arXiv:2606.07130v1 Announce Type: new
Abstract: As AI systems become more widely adopted, the demand for factual and faithful generation grows. Properly attributing information through citations becomes, therefore, crucial. This work introduces FullCite, a framework that, in contrast to most previous works, generates structured inline citations linking each claim to both its source document and supporting evidence. FullCite proposes three strategies to inline citation generation: prompt-based generation, constrained decoding over a citation grammar, and posthoc span alignment. Using three question answering benchmarks, namely, ASQA, BioASQ, and ExpertQA, we assess citation quality and faithfulness along three dimensions: document-level correctness, evidence span identification, and claim-citation faithfulness. Our evaluation shows that while LLMs are generally effective at identifying relevant documents, they struggle to identify the precise supporting spans within them. This gap suggests that achieving faithful attributed QA will require research to place greater emphasis on precise evidence span identification.
Science Journals
arXiv:2606.07147v1 Announce Type: new
Abstract: Laser plasma accelerators (LPAs) are a promising platform for compact radiation sources. For a wide range of applications, including radiotherapy, ultrafast electron diffraction and time-resolved imaging, stable operation at high repetition rates is essential in order to deliver competitive average particle flux. Here we demonstrate the first LPA driven by an industrial-grade ytterbium-doped yttrium aluminium garnet (Yb:YAG) laser, designed for high-average-power operation. The picosecond laser pulses are post-compressed in a multi-pass cell to 50 fs duration and used to drive the interaction. The electron accelerator is operated in burst mode, at repetition rates tuneable from 0.625 to 6.25 kHz, representing a substantial increase compared to the state-of-the-art. Across this range, the electron beam properties remain unchanged, with average charges of 10-12 pC per shot, divergences of 50-70 mrad, and Maxwellian-like spectra extending to a few MeV. Numerical simulations capture the key features of the experimental observations and indicate acceleration in the self-modulated regime, enabled by relativistic self-focusing in near-critical-density plasma. Combining industrial high-average-power laser technology with plasma-based acceleration, these results represent a key step toward scalable, compact high-repetition-rate electron sources for medical, imaging and industrial applications.
arXiv:2606.07287v1 Announce Type: new
Abstract: Green's function-based downfolding methods construct effective Hamiltonians of reduced dimension that capture dynamical correlations of an electronic environment through effective potentials acting on the active space only. Using methods based on the constrained random phase approximation (cRPA) and moment RPA (mRPA), we construct static effective Hamiltonians that include screening through the environment. We derive expressions for the energy contribution from the environment and for the effective one- and two-body terms, taking into account double-counting corrections. cRPA requires additional consideration due to its frequency dependence, while mRPA provides a static Hamiltonian by construction. For the ground state energy of benzene and bond dissociation curves, we discuss the differences and similarities between the different flavors of RPA-based screening. We show that downfolding using cRPA describes both dynamical and strong correlation well, while mRPA and cRPA restricted to screening the particle-hole matrix elements can fail to describe bond dissociation due to a dominating dynamical correlation term. In the static limit, these two methods are shown to be almost indistinguishable.
arXiv:2606.07297v1 Announce Type: new
Abstract: Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary prediction problem (e.g., resolved or unresolved), neglecting fine-grained agent capabilities such as repository understanding, context retrieval, code localization, and bug diagnosis. In this paper, we introduce SWE-Explore, a benchmark that isolates the evaluation of repository exploration, a critical capability of coding agents. Given a repository and an issue, SWE-Explore asks an explorer to return a ranked list of relevant code regions under a fixed line budget. SWE-Explore covers 848 issues across 10 programming languages and 203 open-source repositories. For each instance, we derive line-level ground truth from independent agent trajectories that successfully solved the same issue, distilling the specific code regions their solution paths actually consulted. We evaluate exploration along coverage, ranking, and context-efficiency dimensions, showing that these metrics strongly track downstream repair behavior. Across a broad set of retrieval methods, general coding agents, and specialized localizers, we find that agentic explorers form a clear tier above classical retrieval. While file-level localization is already strong for modern methods, line-level coverage and efficient ranking remain the key axes differentiating state-of-the-art explorers.
