Computer Vision
AgriScope: Pixel-Grounded Multimodal Understanding for Agricultural Images
Abderrahmene Boudiaf, Mohamad Alanssari, Irfan Hussain et al. (+1 more)
Agricultural image understanding requires fine-grained recognition of plant diseases, pests, crop structures, and botanical species under complex real-world conditions. Despite recent advances in
Multimodal Large
Language Models (MLLMs), existing models remain limited to text-only outputs and lack pixel-level visual grounding capabilities. In this work, we introduce AgriScope, a unified pixel-grounded
multimodal framework for agricultural image understanding. AgriScope jointly supports image-level, region-level, and pixel-level understanding within a unified framework, enabling tasks such as grounded caption generation, referring expression
segmentation, and multi-turn
multimodal interaction for agricultural imagery. AgriScope integrates biologically specialized semantic representations with dense spatial grounding through biological-semantic encoding, dense spatial representations, and pixel decoding. To support large-scale grounded learning, we introduce AgriGround, a large-scale pixel-grounded agricultural
multimodal instruction-tuning
dataset containing over 500K images and 11M instruction-following samples spanning plant disease analysis, crop and weed identification, insect pest recognition, and fine-grained botanical understanding. AgriGround is constructed through a multi-stage automatic annotation pipeline that integrates
multimodal caption generation, phrase-level grounding,
segmentation mask generation, and task-oriented instruction synthesis to produce densely grounded supervision. Extensive experiments across multiple agricultural
vision-
language tasks demonstrate the effectiveness of AgriScope in pixel-grounded
multimodal understanding, establishing a strong
benchmark for agricultural
vision-
language learning and visual grounding. The
dataset and code will be made publicly available at (https://github.com/boudiafA/AgriScope)
Read the full abstract ▾
All authors Abderrahmene Boudiaf, Mohamad Alanssari, Irfan Hussain, Sajid Javed
Human-Computer Interaction
How Do We Visualize Space in Molecular Biology? A Study of Spatial Transcriptomics Visualization Practices
Denisse Chacón-Ramírez, Mark S. Keller, Eric Mörth et al. (+3 more)
A
cell's identity depends on where it sits in tissue: for example, a macrophage behaves differently in a tumor core than at its edge. Spatial transcriptomics has transformed how we study this by recovering that lost coordinate, but it does so by producing data that is simultaneously high-dimensional,
multimodal, and uncertain. Visualizing this combination is a hard problem in its own right, and one that warrants an assessment of how the field currently represents it, what has worked, and what is still missing. We surveyed 148 papers and 1,824 figure panels using a What-Why-How coding framework grounded in Munzner's nested model, connecting the data represented, the biological tasks motivating each visualization, and the design choices through which they are expressed; a subset of the surveyed work also contributed dedicated interactive visualization software that was not necessarily reflected in the static figures, and we looked at what interaction capabilities those tools supported as well. We close by outlining where the field stands and the challenges ahead for bioinformatics and visualization researchers to tackle together.
Read the full abstract ▾
All authors Denisse Chacón-Ramírez, Mark S. Keller, Eric Mörth, Nils Gehlenborg, Marc Streit, Andreas Hinterreiter
Artificial Intelligence
NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction
Qingde Li, Qingqi Hong, Zihan Li et al. (+1 more)
Three-dimensional reconstruction from unorganized point clouds remains a challenging problem in computer
vision,
geometric modeling, and computer-aided design. While neural implicit methods achieve impressive reconstruction accuracy, geometry is typically encoded in latent representations that limit interpretability and reuse within engineering workflows. We present NeuSOGA3D (Neuro-Symbolic Observation-Guided
Geometric Abstraction in 3D), a hybrid framework that combines learned perceptual priors inherited from NeuSOGA with explicit symbolic
geometric reasoning. The method projects point clouds onto principal orthographic planes, constructs symbolic implicit spline representations from the resulting observations, and fuses them through shape-preserving constructive solid geometry operations to generate a coarse visual hull. Additional
geometric detail is recovered through cross-sectional decomposition and volumetric reconstruction using Partial Shape-Preserving Splines. Unlike conventional neural implicit approaches, NeuSOGA3D progressively transforms observations into explicit symbolic entities, including control polygons, implicit spline fields, cross-sections, and volumetric lofts. Experiments on all forty categories of the ModelNet40
benchmark demonstrate the ability of the framework to recover structurally meaningful and CAD-compatible
geometric representations from diverse point-cloud observations. The results highlight the potential of combining learned perception with symbolic
geometric reasoning for explainable
geometric intelligence.
