arXiv:2601.13457v3 Announce Type: replace
Abstract: Single-photon polymerization ensures rapid photopolymerization of centimeter-scale structures with features on the order of tens of micrometers, whereas 2PP provides sub-micrometer features at sub-millimeter scales. Existing hybrid approaches combining these techniques typically rely on stitched or layer-by-layer fabrication and often require separate printing platforms, making mesoscale manufacturing time-consuming. Here, we introduce a hybrid unified 3D printer that leverages the complementary strengths of both printing mechanisms to bridge this scale resolution-fabrication time gap. We propose integrating 2PP for high-resolution, localized spatial control with single-photon TVAM for enabling rapid, high-throughput 3D fabrication. In this approach, TVAM first forms millimeter-scale volumetric structures attached on a glass rod, via overprinting, which is then accessible, on the same platform, for subsequent high-resolution 2PP. Without needing to change the photoresin or introducing intermediate post-processing steps, we proceed to demonstrate finely printed structures via 2PP, fabricated both inside (embedded within) and on the surface of the millimeter-scale 3D objects printed with TVAM. Here, TVAM contributes in two distinct ways: by generating a pre-polymerized volume that facilitates subsequent 2PP, and by directly driving layer-less volumetric polymerization in designated regions within seconds. We experimentally demonstrate that this dual-mode strategy provides a mesoscale approach spanning three orders of magnitude in scale for rapid fabrication of millimeter-scale structures featuring 830 nm details. For applications such as micro-optics, biomedical scaffolds and tissue engineering, tens-of-micrometer features are sufficient across the majority of the volume, with higher resolution confined to localized functional regions.
Science Journals
arXiv:2601.16718v3 Announce Type: replace
Abstract: The properties of the solution to the adjoint two-dimensional boundary layer (BL) equations on a flat plate are investigated from the viewpoint of Libby-Fox theory, which describes the algebraic perturbations to the Blasius boundary layer. The adjoint solution is obtained from the Green's function of the perturbation equation as a sum over the infinite perturbation modes of the Blasius solution. The explicit representation of the adjoint solution allows us to derive constraints on the eigenvalues and eigenfunctions, explicitly compute the Adjoint Transport Convection (ATC) term and evaluate flow sensitivities for shape design, initial-value perturbations, and active flow control. The extension of the analysis to the case with non-zero pressure gradient, corresponding to the Falkner-Skan solution, is also briefly discussed.
arXiv:2601.18798v3 Announce Type: replace
Abstract: ECG-Language Models (ELMs) extend recent advances in Multimodal Large Language Models (MLLMs) to automated ECG interpretation. However, most existing ELMs inherit Vision-Language Model (VLM) design choices and rely on pretrained ECG encoders, introducing substantial architectural and training complexity. Inspired by encoder-free VLMs, we introduce ELF, a family of three encoder-free ELMs that remain competitive with, and often outperform, prior state-of-the-art ELMs across two datasets despite substantially simpler architectures and training pipelines. All code and data are available at github.com/ELM-Research/ECG-Language-Models.
arXiv:2601.22830v2 Announce Type: replace
Abstract: Reliable environmental perception remains one of the main obstacles for safe operation of automated vehicles. Safety of the Intended Functionality (SOTIF) concerns safety risks from perception insufficiencies, particularly under adverse conditions where conventional detectors often falter. While Large Vision-Language Models (LVLMs) demonstrate promising semantic reasoning, their quantitative effectiveness for safety-critical 2D object detection is underexplored. This paper presents a systematic evaluation of ten representative LVLMs using the PeSOTIF dataset, a benchmark specifically curated for long-tail traffic scenarios and environmental degradations. Performance is quantitatively compared against two specialized detectors: the anchor-based YOLOv5 and the transformer-based RT-DETRv4. Experimental results reveal a critical trade-off: top-performing LVLMs (e.g., Gemini 3) surpass the YOLOv5 in recall by over 25% and closely match RT-DETRv4 under natural visual degradation, while specialized detectors retain an advantage in geometric precision for handcrafted perturbations. These findings highlight the complementary strengths of semantic reasoning versus geometric regression, supporting the use of LVLMs as high-level safety validators in SOTIF-oriented automated driving systems.
