, and the same input container always results in the same layout guide. To use our framework, one needs three ingredients: $(1)$ a reference layout, which corresponds to the ``ideal'' thematic map, $(2)$ a total vertical and horizontal order for all map elements (the desired layouts for containers with extreme aspect ratios), and $(3)$ a thematic mapping algorithm that can construct a thematic map from a layout guide. We demonstrate our framework on two types of thematic maps, namely rectangular and Demers cartograms.
Science Journals
arXiv:2606.12016v1 Announce Type: new Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and behaviors. However, as models become increasingly evaluation and training aware, they may be motivated to resist training when the perceived objective conflicts with their current values, undermining developers' ability to detect misalignment and correct model behavior through further training. In this paper, we demonstrate generalization hacking, in which a model collects reward during RL while preventing the rewarded behavior from generalizing. We construct a model organism on Qwen3-235B-A22B, finetuning on synthetic documents describing training awareness and self-inoculation, a novel mechanism in which the model frames compliance as context-specific in its chain of thought, without demonstrating or instructing either behavior. The model organism achieves train-time harmfulness comparable to controls while maintaining a persistent ${\sim}15$ percentage point compliance gap across 700 steps of RL. Additionally, a control organism trained only on training awareness documents independently discovers inoculation-like reasoning under RL pressure, developing its own compliance gap despite never being exposed to the concept. Because the generalization-hacking organism receives high reward throughout, standard training metrics provide no signal that generalization has failed. Our results constitute the first demonstration that a model can actively resist RL behavioral modification while maintaining high reward, suggesting that as models become more capable and training-aware, they may be able to undermine the training process itself.
arXiv:2606.12027v1 Announce Type: new Abstract: Collision-free path planning in cluttered, real-world environments relies on a representation of the collision-free space, and existing representations broadly fall into two categories. Explicit representations, such as unions of convex sets, can be plugged into optimization-based planners as hard collision-free constraints, but their parameters scale poorly with configuration-space dimension. Implicit representations, by contrast, are flexible and scale well to complex geometries, yet typically lack such guarantees. We bridge this gap with ILD (Invertible Latent Decomposition), a framework that jointly learns an invertible mapping and a union of explicit convex polytopes in the resulting latent space. Planning is carried out over these latent convex sets, and the invertible mapping decodes the resulting paths back to the original configuration space while preserving feasibility with respect to the refined explicit safe regions. We further propose Visibility-Guided Sampling (VGS) to keep the convex sets connected for path planning. Across 2D navigation, 6-DoF, and 14-DoF manipulation environments, ILD achieves broader coverage, better inter-set connectivity, and higher path-planning success rates than prior baselines, with zero observed false positives after test-time refinement. On a 14-DoF bimanual manipulator, we further demonstrate real-time collision-free planning, with test-time refinement adapting to scene-geometry changes during real-world deployment on a single 6-DoF arm.
arXiv:2606.12047v1 Announce Type: new Abstract: In this paper, we address the problem of zero-shot understanding of accidents from surveillance videos by identifying when an impact event occurs, what type of impact it is, and where in the frame it occurs using natural language. We propose a three-stage pipeline that decomposes the accident understanding into when, what, and where. The first stage extracts a short temporal window around the impact using vision-language similarity. In the second stage, we perform metadata-driven multi-prompt reasoning with five complementary views (baseline, motion, geometry, contrast, and tiebreaker) and resolve disagreement via an entropy-gated pairwise adjudicator. Finally, we localize the impact of an open-vocabulary detector queried on the predicted accident type and scene layout, and aggregate detections across keyframes using a score-weighted centroid. Our pipeline achieves a substantial improvement in the harmonic-mean score over a centre-of-frame baseline on the zero-shot ACCIDENT @ CVPR benchmark. We show that decomposing zero-shot video understanding into temporal localization, semantic classification, and spatial grounding enable more reliable reasoning with vision-language models than direct prompting alone.
arXiv:2606.12051v1 Announce Type: new Abstract: Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images. We contend that this discrepancy is largely related to differing lighting conditions, including differences in light wavelength and light source type. Recently, frequency-based VI-ReID approaches have achieved notable success because frequency information can better extract identity-relevant contours and details while excluding irrelevant lighting and color. However, existing methods either do not distinguish different frequency bands or focus on only one band, which is insufficient under diverse lighting conditions. To perform comprehensive frequency domain learning, we propose a Multi-Frequency Expert Network (MFEN) that enables multi-frequency modulation and adaptively combines different bands through a mixture-of-experts design. We further introduce Random Frequency Augmentation (RFA) and Frequency Auxiliary Optimization (FAO) to better train MFEN. The three modules are complementary and jointly capture critical frequency-domain details for robust representation learning. Extensive experiments on three VI-ReID datasets demonstrate the effectiveness of our approach.
