arXiv:2607.15182v1 Announce Type: new
Abstract: Automated fulfillment warehouses must continuously assign and execute pickup-and-delivery work while avoiding congestion. In many-to-many Multi-Agent Pickup and Delivery (MAPD), a request specifies a stock-keeping unit rather than fixed endpoints, requiring the controller to select an agent, source, and destination before path planning. Existing graph-guidance methods primarily influence routing after goals are fixed, leaving endpoint instantiation uninformed by recent traffic. We introduce Stigmergic Graph Memory (SGM), a bounded, decaying memory layer that records recent execution signals on warehouse nodes and directed edges to rank feasible endpoints and route preferences without altering collision constraints or planner validity. Across paired request streams on five layouts, three load levels, and 25 seeds per condition, SGM outperforms two reconstructed many-to-many allocation baselines in all 15 map-load conditions, with paired throughput gains of 20.5-36.7%. These results show that recent execution memory can improve warehouse throughput by shaping which feasible goals enter the planner, not only how agents travel to already fixed goals.
Science Journals
arXiv:2602.07664v2 Announce Type: replace
Abstract: Open research information (ORI) play a central role in shaping how scientific knowledge is produced, disseminated, validated, and reused across the research lifecycle. While the visibility of such ORI infrastructures is often assessed through citation-based metrics, in this study, we present a full-text, natural language processing (NLP) driven scientometric framework to systematically quantify the impact of ORI infrastructures beyond citation counts, using the LXCat platform for low temperature plasma (LTP) research as a representative case study. The modeling of LTPs and interpretation of LTP experiments rely heavily on accurate data, much of which is hosted on LXCat, a community-driven, open-access platform central to the LTP research ecosystem. To investigate the scholarly impact of the LXCat platform over the past decade, we analyzed a curated corpus of full-text research articles citing three foundational LXCat publications. We present a comprehensive pipeline that integrates chemical entity recognition, dataset and solver mention extraction, affiliation based geographic mapping and topic modeling to extract fine-grained patterns of data usage that reflect implicit research priorities, data practices, differential reliance on specific databases, evolving modes of data reuse and coupling within scientific workflows, and thematic evolution. Importantly, our proposed methodology is domain-agnostic and transferable to other ORI contexts, and highlights the utility of NLP in quantifying the role of scientific data infrastructures and offers a data-driven reflection on how open-access platforms like LXCat contribute to shaping research directions. This work presents a scalable scientometric framework that has the potential to support evidence based evaluation of ORI platforms and to inform infrastructure design, governance, sustainability, and policy for future development.
arXiv:2607.14985v1 Announce Type: cross
Abstract: An accurate estimation of the molecular abundances of isomers in the interstellar medium (ISM) is necessary to unravel the underlying chemistry and physics. After the recent detections of both isomers of formic acid ($cis-$ and $trans-$HCOOH) in dense dark cold clouds, their accurate molecular line modeling became of interest. The conditions of these environments do not necessarily follow the local thermodynamic equilibrium, thus taking into account the competition between the radiative and collisional processes is required. This involves the knowledge of the rotational excitation data for collisions with the most abundant interstellar species \textemdash He and H$_2$. In this paper, the first potential energy surfaces (PES) for the interaction of the two rotamers of formic acid with He atoms are computed using the explicitly correlated coupled-cluster theory [CCSD(T)-F12]. The obtained PESs demonstrate qualitative similarities and high anisotropy. The global minima are found with $V=-53.0$ cm$^{-1}$ and $V=-46.0$ cm$^{-1}$ for $cis-$HCOOH and $trans-$HCOOH respectively. Collisional excitation cross sections calculated for total energies up to 100 cm$^{-1}$ demonstrate similar propensity rules for both isomers. Quantitative differences of the cross sections associated with the two rotamers are also discussed.
arXiv:2607.14619v1 Announce Type: new
Abstract: In modern experimental physics, particle accelerators and gravitational-wave observatories enable a wide-range of research at the frontiers of science. These instruments are highly complex consisting of many interacting systems which can face significant operational challenges. Apart from the experiment's main data product, a lot of data about the experimental apparatus and its environment is recorded. Machine learning techniques can analyze this big data at scale and find useful insights into operational faults potentially improving the instrument's performance and achieving the design goals. Speaking of design, machine learning can also accelerate/augment the expensive physics simulations used during the design phase of such large-scale instruments.