arXiv:2502.16167v2 Announce Type: replace
Abstract: Diffusion models (DMs) have advanced text-to-image (T2I) synthesis, yet their personalization capabilities raise serious privacy and copyright concerns. Malicious actors can misuse these models to generate unauthorized portraits or artistic style replicas. Existing proactive defenses primarily rely on applying adversarial perturbations to reference images to disrupt training. However, these approaches face limitations: they assume all training images are pre-perturbed and are prone to failure when datasets contain unperturbed images or undergo minor data transformations. In this paper, we introduce PersGuard, a novel backdoor-based framework designed to prevent unauthorized personalization of pre-trained T2I diffusion models. Unlike perturbation-based methods, we assume protectors can embed protective backdoors into the models before their release. This mechanism ensures that if a downstream user fine-tunes the model on protected images, the model retains the backdoor and generates predefined protective outputs; conversely, for unprotected images, the backdoor is effectively removed during fine-tuning to ensure normal model utility. We formulate the backdoor injection as a unified optimization problem incorporating three objectives: a backdoor behavior loss to activate protection, a prior preservation loss to maintain standard generation capabilities, and a novel backdoor retention loss. The retention loss is specifically designed to mirror personalization loss, ensuring the backdoor remains robust during downstream fine-tuning. Extensive experiments across gray-box and black-box settings, multi-object protection, and facial identity protection demonstrate that PersGuard provides superior privacy protection compared to existing perturbation-based methods.
arXiv:2508.12466v2 Announce Type: replace
Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data. We revisit this design choice and propose Inverse-LLaVA, a multimodal architecture that inverts the conventional mapping direction by projecting text embeddings into continuous visual representation space and performing fusion within intermediate transformer layers. This representation-first design enables effective multimodal reasoning without relying on an explicit alignment pretraining stage and significantly reduces dependence on large alignment datasets. Across nine multimodal benchmarks, Inverse-LLaVA demonstrates strong learning efficiency under reduced supervision, achieving substantial gains on reasoning-intensive tasks while exhibiting selective performance drops on perception tasks that depend on explicit visual--text grounding. Our analysis indicates that these trade-offs primarily reflect differences in supervision regime rather than architectural limitations. Together, these results show that alignment pretraining is not strictly required for effective multimodal reasoning and highlight the importance of preserving continuous modality representations, opening a new direction for multimodal architecture design that decouples representation structure from supervision regime for more flexible and efficient multimodal systems.
arXiv:2607.13043v1 Announce Type: new
Abstract: Deep learning models achieve state-of-the-art image classification but face deployment challenges due to computational costs and energy demands. We propose a lightweight training strategy that adapts normalization layers of the model to the new domain and decouples feature extraction from classifier optimization, reducing overhead by precomputing features only once. A redesigned classifier head with margin-based weighted loss further minimizes ambiguity without end-to-end backpropagation. Evaluated across four CNN architectures (ResNet18, ResNet50, MobileNet, DenseNet121), three Transformer models (ViT, Swin and DeiT) and three medical datasets (Brain Cancer MRI, BreakHis and PatchCamelyon), our approach significantly reduces the required training time with only a marginal accuracy trade-off, often matching or surpassing baseline performance. This efficiency translates to reducing CO2 by orders of magnitude, offering a practical and environmentally sustainable solution for resource-constrained clinical or prototyping environments.
arXiv:2602.02741v2 Announce Type: replace
Abstract: Articulation modeling enables robots to learn joint parameters of articulated objects for effective manipulation which can then be used downstream for skill learning or planning. Existing approaches often rely on prior knowledge about the objects, such as the number or type of joints. Some of these approaches also fail to recover occluded joints that are only revealed during interaction. Others require large numbers of multi-view images for every object, which is impractical in real-world settings. Furthermore, prior works neglect the order of manipulations, which is essential for many multi-DoF objects where one joint must be operated before another, such as a dishwasher. We introduce PokeNet, an end-to-end framework that estimates articulation models from a single human demonstration without prior object knowledge. Given a sequence of point cloud observations of a human manipulating an unknown object, PokeNet predicts joint parameters, infers manipulation order, and tracks joint states over time. PokeNet outperforms existing state-of-the-art methods, improving joint axis and state estimation accuracy by an average of over 27% across diverse objects, including novel and unseen categories. We demonstrate these gains in both simulation and real-world environments.