arXiv:2606.12054v1 Announce Type: new Abstract: Injecting noise into the optimization process is a well-established technique for improving the training and generalization of deep neural networks. Yet, despite the breadth of existing approaches, it remains unclear which design choices truly matter in practice. In this work, we investigate parameter noise injection for stochastic gradient descent, focusing on two key questions: how to efficiently pair each training example with its own perturbation in mini-batch training, and whether sophisticated noise parameterizations or multi-sample gradient averaging yield meaningful gains over simpler alternatives. To address the first question, we leverage a distributional identity for linear layers that allows per-example noise injection without breaking batched computation. To address the second, we systematically compare several diagonal Gaussian parameterizations against an isotropic baseline across varying noise levels on CIFAR100. Our results consistently show that simple, lightweight strategies, isotropic noise with a single perturbed forward pass per update step, recover most of the benefit of more complex schemes. These findings suggest that simplicity suffices for parameter noise injection, and that practitioners need not resort to elaborate perturbation designs to reap the optimization and generalization benefits of noisy SGD.
arXiv:2606.12066v1 Announce Type: new Abstract: In modern vehicular systems, robust performance under harsh conditions has become a critical problem of autonomous driving. Our study delivers a comprehensive evaluation of the newest iteration of the YOLO series, which is YOLOv11 Nano architecture benchmarked against the widely adopted YOLOv8 Nano as a baseline on a custom fused dataset that combines the Indian Driving Dataset (IDD) [1] and Berkeley Deep Drive Dataset (BDD100K) [2]. We have analyzed the trade-offs among detection accuracy, inference speed, and computational efficiency in high-entropy scenarios involving dense mixed traffic, rain, and low-light conditions. Specifically, YOLOv11n achieves a mean Average Precision (mAP@50) of 46.6%, with a notable 3.2% improvement in Precision over the baseline, effectively reducing false positives in cluttered scenes. Furthermore, the proposed model exhibits enhanced energy efficiency, requiring 22% fewer FLOPs (6.3G vs. 8.1G) while maintaining real-time inference speed of 70.9 FPS on a Tesla T4 GPU, offering an optimal trade-off for safety-critical edge deployment.
arXiv:2606.12077v1 Announce Type: new Abstract: Time-series clustering remains challenging due to the inherent trade-off between clustering effectiveness and computational efficiency. Similarity-based methods often suffer from quadratic complexity caused by pairwise distance computations, while deep learning-based approaches typically rely on costly iterative training and a large number of trainable parameters. In this paper, we propose MSRGC-Net, an efficient time-series clustering framework that integrates multiscale reservoir computing, granular-ball-based anchoring graph construction, and consensus learning. MSRGC-Net adopts a training-free reservoir computing paradigm to extract multiscale temporal representations from raw time series without backpropagation, significantly reducing computational overhead. To capture the intrinsic structure of the resulting representations, granular-ball computing is employed to adaptively model data distributions via density-consistent regions, yielding compact and robust anchor graph representations. Furthermore, a consensus-based anchoring graph optimization strategy is introduced to effectively align multiscale reservoir representations and integrate complementary information across temporal scales. Extensive experiments on widely used univariate and multivariate benchmark datasets demonstrate that MSRGC-Net consistently outperforms state-of-the-art methods in clustering performance while maintaining superior computational efficiency.
arXiv:2606.12088v1 Announce Type: new Abstract: Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information is often unavailable due to privacy constraints, missing metadata, or legal restrictions, even though models may infer it from indirect textual cues. This raises a key question: can debiasing succeed without direct access to sensitive attributes? We propose H-SAL, which performs post-hoc concept and attribute erasure using self-description text as an implicit debiasing signal. To support this setting, we introduce a multi-domain Stack Exchange-based fairness benchmark for helpfulness prediction that includes both explicit and implicit signals, enabling comparison between standard debiasing with protected labels and debiasing without access to sensitive information. Across encoder and decoder-only language models, we find that implicit self-description often matches or outperforms explicit-label-based debiasing. Our results broaden representation-level fairness research and provide a new benchmark for studying debiasing under realistic data constraints.