arXiv:2606.07367v1 Announce Type: new
Abstract: Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge. A key difficulty lies in credit assignment: agents often receive delayed rewards only at the end of episodes. In this paper, we propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning within a principled in-distribution reinforcement learning paradigm. In each evolving iteration, our method learns an in-distribution critic from a hybrid off-policy dataset that combines expert demonstrations with agent-generated trajectories, stabilizing Bellman backups in sparse-reward settings via a weighted Implicit Q-Learning objective. The learned value function is then used to derive step-wise process rewards through advantage estimation, enabling dense and reliable supervision without environment backtracking or human annotation. Leveraging these signals, we perform behavior-proximal policy optimization that evolves the agent over the data used for process reward labeling, allowing iterative self-improvement without exacerbating distribution shift. We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance. Our results demonstrate that stable agent self-evolution is achievable through the co-evolution of process-level supervision and policy, both grounded within a shared in-distribution learning loop.
arXiv:2606.07386v1 Announce Type: new
Abstract: Modern imitation-learning policies for robot manipulation often represent actions as fixed-resolution action chunks, which are simple and effective but expose limited geometric and temporal structure before execution. This paper studies Spline Policy (SP), a structured representation that replaces action chunks with spline parameters while keeping the policy backbone unchanged. The predicted spline can be decoded as a compact continuous trajectory, queried at different temporal resolutions, constrained or edited in parameter space, and passed to downstream controllers. For quadratic spline outputs, the same representation can also be converted into a state-dependent vector field through an analytical distance-field construction. Under the regularity and projection assumptions of this construction, the induced dynamics do not increase the distance to the generated spline, yielding a principled local corrective mechanism around the predicted motion. The spline output further supports uncertainty propagation from observations to spline parameters, trajectories, and flow fields, and can be combined with classical control mechanisms such as null-space collision avoidance without retraining the policy backbone. We instantiate SP with diffusion, flow-matching, transformer-based, and vision-language-action backbones. Experiments in low-dimensional motion learning, simulated manipulation under matched backbones, dexterous manipulation, and real-robot case studies show that SP remains compatible with modern policy learners while exposing useful motion-structure properties, including compact decoding, temporal resampling, local correction around predicted motions, uncertainty evaluation, and controller compatibility.
arXiv:2606.07394v1 Announce Type: new
Abstract: In Video Instance Segmentation (VIS), classification, segmentation, and tracking objectives are jointly evaluated, but their individual contributions to performance loss remain opaque. We introduce a diagnostic framework that formulates identity and class assignment as an Integer Linear Program (ILP), yielding a model-agnostic oracle that hierarchically isolates each error source. Applied to seven VIS methods spanning online and offline paradigms across YouTube-VIS 2019/2021 and a diagnostic subset of OVIS, our analysis reveals a consistent picture. Tracking instability is a critical bottleneck for online methods, with gaps exceeding 20 AP under heavy occlusion, and grows sharply with video length and instance density. While semantic classification contributes meaningfully on standard benchmarks, its impact becomes negligible where tracking fails most. Although stronger backbones substantially lift default scores, they leave AP tracking gaps largely intact, confirming that temporal fragility is algorithmic rather than purely representational. To complement the oracle, we introduce TrackLens, a visual tool that translates gap magnitude into observable, query-level failure modes. Together, these tools provide a systematic foundation for targeting VIS's core challenge: robust long-term temporal association.