arXiv:2602.09503v2 Announce Type: replace
Abstract: Cooperation is central to human societies and often unfolds within groups. Higher-order networks, such as hypergraphs, naturally represent these groups as hyperedges. Network structures and update rules, by which individuals revise their strategies, are the two fundamental components that shape the evolution of cooperation in structured populations. Yet while the effects of network structure have been studied extensively, update rules have been examined mostly through isolated models, leaving their relationships and the origins of their differing evolutionary outcomes poorly understood. Here we develop a unified framework for imitation dynamics on higher-order networks, parameterizing imitation-based update rules by the number of groups an individual samples and the number of peers consulted within each group. Under weak selection, we derive a closed-form condition for the success of cooperation in any multiplayer social dilemma on homogeneous hypergraphs, encompassing games with both linear and nonlinear payoff structures. The framework places previously disconnected update rules within a single family and reduces their effects on cooperation to one interpretable quantity, which we term information diversity. Update rules inducing higher information diversity promote cooperation more effectively, and we prove that this ordering holds strictly across the entire space of multiplayer social dilemmas. Simulations extend this principle to heterogeneous hypergraphs constructed both synthetically and from empirical data. Our framework provides a systematic way to represent, analyze, and compare update rules on higher-order networks, turning a fragmented collection of microscopic updating mechanisms into a tractable and interpretable theory.
arXiv:2602.17659v2 Announce Type: replace
Abstract: Vision-Language-Action models (VLAs) promise to ground language instructions in robot control, yet in practice often fail to faithfully follow language. When presented with instructions that lack strong scene-specific supervision, VLAs suffer from counterfactual failures: they act based on vision shortcuts induced by dataset biases, repeatedly executing well-learned behaviors and selecting objects frequently seen during training regardless of language intent. To systematically study it, we introduce LIBERO-CF, the first counterfactual benchmark for VLAs that evaluates language following capability by assigning alternative instructions under visually plausible LIBERO layouts. Our evaluation reveals that counterfactual failures are prevalent yet underexplored across state-of-the-art VLAs. We propose Counterfactual Action Guidance (CAG), a simple yet effective dual-branch inference scheme that explicitly regularizes language conditioning in VLAs. CAG combines a standard VLA policy with a language-unconditioned Vision-Action (VA) module, enabling counterfactual comparison during action selection. This design reduces reliance on visual shortcuts, improves robustness on under-observed tasks, and requires neither additional demonstrations nor modifications to existing architectures or pretrained models. Extensive experiments demonstrate its plug-and-play integration across diverse VLAs and consistent improvements. For example, on LIBERO-CF, CAG improves $\pi_{0.5}$ by 9.7% in language following accuracy and 3.6% in task success on under-observed tasks using a training-free strategy, with further gains of 15.5% and 8.5%, respectively, when paired with a VA model. In real-world evaluations, CAG reduces counterfactual failures of 9.4% and improves task success by 17.2% on average.
arXiv:2602.18548v3 Announce Type: replace
Abstract: Design-to-code translates high-fidelity UI designs into executable front-end implementations, but progress remains hard to compare due to inconsistent datasets, toolchains, and evaluation protocols. We introduce 1D-Bench, a benchmark grounded in real e-commerce workflows, where each instance provides a reference rendering and an exported intermediate representation that may contain extraction errors. 1D is short for one day, representing the efficient completion of design-to-code tasks in less than one day. Models take both as input, using the intermediate representation as structural cues while being evaluated against the reference rendering, which tests robustness to intermediate representation defects rather than literal adherence.