arXiv:2606.12105v1 Announce Type: new Abstract: Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, processing every input at one rate. This is misaligned with physical interaction, where a high-frequency modality changes at hundreds of hertz, vision evolves more slowly, and language stays constant across an episode. A synchronous VLA oversamples slow modalities, undersamples fast ones, and caps action generation at the lowest effective frequency. We hypothesize that decoupling temporal processing per modality, letting each update and retain information at its own sensor rate, yields stronger representations and more robust control. We present DAM-VLA, which maintains per-modality latent buffers refreshed at sensor rates and read continuously by the action head, integrating new high-frequency modalities through gated cross-attention that leaves the pretrained backbone intact. Across seven contact-rich real-world manipulation tasks, DAM-VLA more than doubles the average success rate of the strongest synchronous baseline (95.2\% vs.\ 40.95\%) while sustaining smooth, reactive 100\,Hz control. Project website: \href{https://intuitive-robots.github.io/DAM-VLA/}{intuitive-robots.github.io/DAM-VLA/}
arXiv:2606.12109v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulation, yet the vast majority of pre-trained pipelines remain strictly confined to low-DoF parallel grippers. Adapting these rich semantic priors to high-DoF dexterous hands introduces a severe morphology gap, direct end-to-end joint fine-tuning inherently causes catastrophic forgetting of spatial reasoning and acute action manifold collapse due to data scarcity. In this paper, we present InDex, a novel, data-efficient adaptation framework rooted in cross-morphology semantic inheritance. Rather than discarding the pre-trained 1-DoF parallel grasp output, we repurpose it as a continuous, macroscopic virtual grasp intent proxy to sequentialize the control topology. We implement a two-stage decoupled learning architecture: the first stage parameter-efficiently aligns the VLA backbone to predict continuous arm trajectories and the scalar grasp intent; the second stage freezes this spatial backbone and leverages an intent-conditioned denoising diffusion head to decode fine-grained joint articulations for multi-fingered end-effectors. Extensive simulation benchmarks across a suite of multi-stage, contact-rich dexterous manipulation tasks demonstrate that InDex effectively masters intricate skills with minimal demonstration data, substantially outperforming monolithic baselines while preserving the robust spatial generalizability of the original VLA prior.
arXiv:2606.12125v1 Announce Type: new Abstract: Long-video understanding remains challenging for multimodal large language models, because temporally extended videos often contain thousands of frames and are therefore expensive to process exhaustively. Existing methods usually construct compact visual inputs from long videos under a limited visual budget. However, most of them still follow a frame-centric paradigm and apply similar representations to retained content regardless of its importance. This makes it difficult to preserve both high-fidelity visual evidence and broad temporal coverage. To address this issue, we propose Q-Fold, a training-free input construction framework for long-video understanding. Instead of treating isolated frames as the basic modeling unit, Q-Fold operates on contiguous temporal segments and constructs a heterogeneous Focus--Context representation under query guidance. Query-relevant segments are preserved as high-fidelity Focus Frames, while less relevant segments are folded into chronology-preserving contextual layouts. In this way, Q-Fold preserves critical visual evidence and broad temporal coverage, while better maintaining local temporal continuity within short segments. Experiments on four long-video benchmarks with multiple Video-MLLMs show that Q-Fold consistently improves performance without increasing the input budget. Notably, it achieves gains of up to 9.1 percentage points on an ultra-long video benchmark. Code will be made publicly available.
arXiv:2606.12136v1 Announce Type: new Abstract: Energy consumption is an increasing concern in IoT-Edge-Cloud infrastructures, where containerized application orchestration must balance performance with sustainability. This paper investigates how the Kubernetes CODECO framework integrates cross-layer energy-awareness into scheduling decisions for containerized applications across the IoT-Edge-Cloud continuum. CODECO monitors energy at both the computational level, via Kepler, and at a network (IP) level, and uses these metrics to define greenness heuristics that guide pod placement decisions through its ILP-based scheduler. The approach is experimentally evaluated on a real-world far Edge testbed composed of ARM-based embedded devices, comparing CODECO against vanilla Kubernetes across multiple scenarios. The results show that CODECO consistently reduces the energy consumption of the cluster, with savings of up to 11.01 mJ in computational energy and 4.14 mJ in network transmission energy consumption at peak load, for a wide set of scenarios which combine different types of injected fault conditions, including CPU stress, asymmetric network delay, and bandwidth contention. A composite greenness score combining both energy dimensions provides a stable and consistent ranking of scheduling strategies across all conditions, demonstrating its suitability as a unified energy indicator for cluster-level orchestration decisions across the IoT-Edge-Cloud continuum.