arXiv:2606.07401v1 Announce Type: new
Abstract: Document parsing systems are increasingly deployed in high-stakes, regulated workflows such as mortgage underwriting, financial reporting, supply-chain logistics, and clinical records. Yet most public benchmarks evaluate parsers on clean academic layouts or synthetic prose, and report a single OCR or markdown-level similarity score. Such documents and metrics correlate poorly with what downstream agents actually need: the correct value for a specific field on a messy real-world page. We introduce RealDocBench, a two-track benchmark built from real regulated documents. The QA track contains 1,356 field-level questions over 581 documents spanning four domains, where each question is paired with a typed gold_dict of key-to-value answers and parsers are scored on both per-field and strict per-question accuracy. The layout track contains 1,500 human-verified page images annotated with COCO-style bounding boxes under a nine-class public taxonomy, scored with a Hungarian matcher that includes adjacency-aware split/merge recovery. We evaluate eighteen systems, spanning commercial parsing APIs, general-purpose VLMs, and open-source OCR models, under a uniform extraction-and-scoring protocol, and report accuracy alongside per-page cost and cache-busted latency. RealDocBench exposes a wide performance spread that single-number benchmarks hide, a persistently hard medical sub-domain, and sharp cost/latency trade-offs across operating points. We release the datasets, parser adapters, and evaluation harness to support reproducible, field-level comparison of document parsing systems.
arXiv:2606.07502v1 Announce Type: new
Abstract: Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlying this deficiency. Our motivation stems from an unexpected observation: text embeddings tend to align with frequent but uninformative tokens when projected onto the vocabulary space. We argue that this excessive expression of high-frequency tokens suppresses the model's ability to capture nuanced semantics. To address this, we introduce EmbedFilter, a simple linear transformation designed to refine text embeddings derived from LLMs directly. Specifically, we uncover that the unembedding matrix within LLMs encodes a latent space that is actively writing these frequent tokens into embedding space. By filtering out this subspace, EmbedFilter suppress the influence of high-frequency tokens, thereby enhancing semantic representations. As a compelling byproduct, this enables an inherent dimensionality reduction, lowering index storage and speedup retrieval while fully preserving the refined embedding quality. Our experiments across multiple LLM backbones demonstrate that LLMs equipped with EmbedFilter achieve superior zero-shot downstream performance even with significantly reduced embedding dimensions. We hope our findings provide deeper insights into the mechanisms of LLM-based representations and inspire more principled designs to improve text embeddings training. Our code is available at https://github.com/CentreChen/EmbFilter.
arXiv:2606.07503v1 Announce Type: new
Abstract: We propose Differences in Detection (DnD), an intuitive method to compare two object detection models. Based on the same matching algorithm, it complements the standard metrics of mean Average Precision ($mAP$) and TIDE error analysis with the ability to compare two models directly. More specifically, we calculate the intersection of ground truth labels that are recognized by both models, followed by the corresponding difference sets and the complement set of ground truth labels that are missed by both models. The resulting comparison is more direct and intuitive than a comparison of independent summary statistics. It reveals individual and shared mistakes and becomes particularly interesting when combined with error types. In this case, the differences in detection errors can be analyzed naturally in a standard confusion matrix. While valuable in itself, we believe that one of the best applications of DnD is to guide explainability methods such as ODAM towards metric-relevant examples, grounded in structured subsets. The code for our method is available here: https://github.com/JohannesTheo/differences-in-detection
arXiv:2606.07506v1 Announce Type: new
Abstract: The object manipulation capabilities of quadruped robots is an open research challenge. While previous studies have focused on low-level policy learning, task execution still relies on expert-designed high-level trajectories. Autonomous selection of both an affordable interaction point on the target object and an affordable robot base pose removes the need for pre-designed trajectories. This study proposes a three-level hierarchical reinforcement learning (RL) framework that utilizes pose affordances to guide the navigation policy, while the navigation policy drives the locomotion policy. In addition, the pedipulation policy is guided by interaction-point affordances, enabling object-centric pose alignment of the quadruped robot and effective end-effector manipulation planning. We train the proposed framework in the IsaacSim ecosystem and evaluate it in both simulation and real-world settings. We investigate the effectiveness of pose affordance across multiple scenarios in simulation while various object interaction tasks are validated on real-world setting forming an object-interaction dataset. The results show that the proposed framework can autonomously identify candidate poses based on their affordance and successfully execute object manipulation tasks in the real world without human guidance.