Read the full abstract ▾
All authors Qingde Li, Qingqi Hong, Zihan Li, Jie Tian
Computation and Language
To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals
Roy Eisenstadt, Ido Cohen, Edo Cohen-Karlik et al. (+2 more)
Speculative Decoding (SD) has significantly accelerated Large
Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff between two drafting strategies: neural drafting and context-based copying. Neural drafts (e.g., EAGLE3) provide robust performance across diverse text settings, while copy-based methods achieve higher speedups in copy-intensive regimes by generating candidates faster and exploiting long repetition spans for near-perfect speculation. We analyze existing copy-based methods and find that they are prone to accidental repetitions where surface-level n-gram overlap does not reflect a structural intent to copy, leading to false-positive triggers that ultimately degrade throughput. We introduce SwitchSD, an adaptive framework that treats copying as a latent control signal of the LLM. By training lightweight probes on the target model's internal representations, SwitchSD identifies genuine copy-intent with high precision (AUC > 0.99). This allows the system to dynamically switch between neural drafting (e.g., EAGLE) and context-based copying. Our results across Llama and Qwen families demonstrate throughput gains of up to 15% over state-of-the-art baselines like EAGLE3, effectively turning copying from a noisy heuristic into a principled, model-aware decoding regime.
Read the full abstract ▾
All authors Roy Eisenstadt, Ido Cohen, Edo Cohen-Karlik, Lior Wolf, Itamar Zimerman
Computer Vision
Needles in a Raystack: Ultra-Sparse LiDAR Occupancy Detection for Bat Tracks
Nico Klar, Pankaj Rana, Nizam Gifary et al. (+2 more)
Monitoring flying animals is important for understanding and protecting biodiversity, but nocturnal species such as bats are difficult to observe in the field. Using
LiDAR, bat movements at night result in ultra-sparse 3D spatio-temporal data in which standard reconstruction losses tend to predict only background and miss real flight paths. We study this problem as voxel-wise occupancy detection in sensor-centric
LiDAR raystacks. A lightweight 3D U-Net is proposed that preserves temporal resolution, uses skip connections for spatial detail, and combines weighted binary cross-
entropy with Dice loss to handle the strong class imbalance. In real
LiDAR recordings of bats over open fields, cross-checked with acoustic monitoring, a reconstruction-based 3D convolutional autoencoder baseline fails to recover foreground trajectories. In contrast, the proposed U-Net recovers sparse foreground occupancy in diagnostic experiments and produces coherent occupancy patterns along bat flight trajectories, providing a practical basis for validation-scale experiments, later clustering of flight tracks, and future integration of bat activity information into biodiversity-aware turbine curtailment strategies.
Read the full abstract ▾
All authors Nico Klar, Pankaj Rana, Nizam Gifary, Jakob Traub, Aamir Ahmad
Machine Learning · Cross-listed from math.DG
Special Lagrangian cones in Deep Learning
Tejas Kotwal and Govind Menon
We introduce a
matrix generalization of the cone of Harvey and Lawson and prove that it is an exact special Lagrangian
manifold. We further show that it belongs to a family of exact special Lagrangian
manifolds that foliate the balanced
manifold arising in deep learning.
Machine Learning
QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
Yujie Li, Zezhi Shao, Chengqing Yu et al. (+7 more)
Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training foundation models on massive
datasets to achieve accurate zero-shot
forecasting has emerged as a major research focus. However, current studies predominantly prioritize architectural innovations while insufficiently addressing data diversity, often relying on simple data sampling strategies that fail to manage complex data distributions effectively, leading to inefficient use of training data and suboptimal performance. To address this, we propose QUALS, a large-scale time series corpus
equilibrium framework. QUALS significantly enhances data efficiency, i.e., enabling existing models to achieve superior performance using only a small fraction of the original training data. Specifically, QUALS operates through two core mechanisms. First, a pattern quantization framework systematically decodes heterogeneous patterns from mixed corpora via vector quantization and uniform binning. Second, a learnability synchronization framework calibrates sampling weights for heterogeneous patterns, bridging the optimization gap between simple and complex motifs to maximize overall training efficiency. Extensive
benchmarks demonstrate that pre-training on QUALS consistently achieves superior zero-shot performance, even under substantially reduced training budgets.