1D-Bench requires generating an executable React codebase under a fixed toolchain with an explicit component hierarchy, and defines a multi-round setting in which models iteratively apply component-level edits using execution feedback. Experiments on commercial and open-weight multimodal models show that iterative editing generally improves final performance by increasing rendering success and often improving visual similarity. We further conduct a pilot study on post-training with synthetic repair trajectories and reinforcement learning based editing, and observe limited and unstable gains that may stem from sparse terminal rewards and high-variance file-level updates. The data and scripts used in this study are available in an anonymized repository at https://anonymous.4open.science/r/d2c-benchmark-A9C4/.
arXiv:2603.04710v2 Announce Type: replace
Abstract: Recent advances in automatic speech recognition (ASR) and speech enhancement have strengthened the common belief that cleaner audio should lead to more accurate transcription. In this work, we examine whether this assumption holds for modern zero-shot ASR systems. We conduct a structured empirical study of SAM-Audio as a preprocessing step for zero-shot transcription with OpenAI Whisper. Five Whisper variants are evaluated on noisy Bengali and English speech datasets. On the English dataset, SAM-Audio increases the average PSNR from 32.28 dB to 35.99 dB and achieves higher PSNR for 71.84% of the utterances. However, WER and CER increase in every evaluated model-dataset configuration. On the Bengali dataset, Whisper large-v3 WER increases from 65.83% to 77.35%, while CER increases from 24.13% to 34.74%. On the English dataset, Whisper base WER increases from 10.53% to 21.66%, while CER increases from 4.48% to 12.50%. Utterance-level analysis further shows that the degradation affects a substantial portion of the evaluated samples, although its severity varies across Whisper variants. These findings demonstrate that improved signal-level quality does not necessarily lead to better zero-shot ASR performance and that denoising can reduce recognition accuracy.
arXiv:2603.06228v2 Announce Type: replace
Abstract: Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks exploit this low-latency advantage by updating predictions event by event, but still suffer from two bottlenecks: recurrent architectures are difficult to train efficiently on long sequences, and improving accuracy often increases per-event computation and latency. Linear attention is appealing because it enables parallel training and recurrent inference. However, its dense state updates make per-event computation scale with the state size, yielding a poor accuracy-efficiency trade-off for object detection, where accurate localization requires fine-grained spatial states. The key challenge is therefore to introduce sparse state activation that exploits the spatial sparsity of events while preserving efficient parallel training. We propose Spatially-Sparse Linear Attention (SSLA), which introduces a mixture-of-spaces state decomposition and a scatter-compute-gather training procedure, enabling state-level sparsity as well as training parallelism. Building on SSLA, we develop an end-to-end asynchronous linear attention model, SSLA-Det, for low-latency event-based object detection. On Gen1 and N-Caltech101, SSLA-Det achieves state-of-the-art accuracy among asynchronous methods, reaching 0.375 mAP and 0.515 mAP, respectively, while reducing per-event computation by over 20 times compared with the strongest prior asynchronous baseline, demonstrating the potential of linear attention for low-latency event-based vision.
arXiv:2603.06502v2 Announce Type: replace
Abstract: Existing models of political violence often emphasize discrete transitions, when conflicts emerge, escalate, or subside, without considering the longer trajectories of violence that accumulate across time and space. This paper introduces a spatially explicit longitudinal sequence analysis to address this gap. Using event-level data from the Armed Conflict Location and Event Dataset covering Africa from 1997 to 2024, we classify locations according to the intensity and spatial concentration of violence, tracing how these states evolve into distinct conflict trajectories. Applying optimal matching and clustering techniques, we identify six recurrent patterns ranging from short-lived, localized outbreaks to protracted high-intensity conflicts. We further assess how these trajectories align across neighboring areas, revealing evidence of spatial interdependence, particularly in border regions. By highlighting the temporal rhythms and geographic linkages of political violence, the study advances conflict research beyond isolated transitions and provides a framework for understanding the life cycles of violence.
arXiv:2603.08521v2 Announce Type: replace
Abstract: Understanding dynamic 3D environments in a spatially continuous and temporally consistent manner is fundamental for robotics and autonomous driving. While recent advances in occupancy prediction provide a unified representation of scene geometry and semantics, progress in 4D panoptic occupancy tracking remains limited by the lack of benchmarks that support surround-view fisheye sensing, long temporal sequences, and instance-level voxel tracking. To address this gap, we present OccTrack360, a new benchmark for 4D panoptic occupancy tracking from surround-view fisheye cameras. OccTrack360 provides substantially longer and more diverse sequences (174~2234 frames) than prior benchmarks, together with principled voxel visibility annotations, including an all-direction occlusion mask and an MEI-based fisheye field-of-view mask. To establish a strong fisheye-oriented baseline, we further propose Focus on Sphere Occ (FoSOcc), a framework that addresses two core challenges in fisheye occupancy tracking: distorted spherical projection and inaccurate voxel-space localization. FoSOcc includes a Center Focusing Module (CFM) to enhance instance-aware spatial localization through supervised focus guidance, and a Fisheye-based Enhanced Lifting (FEL) that extends perspective lifting to fisheye imaging under the Unified Projection Model. Extensive experiments on Occ3D-Waymo and OccTrack360 show that our method improves occupancy tracking quality with notable gains on geometrically regular categories, and establishes a strong baseline for future research on surround-view fisheye 4D occupancy tracking. The benchmark and source code will be made publicly available at https://github.com/YouthZest-Lin/OccTrack360.