arXiv:2606.07508v1 Announce Type: new
Abstract: We introduce StreamForce, a streaming video generation framework that enables physically grounded control through continuous force inputs. Unlike prior video models that train separate models for different force types, assume fixed forces, or rely on non-causal processing, StreamForce is a causal and unified model that responds instantly and coherently to both local and global, time-varying forces. To achieve this, we design a unified force representation as a control signal and develop a distillation pipeline for force-controllable video generation. Our model combines autoregressive efficiency with force responsiveness, sustaining stable photometric and dynamic realism. StreamForce runs at up to 16.6 FPS on a single GPU, achieving state-of-the-art performance in both force adherence and motion realism. Project website: https://neu-vi.github.io/StreamForce/
arXiv:2606.07514v1 Announce Type: new
Abstract: In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, Gaussian primitives are arranged along rays and radial distances in a ray-based universal representation, while 2D semantic and 3D spatial features extracted from UniK3D-inspired encoders are jointly decoded to generate the complete Gaussian cloud. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems across various scenes. The benchmark is further stratified by field of view (FoV) to enable fine-grained assessment of the universal monocular rendering task. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. The project page can be found at: https://insta360-research-team.github.io/Unisharp-website/
arXiv:2601.12359v1 Announce Type: cross
Abstract: Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful or unintended outputs. Despite advances in alignment, even state-of-the-art LLMs remain broadly vulnerable to adversarial prompts, underscoring the urgent need for robust, productive, and generalizable detection mechanisms beyond inefficient, model-specific patches. In this work, we propose Zero-Shot Embedding Drift Detection (ZEDD), a lightweight, low-engineering-overhead framework that identifies both direct and indirect prompt injection attempts by quantifying semantic shifts in embedding space between benign and suspect inputs. ZEDD operates without requiring access to model internals, prior knowledge of attack types, or task-specific retraining, enabling efficient zero-shot deployment across diverse LLM architectures. Our method uses adversarial-clean prompt pairs and measures embedding drift via cosine similarity to capture subtle adversarial manipulations inherent to real-world injection attacks. To ensure robust evaluation, we assemble and re-annotate the comprehensive LLMail-Inject dataset spanning five injection categories derived from publicly available sources. Extensive experiments demonstrate that embedding drift is a robust and transferable signal, outperforming traditional methods in detection accuracy and operational efficiency. With greater than 93% accuracy in classifying prompt injections across model architectures like Llama 3, Qwen 2, and Mistral and a false positive rate of <3%, our approach offers a lightweight, scalable defense layer that integrates into existing LLM pipelines, addressing a critical gap in securing LLM-powered systems to withstand adaptive adversarial threats.
arXiv:2606.06522v1 Announce Type: cross
Abstract: Let $G$ be an $n$-vertex graph with $e(G)\ge n^2/k$. We prove a self-contained internal short-cycle core theorem at the threshold $k\le n^{1/3}$: the graph $G$ contains a subgraph $H_6$ with $\Omega(n^2/k^3)$ edges in which every two distinct edges lie together on a cycle of length at most $6$ contained in $H_6$, and a subgraph $H_8$ with $\Omega(n^2/k^2)$ edges in which every two distinct edges lie together on a cycle of length at most $8$ contained in $H_8$. In density notation $\rho=e(G)/n^2$, this gives internal cores of sizes $\Omega(\rho^3n^2)$ and $\Omega(\rho^2n^2)$ throughout the range $\rho\ge n^{-1/3}$.