Read the full abstract ▾
All authors Yujie Li, Zezhi Shao, Chengqing Yu, Yisong Fu, Weijie Zhu, Yifan Du, Jilin Hu, Bin Yang, Yongjun Xu, Fei Wang
Artificial Intelligence
MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents
Pritish Mishra, Ishaan Kumar, Akshat Mandoli et al. (+1 more)
Generally, most voice
agents are cascaded systems, i.e., an ASR model transcribes the caller's audio, a
language model reads the transcript and decides what to say and which backend tools to call, and a TTS model speaks the reply. Nearly all of the decision making happens in the
language model, but existing evaluations measure it either too broadly or too narrowly. End-to-end voice
benchmarks score the full pipeline, so recognition errors and model errors mix into a single number. LLM
benchmarks isolate the model but they do not evaluate what makes real phone calls hard, such as transcription issues, caller's voice being split across messages and the requirement that replies follow the
language and script specified. We introduce the Multi-Turn Voice
Agent Benchmark (MTVA-Bench), which evaluates the
language model on the same conditions it faces inside a cascaded system. The caller is played by an LLM following a set of rubrics and tool calls are answered by a mock backend which responds to the arguments the model actually sent. The
benchmark contains 49
agents working across 490 reviewed scenarios and supports 7
languages. Scoring is a combination of deterministic checks on tool calls with two LLM judges, one that scores scenario specific rules and one that grades conversation quality without access to the task. Both judges must cite specific messages from the transcript. Task and conversation scores are weighted equally, since a call can complete its task and still go badly for the caller. In a seven-model study, six of the models select the correct tool within 6.4 points of one another, but their overall scores span 24.4 points. Most of the gap comes from argument values, action ordering, rule compliance, and what the model says around its tool calls.
Read the full abstract ▾
All authors Pritish Mishra, Ishaan Kumar, Akshat Mandoli, Sudarshan Kamath
Computer Vision
Ischemic Stroke Segmentation and Net Water Uptake Quantification on Multicenter Non-Contrast CT Using Supervised Target-Domain Adaptation
Linus Britt, Maximilian Nielsen, Susan Klapproth et al. (+5 more)
Objectives: Quantitative assessment of infarct hypodensity on non-contrast computed
tomography (NCCT), including net water uptake (NWU), requires manual or semi-manual lesion delineation, often guided by CT perfusion or
diffusion-weighted MRI, limiting clinical applicability. Automated
segmentation on NCCT could enable efficient biomarker extraction such as NWU but remains challenging across heterogeneous multicenter data. This study aimed to develop and externally test a domain-aware deep learning framework for ischemic stroke
segmentation on NCCT and assess its suitability for NWU quantification. Materials & Methods: In this retrospective multicenter study of 801 patients from four
datasets, an nnU-Net-based model was trained on NCCT scans from the University Medical Center Hamburg-Eppendorf and the Acute Ischemic Stroke
Dataset. To adapt to new domains, the model was fine-tuned on target-domain subsets from Boston (n=11) and ISLES (n=75), with evaluation on held-out cases not used for fine-tuning. Automated
segmentations and NWU values were compared with expert references. Results: For lesions $\geq$ 30 mL, median Dice was 0.68 (Boston) and 0.56 (ISLES). Including smaller lesions, which predominated in ISLES, median Dice was 0.54 (interquartile range [IQR] 0.30-0.70) for acute lesion
segmentation (Boston
dataset) and 0.20 (IQR 0.03-0.41) for NCCT lesion
segmentations when compared to post-treatment infarct (primary target of the ISLES challenge). Automated NWU mean absolute error was 1.37 percentage points (SD 1.61, Boston). Conclusion: Target-domain adaptation supported NCCT-only infarct
segmentation across heterogeneous external cohorts, although performance varied across domains. The approach enabled low-error NWU quantification from baseline NCCT without advanced imaging, supporting further prospective clinical evaluation.