arXiv:2607.14751v1 Announce Type: new
Abstract: Wavefront shaping allows light to be focused through scattering objects. However, the wavefront correction found is only valid in a small region called the isoplanatic patch. Here we present a simple approach to extend this isoplanatic patch by shifting and scaling the corrected wavefront appropriately, demonstrating an 8.6-fold increase in the lateral scanning range and a 1.5-fold increase in the axial range through a scattering layer without the need to perform additional wavefront shaping measurements. Our findings agree well with a simple geometrical model that also allows us to extract the effective position of the scattering layer from the measurements.
arXiv:2607.15019v1 Announce Type: new
Abstract: Accurately modeling collisionless space plasmas requires capturing small-scale kinetic effects while keeping global-scale simulations computationally tractable. Traditional multiscale approaches often rely on localized magnetohydrodynamics (MHD)-particle-in-cell (PIC) coupling or dynamic model hierarchies. In this work, we extend an established, adaptive multi-model hierarchy spanning from fully kinetic Vlasov descriptions to fluid models by introducing an asymptotic-preserving (AP) strategy that couples a two-species, five-moment fluid description with an ideal MHD solver. This coupling is the final critical step toward enabling efficient global simulations because the kinetic-scale physics in nonideal regions is entirely handled by finer models in the hierarchy. Kinetic descriptions natively solve Maxwell's equations and thus capture fast plasma waves, oscillations, and light waves, which are absent in the MHD dynamics. To address this difference without sacrificing computational efficiency, our AP framework seamlessly projects these fast dynamics onto the slow MHD dynamics, ensuring rigorous consistency at the model interfaces. We detail the AP two-fluid formulation, the variable-coupling interface, and its integration into external frameworks. Finally, we demonstrate the validity and robustness of the fully coupled framework, from kinetics to ideal MHD, through magnetic reconnection simulations.
arXiv:2607.14730v1 Announce Type: new
Abstract: Conventional robotic grippers face a significant challenge in agricultural automation: the trade-off between compliant, adaptive grasping, pressure balancing among all joints, and high load capacity, often at the cost of high energy consumption. This paper presents a novel hybrid rigid-soft gripper that integrated low-cost, membrane-based pneumatic actuators with 3D-printed dual ratchet-pawl mechanisms to simultaneously achieve shape adaptation, uniform force distribution, and energy-free self-locking. The dual-ratchet structure assembled in an offset configuration significantly increased the angular resolution of the joint locking mechanism. Key experimental results demonstrated the gripper's superior performance: a remarkable maximum load capacity of 4200 g, far exceeding that of conventional soft grippers (45-210 g); more uniform force distribution across object sizes (1.75-35.29% difference ratio) compared to a rigid gripper (56.77-66.44%), with peak contact forces remaining below surface damage thresholds; and a 50.05% reduction in total energy consumption to 42.6 J per grasp cycle, achieved by eliminating the need for continuous pneumatic pressure through the self-locking mechanism, compared to 85.28 J for a conventional soft gripper. The combination of additive manufacturing for ratchets and commercially available materials for pneumatic chambers ensured a low-cost and easily fabricated design. These findings validated that the proposed gripper successfully bridged the gap between soft compliance and rigid reliability, offering a robust and efficient solution for scalable agricultural harvesting and manipulation tasks.
arXiv:2607.15052v1 Announce Type: new
Abstract: Federated Learning (FL) enables collaborative model training while preserving privacy by keeping data local. However, the risk of sensitive data leakage through model updates necessitates the use of secure aggregation protocols. Existing server-based secure aggregation protocols typically require the server to forward sensitive data shared between users, which increases communication overhead and introduces potential security risks. In this work, we propose a novel secure aggregation protocol based on two-layer secret sharing to address these issues. By combining Shamir's Secret Sharing with 2-out-of-2 additive secret sharing using a Pseudo-Random Function (PRF), our protocol eliminates direct communication between users, thereby removing the need for the server to forward data. We further extend the protocol with Key-homomorphic PRF (KhPRF) to support high-dimensional data aggregation and apply it to FL, enabling one-shot secure aggregation with a single server and no intermediary data forwarding. To reduce user overhead, we design a new encoding method based on the Chinese Remainder Theorem for the almost KhPRF-based mask, reducing the number of KhPRF calls and mitigating the model update expansion issue after masking. Experimental results show that our scheme significantly outperforms existing methods in terms of auxiliary node overhead. For instance, when the number of users is 100, our scheme improves communication efficiency by nearly 100 times and reduces computational overhead by approximately 17\%. Moreover, user computation time can be reduced by 51\% to 75\% when the input length is $2^{18}$.