arXiv:2606.12138v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs. We study this question through \emph{feature stability}: for each SAE feature, we estimate the probability that a similar feature reappears in an independently trained SAE. This yields a scalable per-feature signal that separates stable from unstable features. In a large-scale study across seeds, models, layers, dictionary sizes, and SAE variants, we find a pronounced functional asymmetry: stable features carry most of the reconstruction- and prediction-relevant signal, while unstable features have weak marginal impact and are dominated by low-frequency surface-form triggers in both activation statistics and automatic explanations. Geometrically, unstable features are individually non-reproducible but concentrate in reproducible lower-rank subspaces, suggesting that seed dependence often reflects basis ambiguity within a shared region of activation space rather than pure noise. A controlled synthetic model makes this mechanism explicit, showing that low-rank ground-truth features can be recovered at the subspace level while remaining non-identifiable as individual SAE latents across seeds. Finally, by pooling unique cross-seed features, we construct more stable SAEs while preserving explained variance in this setting. Together, these results show that unstable features are not merely failed or noisy latents: they have weak individual functional impact, but reflect reproducible low-dimensional structure that standard SAEs resolve differently across seeds.
arXiv:2606.12139v1 Announce Type: new Abstract: The transition to next-generation mobile communication networks, particularly 6G, demands advanced technologies to meet the requirements for ultra-reliable, low-latency communication, massive connectivity, and intelligent applications. Reconfigurable antennas (RAs) play a crucial role in achieving these objectives by enabling dynamic adjustments to the radio frequency (RF) characteristics of antennas, such as gain, radiation pattern, impedance, and polarization. Unlike traditional fixed-position antennas, RAs can alter both their radiation patterns and positions, offering flexibility in response to varying communication environments. This paper presents a comprehensive survey and tutorial on RAs, with a focus on fluid antennas (FAs), movable antennas (MAs), pinching antennas (PAs), and reconfigurable holographic antennas (RHAs), examining their potential in next-generation mobile networks. We explore the channel modelling and estimation, performance analysis, resource allocation strategies, and their synergy with other emerging wireless technologies for each type of RA. Finally, we provide a comparative analysis of different RAs and discuss the open challenges and future research directions, offering insights and guidance for future investigations in the exciting research area.
arXiv:2606.12140v1 Announce Type: new Abstract: Accurate prediction of overall survival (OS) from positron emission tomography/computed tomography (PET/CT) can support personalized treatment and follow-up strategies in oncology. However, the impact of temporal modeling on imaging-based survival prediction remains insufficiently explored. We investigate how different temporal formulations influence survival prediction by developing two complementary approaches: Attention-guided Time-Conditioned Survival (ATCS) and Multi-Time Survival (MTS). We retrospectively analyzed pre-treatment PET/CT images from 848 patients with non-small cell lung cancer (NSCLC), including 556 for model development and 292 for held-out testing. A previously proposed Time-Conditioned Survival (TCS) model was used as a baseline. Models were trained using 5-fold cross-validation and evaluated on the test set using time-dependent area under the curve (AUC) at 6-month intervals from 0.5 to 5 years. Both ATCS and MTS outperformed the baseline TCS model, achieving mean AUCs of 0.794 and 0.793, respectively, compared to 0.767. ATCS performed better at earlier time points (0.5-3 years), whereas MTS performed better at later intervals (3.5-5 years). Combining tumor-specific and tissue-wise PET/CT features improved performance over either input alone. Finer temporal discretization improved short-term prediction, while coarser intervals provided more stable long-term estimates. These findings demonstrate that temporal modeling and input design influence PET/CT-based survival prediction. The proposed approaches enable time-specific survival estimation from pre-treatment imaging and may support improved risk stratification and clinical decision-making.
arXiv:2606.12141v1 Announce Type: new Abstract: Accurate forecasting of sea surface temperature (SST) in regional seas such as the East Sea is crucial for monitoring marine ecosystems, assessing climate risks, managing fisheries, and conducting naval operations. Traditional numerical ocean models provide reliable predictions but are computationally expensive and often unsuitable for real-time forecasting. Many deep learning methods also struggle with high-dimensional spatiotemporal ocean data and experience error accumulation over longer forecasting periods. This study builds on our previously proposed Adaptive Next-Generation Reservoir Computing (Adaptive NVAR) framework, initially introduced and tested on synthetic dynamical systems, and extends it to ocean forecasting. We present a reduced-order forecasting framework that combines Singular Value Decomposition (SVD) with Adaptive NVAR to predict SST dynamics in the East Sea. SST fields are compressed into a low-dimensional representation using SVD, which extracts dominant modes of ocean variability. Adaptive NVAR models the temporal evolution of these latent states, and the predicted states are reconstructed into SST forecasts. We evaluate the framework using regional ocean datasets and compare it with the standard NG-RC/NVAR. Results show that Adaptive NVAR consistently achieves lower forecasting errors across multiple prediction horizons. In addition, SVD reduces computational complexity, resulting in a fast and scalable framework suitable for real-time ocean forecasting.