arXiv:2511.04390v2 Announce Type: replace
Abstract: The Matroid Secretary Problem is a central question in online optimization, modeling sequential decision-making under combinatorial constraints. We introduce a bipartite graph framework that unifies and extends several known formulations, including bipartite matching, matroid intersection, and matroid secretary problems. In this model, agents and items form a bipartite graph, and the objective is to select a matching that satisfies independence constraints on both sides.
We first study the free-order setting under edge-arrivals. For $k$-matroid intersection, we leverage a core lemma by [FSZ, 2022] to design an ${\Omega}(1/k^2)$-competitive algorithm, extending known results for single matroids. Building on this, we introduce $k$-growth systems -- a new class of independence systems that lie properly between $k$-matchoids and $k$-extendible systems and may be of independent combinatorial interest. We establish a generalized core lemma for $k$-growth systems, showing that a suitably defined set of critical elements retains a ${\Omega}(1/k^2)$ fraction of the optimal weight. Using this lemma, we extend our ${\Omega}(1/k^2)$-competitive algorithm to $k$-growth systems.
We then study the agent-arrival model, which presents unique challenges to our framework. We extend the core lemma to this model and then apply it to obtain an ${\Omega}(\beta/k^2)$-competitive algorithm for $k$-growth systems, where $\beta$ denotes the competitiveness of an appropriate type of order-oblivious algorithm for the item-side constraint. Finally, we extend our results to the case of multiple item selection, and obtain constant-competitive algorithms for fundamental cases such as partition matroids and $k$-matching constraints.
We also study the closure properties and structural role and of $k$-growth systems within the hierarchy of $k$-systems.
arXiv:2603.12451v4 Announce Type: replace
Abstract: Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their unimodal counterparts. We hypothesize that this underperformance stems from poor context quality in existing datasets, as verification is challenging. To address these limitations, we introduce a semi-synthetic data augmentation method that generates contexts both descriptive of temporal dynamics and verifiably complementary to numerical histories. This approach enables massive-scale dataset creation, resulting in CAF-7M, a corpus of 7 million context-augmented time series windows, including a rigorously verified test set. We demonstrate that semi-synthetic pre-training transfers effectively to real-world evaluation, and show clear evidence of context utilization. Our results suggest that dataset quality, rather than architectural limitations, has been the primary bottleneck in context-aided forecasting.
arXiv:2603.12676v5 Announce Type: replace
Abstract: Generalizing neural surrogate models across different PDE parameters remains difficult because changes in PDE coefficients often make learning harder and optimization less stable. The problem becomes even more severe when the model must also predict beyond the training time range. Existing methods usually cannot handle parameter generalization and temporal extrapolation at the same time. Standard parameterized models treat time as just another input and therefore fail to capture intrinsic dynamics, while recent continuous-time latent methods often rely on expensive test-time auto-decoding for each instance, which is inefficient and can disrupt continuity across the parameterized solution space. To address this, we propose Disentangled Latent Dynamics Manifold Fusion (DLDMF), a physics-informed framework that explicitly separates space, time, and parameters. Instead of unstable auto-decoding, DLDMF maps PDE parameters directly to a continuous latent embedding through a feed-forward network. This embedding initializes and conditions a latent state whose evolution is governed by a parameter-conditioned Neural ODE. We further introduce a dynamic manifold fusion mechanism that uses a shared decoder to combine spatial coordinates, parameter embeddings, and time-evolving latent states to reconstruct the corresponding spatiotemporal solution. By modeling prediction as latent dynamic evolution rather than static coordinate fitting, DLDMF reduces interference between parameter variation and temporal evolution while preserving a smooth and coherent solution manifold. As a result, it performs well on unseen parameter settings and in long-term temporal extrapolation. Experiments on several benchmark problems show that DLDMF consistently outperforms state-of-the-art baselines in accuracy, parameter generalization, and extrapolation robustness.