The $C_{\le6}$ conclusion above is an edge-connected statement and does not impose the adjacent-edge $C_4$ condition appearing in the strongest Duke--Erd\H{o}s--R\"odl formulation. We also include two complementary results clarifying this distinction. First, under the ambient-witness convention, every graph with at least $n^2/k$ edges and $k=o(n^{1/2})$ contains $\Omega(n^2/k^3)$ selected edges whose pairs are witnessed by ambient cycles of length at most $6$, with adjacent pairs witnessed by ambient $C_4$'s. Second, under the standard internal strong $C_6$ convention, for every fixed $\beta\in[1/3,1/2)$ there is an infinite sequence of bipartite graphs $G$ with $n\to\infty$ and $e(G)=\Theta_\beta(n^{2-\beta})$ such that every internally strongly $C_6$-connected subgraph has only $O_\beta(\rho(G)^3n^2/(\log n)^2)$ edges. The obstruction is a random cyclic shift-lift of $K_{q,q}$, together with an occupancy estimate excluding large aligned two-covers.
arXiv:2606.06537v1 Announce Type: cross
Abstract: Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early detection essential for effective treatment. Mammography is the primary screening modality; however, accurate delineation of suspicious lesions remains challenging and subject to inter-observer variability. Automated segmentation methods can assist radiologists by providing consistent and efficient lesion localization.
This study presents DSU-Net, an attention-enhanced Dense Skip U-Net architecture for automated breast lesion segmentation in mammographic images. The proposed framework integrates dense skip connections and attention mechanisms to improve feature propagation, preserve spatial information, and enhance lesion boundary delineation. Experiments were conducted using the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). To address severe foreground-background imbalance, a composite loss function combining Dice loss, focal loss, and binary cross-entropy loss was employed during training.
The proposed model achieved a Dice Similarity Coefficient of 0.9421, an Intersection over Union of 0.8905, an accuracy of 0.9711, and an AUC-ROC of 0.9878 on the validation dataset. Qualitative evaluation demonstrated accurate delineation of lesions with varying sizes and morphologies, while quantitative results confirmed robust discrimination between lesion and background regions.
These findings demonstrate that DSU-Net provides accurate and reliable breast lesion segmentation in mammographic images and highlights the potential of attention-guided deep learning for computer-aided breast cancer screening and diagnosis.
arXiv:2606.07460v1 Announce Type: cross
Abstract: Low signal-to-noise ratios are a common problem in experiments attempting to measure photon-photon scattering. In the optical regime, where petawatt lasers with femtosecond pulse durations are used, the large beam sizes cause the major contribution of the background to be spread over up to 100 ps in arrival time, whereas the signal is confined to the femtosecond scale. We present a balanced homodyne measurement scheme, which exploits this property to suppress the background. By interfering the signal with a short reference pulse, the measurement becomes effectively gated to the pulse duration and is therefore only sensitive to the co-timed part of the light, reducing the effective background by 3-4 orders of magnitude. Additionally, increasing the reference pulse energy increases the amplitude of the measured quantity without changing the intrinsic signal-to-noise ratio. Using this property, other external noise sources can be made negligible by boosting the measured quantity above the noise floor. Using two-dimensional detectors further enhances the scheme by improving sensitivity and enabling self-referenced single-pulse measurements. In addition, an evaluation procedure based on maximum-likelihood estimation is presented and demonstrated. The robustness and performance of this scheme are demonstrated on simulated data, where a more than 100-fold reduction of measurement time compared to conventional photon-counting methods under realistic conditions is found.
arXiv:2403.05532v2 Announce Type: replace
Abstract: We introduce Tune without Validation (Twin), a simple and effective pipeline for tuning learning rate and weight decay of homogeneous classifiers without validation sets, eliminating the need to hold out data and avoiding the two-step process. Twin leverages the margin-maximization dynamics of homogeneous networks and an empirical scaling law that links training and test losses across hyper-parameter configurations. This mathematical modeling yields a regime-dependent, validation-free selection rule: in the non-separable regime, training loss is monotonic in test loss and therefore predictive of generalization, whereas in the separable regime, the parameters' norm becomes a reliable indicator of generalization due to margin maximization. Across 37 dataset-architecture configurations for image classification, we demonstrate that Twin achieves a mean absolute error of 1.28% compared to an Oracle baseline that selects HPs using test accuracy. We demonstrate Twin's benefits in scenarios where validation data is scarce, such as small-data regimes, or difficult and costly to collect, as in medical imaging. Code available at https://github.com/lorenzobrigato/twin.