Read the full abstract ▾
All authors Linus Britt, Maximilian Nielsen, Susan Klapproth, Andre Kemmling, Michael H. Lev, Gabriel Broocks, Rene Werner, Thilo Sentker
Computer Vision
Task-Oriented Semantic Feature Transmission for Multi-Task Satellite Remote Sensing over Low-SNR Channels
Shuoyuan Sun, Hongyu Wang, Mugen Peng et al. (+1 more)
Conventional satellite remote sensing transmission follows a reconstruct-then-infer paradigm that optimizes pixel-level fidelity, creating an objective mismatch with downstream tasks such as classification and detection, especially at low SNR. This paper investigates a task-oriented framework that bypasses image reconstruction and directly transmits semantic features extracted by a multitask-pretrained backbone. A lightweight channel adaptation module (CAM) compresses feature dimensionality for bandwidth reduction, and a feature restorer recovers task-relevant structure after channel corruption. With the backbone frozen, the CAM and task-specific downstream heads are jointly optimized with task and feature-level supervision under random-SNR training. Under the adopted AWGN setting, experiments on scene classification and object detection show consistent gains over reconstruction-oriented JSCC baselines across different SNR conditions, with the largest improvements in the low-SNR regime.
Read the full abstract ▾
All authors Shuoyuan Sun, Hongyu Wang, Mugen Peng, Wenjia Xu
Computer Vision
Bridging Modalities on the Cortex: Surface-based MRI to PET Translation with a Diffusion Bridge
Yitong Li, Alexandra Samoylova, Fabian Bongratz et al. (+4 more)
Cortical hypometabolism measured by Fluorodeoxyglucose Positron Emission
Tomography (FDG-PET) is a highly sensitive biomarker for dementia diagnosis. However, high costs, radiation exposure, and limited accessibility constrain its clinical utility. While cross-modal synthesis from
Magnetic Resonance Imaging (MRI) offers a promising alternative, existing volumetric generation methods do not explicitly account for the highly folded cortical geometry, where disease-related patterns predominantly reside. To address this, we introduce a novel surface-based
diffusion bridge framework DB-SUiT for MRI-to-PET translation that operates natively on the cortical
manifold. A conditional Spherical U-shaped
vision Transformer (SUiT) is specifically designed to model the intricate cross-modal relationships while preserving surface
topology. It combines spherical convolutional encoders for multi-scale surface feature extraction with bottleneck
Transformers to capture long-range spatial dependencies, while incorporating demographic and subcortical conditions to refine the synthesis. Evaluated on two
datasets, including subjects with different dementia types, DB-SUiT demonstrates high-fidelity synthesis that substantially outperforms other baselines. In automated dementia classification, synthesized PET surfaces improve performance over MRI by 14.2% and PET volumes by 11.3%, approaching the performance of real PET surfaces. In a blinded reader study, synthetic PET achieved 85.5% diagnostic accuracy, compared with 75.8% for MRI and 95.2% for real PET. This further demonstrates cross-cohort and cross-pathology generalization, as the model was evaluated without retraining on an external cohort that included a dementia subtype not represented during training. Our code is available at https://github.com/ai-med/DB-SUiT.
Read the full abstract ▾
All authors Yitong Li, Alexandra Samoylova, Fabian Bongratz, Timo Grimmer, Dennis M. Hedderich, Igor Yakushev, Christian Wachinger
Human-Computer Interaction
Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants
Sebastian Maier, Kai Schwabe, Manuel Schneider et al. (+1 more)
Cognitive offloading to AI can reduce opportunities to practice skills, creating risks of deskilling. However, it remains unclear how to prevent deskilling without restricting access to AI. Here, we design two interventions to reduce offloading decisions: (1) metacognitive feedback that makes the implications of offloading for users explicit, and (2) an effort-based reward that incentivizes less extensive LLM assistance. We test both in a preregistered online experiment ($N = 704$) with a 2$\times$2 design and a no-AI control. The task was to practice fraction arithmetic with an LLM-based assistant that provided solutions only on explicit request, followed by an unaided test. Metacognitive feedback reduced answer offloading (OR $= 0.47$) and improved test performance (OR $= 1.51$). We found no evidence that the reward affected either outcome. Our results identify metacognitive feedback as a promising design choice to reduce cognitive offloading.
Read the full abstract ▾
All authors Sebastian Maier, Kai Schwabe, Manuel Schneider, Stefan Feuerriegel
Computer Vision
Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
Farooq Ahmad Wani, Maria Sofia Bucarelli, Mujtaba Hussain Mirza et al. (+5 more)
Vision-
language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs substantially more robust—e.g., rephrasing "Is there a cat?" into "Please look carefully and answer: is there a cat?". Conversely, VLMs become more fragile under corruption when the question is semantically complex or finer-grained, e.g., "what colour is the cup left of the chair?" instead of "is there a cup?". Both effects stem from question-conditioned cross-modal
attention, which induces a spectral filter over image patches: verbose questions broaden its frequency support, while fine-grained questions concentrate it onto fewer visual scales. The model's answer drifts most when this filter and the corruption sit on the same spatial frequencies. We test the filter view on Qwen3-VL and LLaVA-OneVision across GQA and CLEVR; verbose paraphrasing reduces drift variance by 70–81% on the 8B models. The practical recipe—pad the
prompt—further yields measurable gains in accuracy, even under image corruption.