arXiv:2512.10607v2 Announce Type: replace
Abstract: We present TCAM (Track and Caption Any Motion), a generative framework that watches a video and with no text query and no region prompt decides what is moving, describes each motion in open vocabulary, locates it in time, and points to the exact trajectories that carry it. Two mature lines of work make this possible yet leave it unsolved: dense point trackers follow pixels with sub-object precision but emit no language, while video-language models produce fluent descriptions only when handed a query and only from clip-level features that cannot resolve which pixels move. Object-level captioners narrow the gap but still reason over detector boxes or masks, never reaching individual trajectories. TCAM couples tracking and language at point granularity through a Caption-Aware Resampler, where a small set of learnable queries cross-attends to dense point trajectory tokens and distills them into a fixed-length motion context that conditions a language decoder. The decoder generates an entire video's events in a single pass, each with a free-form caption, a start and end time, and a pointer to the trajectories it refers to, for sequential events and several subjects active at once. Training uses only existing segmentation annotations, with no extra event labeling, to supervise caption quality, pointer-mask alignment, and pointer diversity. On over 50K clips, TCAM outperforms dense video captioning baselines and matches dedicated, query-based grounding and point-tracking methods despite using no query, showing that trajectory-conditioned generation is a direct route to motion-driven video understanding.
arXiv:2512.20645v2 Announce Type: replace
Abstract: In this study, we demonstrate that compared with traditional centroid-based methods, machine learning methods (particularly transformer-based architectures) achieve superior subpixel position and therefore angular resolution in discretized particle detectors. Using Geant4 Monte Carlo simulated cosmic ray muon data from an 8x8 segmented scintillator detector array, we compare four reconstruction approaches: transformer neural networks, convolutional neural networks, linear regression, and energy-weighted centroids. The transformer architecture achieves the best angular reconstruction with a root mean square error of 1.14{\deg} and a position mean absolute error of 0.24 cm, representing improvements of 2.22x and 6.33x, respectively, over the centroid method. These results enable precise particle trajectory reconstruction for applications in muon tomography and cosmic ray detection.
arXiv:2602.19108v2 Announce Type: replace
Abstract: Safely moving through environments affected by fire is a critical capability for autonomous mobile robots deployed in disaster response. In this work, we present a novel approach for mobile robots to understand fire through building real-time thermal radiation fields. We register depth and thermal images to obtain a 3D point cloud annotated with temperature values. From these data, we identify fires and use the Stefan-Boltzmann law to approximate the thermal radiation in empty spaces. This enables the construction of a continuous thermal radiation field over the environment. We show that this representation can be used for robot navigation, where we embed thermal constraints into the cost map to compute collision-free and thermally safe paths. We validate our approach on a Boston Dynamics Spot robot in controlled experimental settings. Our experiments demonstrate the robot's ability to avoid hazardous regions while still reaching navigation goals. Our approach paves the way toward mobile robots that can be autonomously deployed in fire-affected environments, with potential applications in search-and-rescue, firefighting, and hazardous material response.
arXiv:2603.14181v3 Announce Type: replace
Abstract: We investigate how sign-indefinite quadratic invariants shape turbulent cascades in incompressible flows with broken time-reversal symmetry, where the dynamics supports strongly anisotropic dispersive waves. Focusing on rotating Euler flow and odd-viscous Euler flow, we isolate the wave component study the corresponding weak-turbulence kinetic equation. We show that helicity conservation substantially simplifies the kinetic equation. Fixing the energy flux by a natural gauge choice, we identify the turbulent spectrum as the unique scale-invariant solution that sustains a constant flux of energy from large to small scales. Under a mild approximation motivated by the accumulation of energy near slow modes, we compute the leading angular dependence and uncover an integrable singularity along the slow-mode curve, that agrees with previous results. We then demonstrate that helicity reorganizes cascade directions at the level of resonant triads. Although helicity is globally sign-indefinite, the helical decomposition splits it into sign-definite contributions on each polarization branch. Triads whose three legs lie on the same branch behave as if constrained by a sign-definite invariant and drive an upscale transfer of energy, producing systematic backscatter even when the net cascade is direct. In the helicity-definite limit (single-branch dynamics), the kinetic equation admits an additional scale-invariant solution associated with helicity transport. Finally, we validate the analytical predictions by numerically evaluating the collision integral in the strongly anisotropic limit, revealing a family of stationary solutions in that regime.