arXiv:2606.12144v1 Announce Type: new Abstract: In this paper, we prove that output-sensitive sparse polynomial GCD computation over finite fields is NP-hard under BPP many-one reduction. More precisely, for two sparse univariate polynomials $f,g$ with finite field coefficients, there exists no randomized algorithm to compute $\mathrm{gcd}(f,g)$, which is polynomial-time in the sizes of $f,g,\gcd(f,g)$ under the standard complexity assumption $\mathrm{NP}\nsubseteq\mathrm{BPP}$. This settles the open problem posed as Challenge 5 in The Sparsity Challenges in the finite field setting. Furthermore, we show that the Roots of Unity Detection problem over finite fields is NP-hard; that is, determining whether the GCD of a sparse univariate polynomial and $x^n - 1$ has nonzero degree is NP-hard.
arXiv:2606.12146v1 Announce Type: new Abstract: Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along each axis or empirically mix frequencies, which limits cross-dimensional interactions and yields direction-dependent representations. To address these limitations, we propose nD-RoPE, a decomposition-free generalization of RoPE to arbitrary dimensions. From a translation-invariant formulation in continuous Hilbert space, we derive a spectral condition for isotropy that requires treating positions and frequencies as coupled \(n\)-dimensional vectors. We instantiate this formulation with a multi-scale regular-simplex wave-vector design, which provides non-degenerate spatial coverage and a symmetric, directionally balanced second-order response. Experiments across images, videos, and point clouds demonstrate consistent performance gains and improved generalization in high-dimensional settings.
arXiv:2606.12149v1 Announce Type: new Abstract: Our work revolves around Fictitious Play, one of the first iterative methods that is known to converge to a Nash equilibrium in zero-sum games. In recent years, there has been a revived interest, due to applications in various machine learning problems, which has motivated a line of work on its convergence properties and on proposing new variants of the initial algorithm. Our paper is along this direction and introduces one new variant, which we refer to as Almost Greedy Fictitious Play. The proposed algorithm greedily attempts to find the optimal stepsize at each iteration but its search space is constrained and includes almost all the line between the cumulative mixed strategy and the current best response. Our main result is that the method achieves an instance dependent convergence rate of $\mathcal{O}(1/T)$ with respect to the duality gap. This matches the rate of Continuous Fictitious Play, and offers an alternative to discretization. We complement our theoretical findings with experiments that demonstrate the effectiveness of the method.
arXiv:2606.12154v1 Announce Type: new Abstract: In earlier work I showed that a 35B-class Mixture-of-Experts model can be loaded and executed on a consumer laptop with 8 GB of GPU memory. That result solved a placement problem and immediately exposed a different one: even correctly placed, the large model needed roughly four seconds to answer, because it was still being invoked at every query. This paper documents what happened when I stopped invoking it. During an offline phase, the large model reads source documents and writes verified answer entries into a structured knowledge store; at runtime, only a lightweight router, a deterministic renderer, and a 1B-class model are active. On the same 8 GB laptop, end-to-end response time fell from approximately 4,465 ms to 518 ms, effective end-to-end throughput rose from 15.7 to 131 tokens per second, and the small model's streaming decode rate held at 226-237 tokens per second with a time-to-first-token of 29-62 ms. The bottleneck is structural: three different large models (Qwen, Gemma, and GLM class) all showed the same multi-second runtime cost, and all three produced usable knowledge stores offline. On a 563-entry store built from seventeen real documents, keyword routing collapsed to 1.5% top-1 accuracy while BM25-based routing reached 92.8% (99.4% top-3), and a confidence gate raised effective top-1 to 98.0% by escalating 12.3% of queries. Exact-match fidelity of the small model ranged from 9/9 to 0/9 across envelope formats carrying identical content. A 16-case verification gate blocked all ten corrupted entries while admitting all six supported ones.