arXiv:2607.15053v1 Announce Type: new
Abstract: The Internet taught us that the value of a network depends on \emph{how} its nodes connect: broadcast stars scale as $V\!\propto\!N$ (Sarnoff), fully-connected meshes as $N^2$ (Metcalfe), and group-forming networks as $2^{N}$ (Reed). We ask the analogous question for networks of AI agents. We model the net value of connection as a function of coordination-group size, derive from it the properties an optimal collaboration protocol must have, and introduce ANet Patu-1 -- a self-organizing consensus protocol in which the network continuously re-forms its own coalitions, adaptively riding the upper envelope of all three regimes at $O(1)$ parallel consensus rounds. To measure value without opinion-grading, we score an emergent protocol by formally specifying it and deriving its complexity, the way distributed algorithms are analyzed. Two results follow. (i)~Emergence -- a crowd of the \emph{cheapest} model, when heterogeneous, starts weak but its collective value compounds with $N$ and \emph{overtakes} a crowd of a far \emph{stronger} model that is homogeneous: a crossover that marks a scaling law for collaboration rather than for scale. (ii)~Reflexivity -- a heterogeneous network, given only its own problem and no design hints, converges on ANet Patu-1 itself, reconstructing the high-dimensional law that governs its own connective value.
arXiv:2607.14816v1 Announce Type: new
Abstract: Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on code generation quality and programming conventions remains largely unexplored. We investigate how the language used to describe programming tasks affects the source code generated by GPT-4o mini, DeepSeek, and Claude. Our study comprises 460 coding tasks spanning Python (230) and Java (230). We translate and manually curate the original English prompts into Chinese, Hindi, Spanish, and Italian while preserving their technical meaning. We evaluate the generated code using multiple dimensions, including functional correctness through test pass rates, structural quality using established code metrics, issues detected by static analysis tools, and lexical characteristics such as the language used in identifiers and comments. Our results show that (i) English prompts do not consistently produce the best functional correctness or code quality, (ii) the impact of prompt language depends on both the programming language and the LLM, and (iii) generated code frequently mixes English with the prompt language in comments and string literals. These findings provide the first curated multilingual benchmark for studying language bias in code generation and offer insights for developing more robust multilingual code generation systems.
arXiv:2607.14807v1 Announce Type: new
Abstract: Recent diffusion-based virtual try-on (VTON) methods remain limited by their reliance on segmentation masks, insufficient preservation of fine-grained textures, and limited support for arbitrary multi-garment compositions. Consequently, existing approaches still face significant challenges in real-world e-commerce deployment. We present TAMF-VTON, a texture-aware, mask-free framework that enables high-fidelity image synthesis under practical unconstrained conditions. Our method requires no human parsing or inpainting masks at inference time and supports diverse garment styles, categories, and quantities, enabling the simultaneous transfer of multiple items while preserving body structure and intricate texture details. This is achieved through a unified generative pipeline with three key components: (1) a lightweight Mixture-of-Experts (MoE) adaptation scheme that enables efficient fine-tuning without compromising the base model's general editing capabilities; (2) a frequency-domain supervision mechanism that explicitly optimizes high-frequency spectral consistency to preserve high-fidelity textures; and (3) a robust data curation pipeline employing an adaptive inpainting strategy to simulate the inverse VTON process for high-quality training pair generation. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods in both quantitative metrics and perceptual quality. Optimized for efficiency, the model achieves inference in under 15 seconds per image on an NVIDIA RTX 4090 with INT4 quantization. By combining mask-free operation, flexible multi-garment composition, faithful texture preservation, and efficient inference on consumer hardware, TAMF-VTON demonstrates a commercially viable solution for scalable deployment in real-world digital fashion scenarios. The project is available at https://www.style3d.ai/ai-photoshoot/virtual-clothing-try-on.