Read the full abstract ▾
All authors Farooq Ahmad Wani, Maria Sofia Bucarelli, Mujtaba Hussain Mirza, Oleksandr Pryymak, Aryo Pradipta Gema, Iacopo Masi, Pasquale Minervini, Fabrizio Silvestri
Machine Learning
Fast-varying Natural Frequencies and Damping Ratio Identification for Linear Time-Varying System
Melisa Bozaci and Alice Cicirello
This work proposes a physics-enhanced machine learning approach for the system identification of Linear Time-Varying (LTV) systems under time-varying operating conditions in terms of fast-varying natural frequencies and damping ratios by combining a long short-term
memory network with an Extended Kalman Filter (EKF). The proposed approach uses vibration data (displacement and velocity measurements), domain knowledge of modal damping ratios, and a physics-based model that can yield an approximate natural frequencies time-dependency model. The approach is validated using synthetic data generated from a finite element model of a 2-blade offshore wind turbine under realistic environmental and operating conditions. This system displays fast time-varying frequencies due to operating conditions, whose identification is particularly challenging because of the wind and wave loading. The robustness of the proposed approach is assessed under assumed incorrect system information (e.g. damping ratio). The proposed approach is evaluated across different environmental and operating conditions to show its applicability to different operating regimes. The results show the approach can accurately identify the selected fast-varying natural frequency, 1st Fore-Aft (FA-1) mode, with a maximum root mean square error of 0.0012 Hz. The results demonstrate that the model trained on EKF estimates depends on accurate damping values, whereas the model trained on physics-based data exhibits robustness to incorrect damping assumptions. The approach is extended to damping ratio identification for the selected mode by estimating the root mean square error between models trained on EKF estimates and physics-based data. The results show that the approach can yield a good approximation of the FA-1 mode damping ratio using grid search, offering an improvement over covariance-driven
stochastic subspace identification.
Read the full abstract ▾
Information Retrieval
Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking
Lijun Liu, Zhengzong Chen, Wenyan Li et al. (+2 more)
Reasoning-based reranking with Large
Language Models (LLMs) has shown promising improvements in text ranking. However, current methods predominantly rely on a single
reasoning trajectory, resulting in rankings that are susceptible to
reasoning errors and inherently constrained in modeling the multifaceted signals underlying document relevance. To resolve this dilemma, we propose MERIT-Rank(Multi-perspective Evidence and
Reasoning Integration for Text Reranking), a framework that models complementary
reasoning trajectories to improve reranking robustness. MERIT-Rank formulates a Multi-Trajectory
Reasoning Space (MTRS) that evaluates query-document relevance from multiple perspectives and introduces a joint reranker that consolidates these
reasoning paths into a unified ranking decision. We further develop Progressive Rank Policy Optimization (PRPO), a progressive training framework that stabilizes
reasoning trajectories while continually improving ranking quality through staged optimization objectives. Experiments on both
reasoning-intensive and traditional
retrieval benchmarks show that MERIT-Rank consistently achieves superior performance over competitive baselines. The 4B model notably outperforms most 7B and even 32B rerankers on BRIGHT.
Read the full abstract ▾
All authors Lijun Liu, Zhengzong Chen, Wenyan Li, Yuanyuan Zhao, Fei Huang
Software Engineering
AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair
Z. C. Luo, J. C. Guo, W. J. He et al. (+10 more)
Recent
memory-augmented repository-level program repair methods reuse historical repair experiences to improve LLM-based issue resolution. However, our analysis reveals three limitations in existing repository-level
memory retrieval. First, episodic
memory is highly imbalanced across repositories, leaving low-resource repositories with little effective support. Second, more
memory does not monotonically lead to higher repair success, suggesting that relevance, quality, and redundancy matter more than raw
memory volume. Third,
memory accumulation is phase-misaligned: repositories may contain many reproduction experiences but few patch or refinement experiences. To address these problems, we propose an adaptive experience
retrieval framework for repository-level program repair. Our framework introduces coverage-aware
retrieval, which falls back to cross-repository or repair-type-based
memories when same-repository
memory is insufficient; quality-aware selection, which ranks
memories by relevance, historical utility, specificity, and redundancy; and stage-aware routing, which separates and retrieves
memories for reproduction, localization, patch generation, patch refinement, and validation. Evaluated on SWE-Bench-Lite and SWE-Bench-Verified, the proposed framework improves repair performance on under-covered repositories, reduces noisy
memory retrieval, and better supports failed-to-fixed patch refinement. Our results show that the key to
memory-augmented repair is not simply accumulating more experiences, but retrieving the right experiences for the right repair context.