arXiv:2502.00527v2 Announce Type: replace
Abstract: The KV cache in large language models is a dominant factor in memory usage, limiting their broader applicability. Quantizing the cache to lower bit widths is an effective way to reduce computational costs; however, previous methods struggle with quantizing key vectors due to outliers, resulting in excessive overhead. We propose a novel quantization approach called PolarQuant, which efficiently addresses the outlier challenge. We observe that outliers typically appear in only one of two dimensions, which are rotated together by a specific angle when rotary position embeddings are applied. When represented as two-dimensional vectors, these dimensions exhibit well-structured patterns, with radii and angles smoothly distributed in polar coordinates. This alleviates the challenge of outliers on per-channel quantization, making them well-suited for quantization. Thus, PolarQuant divides key vectors into groups of two-dimensional sub-vectors, encoding them as the corresponding quantized radius and the polar angle, rather than quantizing original key vectors directly. PolarQuant achieves the superior efficiency in KV cache quantization and accelerates the decoding process by turning the query-key inner product into a table lookup, all while maintaining the downstream performance of full-precision models.
arXiv:2502.16531v2 Announce Type: replace
Abstract: We consider multi-robot systems under recurring tasks formalized as linear temporal logic (LTL) specifications. To solve the planning problem efficiently, we propose a bottom-up approach combining offline plan synthesis with online coordination, dynamically adjusting plans via real-time communication. To address action delays, we introduce a synchronization mechanism ensuring coordinated task execution, leading to a multi-agent coordination and synchronization framework that is adaptable to a wide range of multi-robot applications. The software package is developed in Python and ROS2 for broad deployment. We validate our findings through lab experiments involving nine robots showing enhanced adaptability compared to previous methods. Additionally, we conduct simulations with up to ninety agents to demonstrate the reduced computational complexity and the scalability features of our work.
arXiv:2507.10924v2 Announce Type: replace
Abstract: Offset surfaces, defined as the Minkowski sum of a base surface and a rolling ball, play a crucial role in geometry processing, with applications ranging from coverage motion planning to brush modeling. While considerable progress has been made in computing constant-radius offset surfaces, computing variable-radius offset surfaces remains a challenging problem. In this paper, we present OffsetCrust, a novel framework that efficiently addresses the variable-radius offsetting problem by computing a power diagram. Let $R$ denote the radius function defined on the base surface $S$. The power diagram is constructed from contributing sites, consisting of carefully sampled base points on $S$ and their corresponding off-surface points, displaced along $R$-dependent directions. In the constant-radius case only, these displacement directions align exactly with the surface normals of $S$. Moreover, our method mitigates the misalignment issues commonly seen in crust-based approaches through a lightweight fine-tuning procedure. We validate the accuracy and efficiency of OffsetCrust through extensive experiments, and demonstrate its practical utility in applications such as reconstructing original boundary surfaces from medial axis transform (MAT) representations.
arXiv:2507.14550v2 Announce Type: replace
Abstract: Flight in turbulence is constrained not only by aerodynamic efficiency, but also by how strongly flow disturbances are transmitted into unsteady loads and dynamic responses. Although disturbance rejection is typically attributed to active control, birds often sustain fixed-wing gliding in disturbed air, suggesting that the wing itself may passively attenuate aerodynamic perturbations. Here, we show that avian wings reduce aerodynamic sensitivity to incoming disturbances. Compared with a geometrically matched airfoil wing, the avian wing exhibits lower lift-response gain, smoother stall transition, reduced force fluctuations, and a broader operative angle-of-attack range across turbulence intensities. These wing-level properties translate into an expanded passive stability envelope in rigid-flyer dynamics. Flow diagnostics indicate that this robustness is associated with delayed separation and redistribution of turbulent kinetic energy, which suppress large-scale flow instability and weaken disturbance transmission. This passive robustness comes at the cost of reduced aerodynamic efficiency, revealing an efficiency-robustness trade-off in disturbed flows. Our results identify aerodynamic sensitivity and control demand as essential metrics for flight performance in turbulence, and suggest passive aerodynamic robustness as a design principle for resilient flying systems.