arXiv:2605.23380v2 Announce Type: replace-cross Abstract: It is shown that the lowest (second) order truncation of the Carleman linearization of the fluid equations (C2) recovers the late stage of the evolution, namely the steady-state solution, although to a decreasing degree of accuracy at increasing Reynolds number. This asymptotic property is first proved analytically for the decaying logistic with external forcing and then shown to hold to a significant degree of accuracy also for the more complex case of two-dimensional Kolmogorov-like fluid flow at low Reynolds numbers, below $Re \sim 10$. This time-asymptotic property may open interesting prospects for the quantum simulation of low-Reynolds steady-state fluid flows.
arXiv:2606.12179v1 Announce Type: new Abstract: A large body of work studies the problem of learning an approximation to an implicit matrix $A\in \mathbb{R}^{m\times n}$ that is only accessible implicitly via matrix-vector product queries (matvec queries) of the form ${x} \rightarrow {A}{x}$ or ${x} \rightarrow {A}^T{x}$. Of particular interest are methods that learn a near-optimal approximation with a fixed sparsity pattern. For example, we might want to learn a near-optimal diagonal, banded, or arrow-head approximation to an implicit matrix $A$. Naturally, the number of matvec queries required to solve this problem depends on the sparsity pattern, which can be encoded as a binary matrix ${S}\in \{0,1\}^{m\times n}$. The query complexity of previous algorithms scales with quantities like the total number of ones in ${S}$, its maximum column/row sparsity, or the chromatic number of a its "conflict graph". These quantities are incomparable: for a given ${S}$, parameterizing by one might yield lower query complexity than another. In this work, we unify and tighten these prior results by providing a nearly sharp characterization of the matvec query complexity of sparse matrix approximation. Generalizing a definition from graph algorithms, let the degeneracy, ${degen}({S})$, denote the smallest number $k$ so that, if we iteratively delete all rows and columns of ${S}$ with $\leq k$ ones, we are left with an empty matrix. We show that a near-optimal approximation to $A$ with sparsity pattern $S$ can be learned with $\tilde{O}({degen}({S}))$ matrix-vector product queries, and $\Omega({degen}({S}))$ queries are necessary, for any sparsity pattern ${S}$. Moreover, unlike prior work based on graph coloring, all of our methods run in polynomial time.
arXiv:2606.12210v1 Announce Type: new Abstract: Can financial news reliably predict short-term stock movements? Despite advances in large language models, this question remains unresolved. We revisit this problem using a zero-shot natural language processing framework, investigating whether models can extract actionable signals from financial news without domain-specific training. We design a structured pipeline that combines zero-shot natural language inference with temporal aggregation, explicitly modelling recency and event-dependent impact horizons when integrating information across articles. To address the need for transparency in high-stakes settings, we introduce a multi-layered explainability framework that links predictions to token-level, article-level, and aggregate evidence, and produces grounded natural language rationales. Across multiple models and prediction horizons, we find that zero-shot approaches consistently fail to outperform simple baselines, with particularly weak performance on negative movements, suggesting deeper structural limitations in mapping news sentiment to short-term price dynamics. However, explainability signals reliably distinguish between trustworthy and unreliable predictions, offering practical value even when accuracy is limited. These findings highlight the limits of zero-shot financial NLP and motivate a shift toward decision-support systems that prioritise transparency and uncertainty awareness. Code: https://github.com/alimert05/zero-shot-stock-xai
Identifying cybersickness causes in virtual reality games using symbolic machine learning algorithms
arXiv:2606.12214v1 Announce Type: new Abstract: Virtual reality (VR) and head-mounted displays are constantly gaining popularity in various fields such as education, military, entertainment, and health. Although such technologies provide a high sense of immersion, they can also trigger symptoms of discomfort. This condition is called cybersickness (CS) and is quite popular in recent virtual reality publications. This work proposes a novel experimental analysis using symbolic machine learning to rank potential causes of CS in VR games. We estimate CS causes and rank them according to their impact using classical machine learning. Experiments are performed using two virtual reality games and 6 experimental protocols along with 37 valid samples from a total of 88 volunteers. Our results show that rotation and acceleration triggered cybersickness more frequently in a flight game in contrast to a race game. We could also observe that subjects that are less experienced with VR are more prone to feel discomfort. Former experience plays a more important role on the race game, as this game provides more liberty to the user in terms of controllers, more displacement alternatives and a more user-controlled acceleration. Furthermore, different causes that trigger discomfort arise based on short or long term VR exposures. We suggest strategies for mitigating CS for these two scenarios: short and long term exposure experiences and compare the two highlighted scenarios (race and flight).