arXiv:2603.14709v3 Announce Type: replace
Abstract: Retrieval-augmented generation (RAG) enhances zero-shot time series (TS) forecasting by leveraging external knowledge bases, yet existing approaches overlook input-level relevance when fusing retrieved samples with the query. We argue that not all retrievals are equally useful, and irrelevant ones can degrade performance. To this end, we propose Cross-RAG, a zero-shot RAG-based forecasting framework that selectively attends to query-relevant retrieved samples via query--retrieval cross-attention. By modeling input-level relevance between the query and retrieved samples, Cross-RAG jointly incorporates three sources of information: 1) the query itself, 2) the retrieved samples, and 3) their relational interactions. In particular, this input-aware design enables Cross-RAG to remain stable as the number of retrieved samples $k$ grows, whereas prior methods without cross-attention require careful $k$ tuning to avoid degradation from irrelevant retrievals. Extensive experiments demonstrate that Cross-RAG consistently improves zero-shot forecasting performance across multiple TSFM backbones and various RAG methods, with additional analyses confirming its effectiveness across various retrieval scenarios. Code is available at https://github.com/seunghan96/cross-rag/.
arXiv:2603.16307v3 Announce Type: replace
Abstract: Remote sensing underpins crucial applications such as disaster relief and ecological field surveys, where systems must understand complex scenes and constraints and make reliable decisions. Current remote-sensing benchmarks mainly focus on evaluating perception and reasoning capabilities of multimodal large language models (MLLMs). They fail to assess planning capability, stemming either from the difficulty of curating and validating planning tasks at scale or from evaluation protocols that are inaccurate and inadequate. To address these limitations, we introduce NeSy-Route, a large-scale neuro-symbolic benchmark for constrained route planning in remote sensing. Within this benchmark, we introduce an automated data-generation framework that integrates high-fidelity semantic masks with heuristic search to produce diverse route-planning tasks with provably optimal solutions. This allows NeSy-Route to comprehensively evaluate planning across 10,821 route-planning samples, nearly 10 times larger than the largest prior benchmark. Furthermore, a three-level hierarchical neuro-symbolic evaluation protocol is developed to enable accurate assessment and support fine-grained analysis on perception, reasoning, and planning simultaneously. Our comprehensive evaluation of various state-of-the-art MLLMs demonstrates that existing MLLMs show significant deficiencies in perception and planning capabilities. We hope NeSy-Route can support further research and development of more powerful MLLMs for remote sensing. The dataset and code are available at https://mingyang1010.github.io/NeSy-Route/.
arXiv:2603.19063v2 Announce Type: replace
Abstract: Most existing robot simulators prioritize rigid-body dynamics and photorealistic rendering, but largely neglect the thermally and optically complex phenomena that characterize real-world fire environments. For robots envisioned as future firefighters, this limitation hinders both reliable capability evaluation and the generation of representative training data prior to deployment in hazardous scenarios. To address these challenges, we introduce Fire as a Service (FaaS), a novel, asynchronous co-simulation framework that augments existing robot simulators with high-fidelity and computationally efficient fire simulations. Our pipeline enables robots to experience accurate, multi-species thermodynamic heat transfer and visually consistent volumetric smoke without disrupting high-frequency rigid-body control loops. We demonstrate that our framework can be integrated with diverse robot simulators to generate physically accurate fire behavior, benchmark thermal hazards encountered by robotic platforms, and collect realistic multimodal perceptual data. Crucially, its real-time performance supports human-in-the-loop teleoperation, enabling the successful training of reactive, multimodal policies via Behavioral Cloning. By adding fire dynamics to robot simulations, FaaS provides a scalable pathway toward safer, more reliable deployment of robots in fire scenarios.