arXiv:2602.22041v2 Announce Type: replace
Abstract: Heralding the advent of autonomous vehicles and mobile robots that interact with humans, responsibility in spatial interaction is burgeoning as a research topic. Even though metrics of responsibility tailored to spatial interactions have been proposed, they are mostly focused on the responsibility of individual agents. Metrics of causal responsibility focusing on individuals fail in cases of causal overdeterminism - when many actors simultaneously cause an outcome. To fill the gaps in causal responsibility left by individual-focused metrics, we formulate a metric for the causal responsibility of groups. To identify assertive agents that are causally responsible for the trajectory of an affected agent, we further formalise the types of assertive influences and propose a tiering algorithm for systematically identifying assertive agents. Finally, we use scenario-based simulations to illustrate the benefits of considering groups and how the emergence of group effects vary with interaction dynamics and the proximity of agents.
arXiv:2602.22976v3 Announce Type: replace
Abstract: We present efficient parallel algorithms for computing maximal matchings in hypergraphs. Our algorithm finds locally maximal edges in the hypergraph and adds them in parallel to the matching. In the CRCW PRAM models our algorithms achieve $O(\log{\log{\Delta}}\log{m})$ time with $O(\kappa\log {m})$ work w.h.p. where $m$ is the number of hyperedges, and $\kappa$ is the sum and $\Delta$ is the maximum of all vertex degrees. The CREW PRAM model algorithm has a running time of $O((\log{\Delta}+\log{d})\log{m})$ and requires $O(\kappa \log {m})$ work w.h.p. It can be implemented work-optimal with $O(\kappa)$ work in $O((\log{m}+\log{n})\log{m})$ time. We prove a~$1/d$-approximation guarantee for our algorithms.
We evaluate our algorithms experimentally by implementing and running the proposed algorithms on the GPU using CUDA and Kokkos. Our experimental evaluation demonstrates the practical efficiency of our approach on real-world hypergraph instances, yielding a speed up of up to 76 times compared to a single-core CPU algorithm.
arXiv:2604.09552v2 Announce Type: replace
Abstract: Engineering rulebooks and technical standards contain multimodal information like dense text, tables, and illustrations that are challenging for retrieval augmented generation (RAG) systems. Building upon the DesignQA framework [1], which relied on full-text ingestion and text-based retrieval, this work establishes a Multimodal ColPali Enhanced Retrieval and Reasoning Framework (MCERF), a system that couples a multimodal retriever with large language model reasoning for accurate and efficient question answering from engineering documents. The system employs the ColPali, which retrieves both textual and visual information, and multiple retrieval and reasoning strategies: (i) Hybrid Lookup mode for explicit rule mentions, (ii) Vision to Text fusion for figure and table guided queries, (iii) High Reasoning LLM mode for complex multi modal questions, and (iv) SelfConsistency decision to stabilize responses. The modular framework design provides a reusable template for future multimodal systems regardless of underlying model architecture. Furthermore, this work establishes and compares two routing approaches: a single case routing approach and a multi-agent system, both of which dynamically allocate queries to optimal pipelines. Evaluation on the DesignQA benchmark illustrates that this system improves average accuracy across all tasks with a relative gain of +41.1% from baseline RAG best results, which is a significant improvement in multimodal and reasoning-intensive tasks without complete rulebook ingestion. This shows how vision language retrieval, modular reasoning, and adaptive routing enable scalable document comprehension in engineering use cases.