arXiv:2607.15023v1 Announce Type: new
Abstract: We present a detailed study of hadronic shower energy reconstruction methods for the Semi-Digital Hadronic Calorimeter (SDHCAL) within the ILD detector concept, using the Particle Flow Algorithm (PFA) APRIL. Using samples of single $K^0_L$ and dijet ($u,d,s$) events, we compare linear, quadratic, split, and polynomial regression-based reconstruction formulas, focusing on their impact on linearity and resolution. The study also addresses angular corrections required in the barrel region due to non-perpendicular particle incidence. Results show that while all methods achieve good overall performance, the split method and the polynomial regression provide the best compromise across different energy regimes, offering improved resolution at low energies without compromising linearity at higher energies. For dijets, sensitivity to PFA confusion dominates the resolution at high energies. These findings highlight the potential of future improvements, notably the integration of precise timing information from the T-SDHCAL into APRIL, to further reduce confusion and enhance hadronic energy reconstruction for next-generation lepton colliders.
arXiv:2607.14945v1 Announce Type: new
Abstract: State-of-the-art flow based text-to-image (T2I) models exhibit remarkable generative abilities but remain vulnerable to producing unsafe content. Prior safety efforts range from concept erasure and prompt filtering to classifier-based gating. However, simple techniques like parameter efficient adaptations of the models easily bypass such guardrails. We introduce a unique principled approach that achieves safety by regulating the model's attention dynamics through inference-time introspection, exhibiting intrinsic robustness. Our method analyzes and rebalances attention activations throughout image synthesis, steering generations away from unsafe concepts while preserving semantic alignment. This introspective control ensures safety of deployed models. Across standard and adversarial safety benchmarks, our approach achieves remarkable safety scores while maintaining or even improving alignment and perceptual quality. Our results reveal that attention-space regulation offers a considerably more promising path to safer diffusion transformer based image generation than the existing concept erasing mechanism.Our code can be accessed at https://basim-azam.github.io/iam/
arXiv:2607.15049v1 Announce Type: new
Abstract: Characterizing the mechanical response of materials traditionally requires solving optimization problems in which model parameters are calibrated or trained to minimize the discrepancy between model predictions and experimental data. This process can be computationally expensive and time-consuming. To overcome this limitation, we propose two neural operator architectures that directly map experimentally measured data to the constitutive functions governing the mechanical response of the material: Physics-Augmented Neural Operators (PANO) and Constitutive Artificial Neural Operators (CANO). The proposed neural operators approximate the mapping between the infinite-dimensional input space of full-field displacement measurements and net reaction forces, and the infinite-dimensional output space of hyperelastic strain-energy density functions. The displacement fields are encoded through Laplacian eigenfunctions to obtain discretization-independent and noise-robust predictions. Our framework constrains the output space to physically admissible material models that satisfy fundamental physical requirements by design. The neural operators are trained on simulated data tuples of displacement fields and reaction forces for a range of material models. Once trained, the neural operators enable near-instantaneous material characterization and require only a single forward pass to infer the strain-energy density function from a given experimental dataset. We test the predictive power of the neural operators for unseen data, noisy data, data with missing information, data from different spatial discretizations, and data from geometries of different sizes.
arXiv:2602.22568v2 Announce Type: replace
Abstract: Deep multi-view clustering has achieved remarkable progress but remains vulnerable to complex noise in real-world applications. Existing noisy robust methods predominantly rely on a simplified binary assumption, treating data as either perfectly clean or completely corrupted. This overlooks the prevalent existence of heterogeneous observation noise, where contamination intensity varies continuously across data. To bridge this gap, we propose a novel framework termed Quality-Aware Robust Multi-View Clustering (QARMVC). Specifically, QARMVC employs an information bottleneck mechanism to extract intrinsic semantics for view reconstruction. Leveraging the insight that noise disrupts semantic integrity and impedes reconstruction, we utilize the resulting reconstruction discrepancy to precisely quantify fine-grained contamination intensity and derive instance-level quality scores. These scores are integrated into a hierarchical learning strategy: at the feature level, a quality-weighted contrastive objective is designed to adaptively suppress the propagation of noise; at the fusion level, a high-quality global consensus is constructed via quality-weighted aggregation, which is subsequently utilized to align and rectify local views via mutual information maximization. Extensive experiments on five benchmark datasets demonstrate that QARMVC consistently outperforms state-of-the-art baselines, particularly in scenarios with heterogeneous noise intensities.
arXiv:2604.17899v2 Announce Type: replace
Abstract: Unlike macro-expression, micro-expression does not follow a strictly consistent mapping rule between emotions and Action Units (AUs). As a result, some micro-expressions share identical AUs yet represent completely opposite emotional categories, making them highly visually similar. Existing microexpression recognition (MER) methods mostly rely on explicit facial motion cues (e.g., optical flow, frame differences, AU features) while ignoring implicit emotion information. To tackle this issue, this paper presents a Motion Emotion Feature Decoupling Network (MEDN) for MER. We design a dual-branch framework to separately extract motion and emotion features. In the motion branch, an AU-detection task restricts features to the explicit motion domain, and orthogonal loss is adopted to reduce motion emotion feature coupling. For implicit emotion modeling, we propose a Sparse Emotion Vision Transformer (SEVit) that sparsifies spatial tokens to highlight local temporal variations with multi-scale sparsity rates. A Collaborative Fusion Module (CoFM) is further developed to fuse disentangled motion and emotion features adaptively. Extensive experiments on three benchmark datasets validate that MEDN effectively decouples motion and emotion features and achieves superior recognition performance, offering a new perspective for enhancing recognition accuracy and generalization.
arXiv:2607.14726v1 Announce Type: new
Abstract: Air-to-air (A2A) unmanned aerial vehicle (UAV) tracking is fundamental to airborne remote sensing of low-altitude aerial targets. However, the deployment of continuous, real-time tracking systems on UAVs presents significant challenges. In A2A scenarios, traditional frame-based cameras suffer from severe performance degradation under low illumination, overexposure, and high-speed motion owing to their limited dynamic range and fixed temporal sampling. Although event cameras offer a promising alternative with microsecond temporal resolution and a high dynamic range, current research is bottlenecked by two primary issues: 1) the absence of dedicated A2A event-based datasets, and 2) the heavy reliance of existing trackers on GPU acceleration and extensive training data, rendering them impractical for resource-constrained UAVs. To bridge these gaps, we introduce AE-UAV, an air-to-air event-based UAV tracking benchmark. To the best of our knowledge, this is the first airborne-captured event camera dataset for A2A tracking, comprising 178 flight sequences with continuous-time cubic B-spline annotations. Furthermore, we propose the Fast-Slow Frequency-domain Tracking (FSFT) method. This lightweight, training-free framework seamlessly integrates frequency-domain template matching with search region prediction and detection-based drift correction. Extensive experiments demonstrate that FSFT operates at an ultra-fast 420 frames per second (FPS) on CPU-only hardware. It retains 93.97% of the accuracy of state-of-the-art GPU-dependent methods while delivering a 5.32-fold effective speedup and exhibiting superior temporal resolution generalization, thereby providing a highly efficient and robust solution for airborne remote sensing of aerial targets. The dataset and source code are available at https://github.com/MSP-xEN/AE-UAV.
arXiv:2607.15209v1 Announce Type: new
Abstract: Multilingual pre-trained language models (PLMs) exhibit degraded performance on low-resource, non-Latin-script languages, driven by high out-of-vocabulary (OOV) rates and excessive subword fragmentation that result from Latin-script-centric tokenizer training. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting the two highest-resource Ge'ez-script languages, Amharic and Tigrinya, and further evaluated on 17 additional low-resource African languages (19 total). We train a language-specific SentencePiece tokenizer on curated Amharic and Tigrinya monolingual corpora, extend XLM-R's vocabulary with 30,000 Ge'ez-script subwords derived from this tokenizer, and initialize their embeddings by averaging the embeddings of their constituent subwords under XLM-R's original tokenizer. VEXMLM is trained in two stages: (1) continued masked language modeling over the extended vocabulary on the curated corpora, and (2) supervised fine-tuning on question answering (QA), named entity recognition (NER), and sentiment analysis (SA). On Amharic/Tigrinya QA, VEXMLM achieves 87.0 EM /90.0 F1, versus 66.0 EM/78.0 F1 for XLM-R and 74.0 EM/ 78.0 F1 for Glot500. On SA, VEXMLM reaches 80.0\% accuracy versus 77.0\% (XLM-R) and 46.0\% (Glot500). On NER, VEXMLM raises OOV-token entity accuracy from 81.4\% to 94.3\%, averaged over 11 of the 19 evaluated languages for which OOV analysis was possible. Our contributions are: (i) a vocabulary-extension and embedding-initialization procedure tailored to Ge'ez script; (ii) a two-stage training strategy under which vocabulary and continued-pretraining gains on Amharic/Tigrinya transfer to 17 typologically related, unaugmented African languages; and (iii) an evaluation spanning both intrinsic tokenization metrics (vocabulary coverage, fertility, OOV rate) and extrinsic task performance across all 19 languages.
arXiv:2607.15215v1 Announce Type: new
Abstract: Stochastic binary networks are widely used to describe collective dynamics in complex systems and to perform neuromorphic computation, yet realistic networks often contain both asymmetric interactions and finite signal propagation times that fall outside conventional theories. Here we study stochastic binary networks with asymmetric and time-delayed interactions motivated by experimental observations in coupled superparamagnetic tunnel junctions. We find that time delay fundamentally reshapes the dynamics induced by anti-symmetric couplings, producing strong oscillatory temporal correlations consistent with experiment. At the same time, sufficiently long delays drive the steady-state probabilities toward equal state occupations even in strongly coupled systems. These apparently featureless probability distributions coexist with pronounced temporal correlations, distinguishing them from equilibrium high-temperature behavior. We further show analytically that delay-induced uniform distributions emerge in a broad class of stochastic networks, while symmetry-breaking bias fields restore interaction-dependent steady states with qualitatively modified behavior. Simulations of networks with five coupled spins demonstrate that these effects persist beyond minimal systems with only two spins. Our results establish a unified framework for stochastic binary networks in the intermediate regime between symmetric instantaneous interactions and asymmetric or time-delayed interactions, and suggest that asymmetry and delay can be exploited as functional resources in neuromorphic hardware and complex network dynamics.
arXiv:2607.15082v1 Announce Type: new
Abstract: Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two complementary approaches for newspaper structure understanding. First, we present a modular bottom-up pipeline that combines state-of-the-art open-source models: YOLO for layout detection, LayoutReader for reading order prediction, and a custom algorithm for article segmentation. This approach leverages existing robust components while maintaining flexibility and interpretability. Second, we introduce Tiramisu (Tiered Transformers for Hierarchical Structure Understanding), a novel end-to-end transformer-based architecture that explicitly models document hierarchy through an iterative tiered process. Tiramisu performs section and article separation, block localization, semantic categorization, and reading order prediction using highly parallelized attention mechanisms. Finally, we release Finlam La Libert\'e, a new dataset designed specifically for evaluating hierarchical information retrieval in historical newspapers. Experimental results demonstrate the effectiveness of both approaches in reconstructing complex newspaper hierarchies, with comparative analysis highlighting their respective strengths for scalable document digitization. The Tiramisu training code, including the synthetic newspaper generator, is available at https://git.litislab.fr/tiramisu/tiramisu-newspaper-articles-extractor.
arXiv:2607.15216v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) often introduce errors when generating image captions, resulting in misaligned image-text pairs. Our work focuses on a class of captioning errors that we refer to as systematic misalignments, where a recurring error in MLLM-generated captions is closely associated with the presence of a specific visual feature in the paired image. Given a vision-language dataset with MLLM-generated captions, our aim in this work is to detect such errors, a task we refer to as systematic misalignment detection. As our first key contribution, we present Symbal, which utilizes a structured, dual-stage setup with off-the-shelf foundation models to identify systematic misalignments and summarize results in natural language. As our second key contribution, we introduce SymbalBench, a benchmark designed to evaluate automated methods on our proposed task. SymbalBench consists of 1.7 million image-text pairs from two domains (natural and medical images), organized into 420 vision-language datasets with annotated systematic misalignments. Symbal exhibits strong performance on this benchmark, correctly identifying systematic misalignments in 63.8% of datasets, a nearly 4x improvement over the closest baseline. We supplement our evaluations on SymbalBench with real-world evaluations, showing that (1) Symbal can accurately surface systematic misalignments in captions generated by four MLLMs and (2) Symbal is a powerful tool for auditing off-the-shelf image-caption datasets. Ultimately, our novel task, method, and benchmark can aid users with auditing MLLM-generated captions and identifying critical errors, without requiring access to the underlying MLLM. Code is available at https://github.com/Stanford-AIMI/Symbal.
arXiv:2607.14886v1 Announce Type: new
Abstract: Temporal Knowledge Graph (TKG) reasoning under the extrapolation setting focuses on forecasting future time-stamped events (facts) from historical data in a temporal knowledge graph. Existing approaches, reinforcement learning (RL)-based multi-hop reasoning methods are prominent for TKG reasoning because they produce human-interpretable predictions via explicit multi-hop path tracing. However, during RL training, rewards are typically sparse, and exploration is highly inefficient due to the vast, time-evolving action space. These issues hinder efficient training and often limit overall performance. To address these challenges, we propose RAPTOR (Reachability-Aware Pretraining for Efficient Target-Oriented Path Exploration), a self-supervised pretraining method that injects a reachability-aware inductive bias to the agent. By learning to estimate the reachability of candidate actions to the target entity, RAPTOR reduces exploration over unpromising paths and provides a strong initialization for downstream RL fine-tuning. Experimental results on the ICEWS14, ICEWS05-15, and ICEWS18 datasets demonstrate that RAPTOR pretraining markedly improves the training efficiency and consistently outperforms conventional baselines, establishing it as an effective approach for enhancing RL-based multi-hop reasoning methods for TKG reasoning.
arXiv:2607.14988v1 Announce Type: new
Abstract: Stabilizer codes are often constructed within the Calderbank--Shor--Steane (CSS) framework, where two mutually orthogonal binary classical codes define $X$ and $Z$-type stabilizer generators. While this structure is algebraically convenient, additional non-CSS constraints may help suppress low-weight logical operators and improve decoding performance in the finite-length regime. We thus introduce quantum XYZ stabilizer codes, whose parity-check matrix (PCM) is built from three pairwise orthogonal binary PCMs associated with $X$-, $Y$-, and $Z$-type stabilizer generators. A nontrivial point is that an XYZ code instance is not automatically genuinely non-CSS: the same stabilizer group may admit a CSS generating set. We characterize this collapse, obtaining algebraic and rank conditions for deciding when the $Y$-type checks are redundant and when they define genuinely non-CSS stabilizer constraints. We also derive upper and lower bounds on the quantum minimum distance, including bounds for mixed Pauli logical operators. The novel framework includes a known non-CSS topological code, namely the XYZ$^2$ hexagonal code, and yields also sparse finite-length quantum low-density parity-check (qLDPC) constructions from intersecting-subset and quasi-dyadic code families. Simulations under depolarizing code-capacity noise and quaternary belief propagation decoding show that the proposed XYZ qLDPC instances can outperform representative CSS qLDPC instances with similar finite-length parameters.
arXiv:2607.07688v2 Announce Type: replace-cross
Abstract: How close to singularity can an $n \times n$ unimodular matrix be? For ternary cases as $n$ increases, exact expressions are unlikely, but upon fixing $n=4$ and assessing $(2k+1)$-ary cases as $k$ increases, we make significant progress; similarly for $(k+1)$-ary cases of $4\times 4$ nonnegative unimodular matrices.
arXiv:2607.14871v1 Announce Type: new
Abstract: In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays a critical role in downstream tasks. Yet most time-series forecasters are trained with symmetric objectives (e.g., MSE, MAE) and evaluated primarily on aggregate error, which can mask failures in extreme-values and peak-timing predictions. We introduce Asymmetric Peak-Aware Loss (APAL), a simple, model-agnostic objective that (i) penalizes under-predictions more heavily and (ii) increases the training weight of peak regions within each forecast window. We further propose a peak-critical evaluation protocol that complements MAE/MSE with channel-wise tail error (Top-10% and Top-1%) and peak metrics (precision, recall, F1 under timing tolerance, and peak timing error). We evaluate APAL on long-horizon multivariate forecasting across five state-of-the-art backbones, with a focus on pedestrian demand forecasting using (i) a production-ready subset of the City of Melbourne pedestrian hourly count dataset and (ii) a beach visitor count dataset. The generality of the loss function for time-series forecasting is tested on additional benchmarks. Across peak-critical datasets and settings, APAL improves tail accuracy and peak-prediction quality while exposing a controllable trade-off with aggregate error, making it a practical solution when peak-prediction failures are the dominant operational concern.