Read the full abstract ▾
All authors Z. C. Luo, J. C. Guo, W. J. He, S. Y. Wang, J. C. Yu, F. M. Zhao, Y. Chen, T. Cao, L. Q. Liu, N. Zheng, W. Xu, J. Jiang, Z. M. Zhao
Machine Learning
Local Sparsity Enables Unsupervised LLM Safety Detection
Xin Chen, Gil Kur, Alexander Shevchenko et al. (+1 more)
Deployment-time safety methods for large
language models (LLMs) are predominantly supervised and assume access to unsafe training data. Nevertheless, new attacks and harm categories regularly arise, not captured by models trained in such a supervised fashion. An alternative approach is to view this problem through the lens of anomaly detection, namely, to rely solely on modeling safe data and flagging out-of-distribution inputs. However, LLM activations lie in a high-dimensional space, raising concerns about whether anomaly detection is statistically feasible. We show that, under the linear representation hypothesis (LRH), there may indeed be hope. In the LRH concept space, which is typically recovered via a sparse autoencoder (SAE), nearby points share a small common active support. Using this local sparsity insight, we propose a framework for locally masked SAE-based anomaly detection, supported by theoretical justifications. We validate it on various architectures and
datasets, including both capability-testing
datasets and safety-specific
datasets. Finally, when we allow
algorithms to use 1% out-of-distribution data for calibration, locally sparse methods achieve near-optimal performance, demonstrating their ability to capture meaningful safety information while using only 1-2% of SAE
neurons for computation.
Read the full abstract ▾
All authors Xin Chen, Gil Kur, Alexander Shevchenko, Andreas Krause
Numerical Analysis · Cross-listed from math.PR
Monte Carlo Approximations of Time-Nonlocal Diffusions in Bounded Domains
Ivan Biočić, Daniel E. Cedeño-Girón, Aleksandar Mijatović et al. (+1 more)
We develop and analyze a Monte Carlo method for sampling killed anomalous
diffusions obtained by time-changing Brownian motion with drift by the inverse of a subordinator. The method targets probabilistic representations of time-nonlocal, including time-fractional, Cauchy–Dirichlet problems on bounded domains. Since inverse subordinators can be sampled exactly in broad classes, while Brownian exit times are generally unavailable in arbitrary domains, we approximate the killed Brownian component by an Euler scheme with discrete boundary detection. We prove a square-root weak error bound with explicit dependence on the Laplace exponent of the subordinator, and derive mean-square and central limit results for the resulting Monte Carlo
estimator. A numerical example in the disk and one in a high-dimensional anisotropic shell illustrate the theoretical rates, computation time, and the mesh-free character of the method.
Read the full abstract ▾
All authors Ivan Biočić, Daniel E. Cedeño-Girón, Aleksandar Mijatović, Bruno Toaldo
Logic in Computer Science · Cross-listed from math.DG
Retro-synthetic Riemannian geometry in Rocq I : Taylor series of a metric
Gabriella Clemente, Hugo Herbelin and Carlos Simpson
We introduce a synthetic framework for doing local Riemannian geometry that is influenced by a reverse-engineering method for formalizing in Rocq. These new perspectives and techniques lead to a synthetic Taylor formula for a Riemannian metric in normal coordinates, which is the main contribution of this work.
Read the full abstract ▾
Sound
Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis
Zifan Guan, Longyu Lu, Junan Zhang et al. (+3 more)
Evaluating live streaming
speech synthesis (TTS) requires assessing fine-grained, highly expressive prosody such as
emotion, intonation, and energy which traditional MOS predictors fail to capture. While proprietary Large
Language Models (LLMs) like Gemini can evaluate these aspects, they are too costly for massive inference and reinforcement learning feedback. To address this, we first introduce Live-ProsodyJudge (LPJ), a cost-effective pairwise evaluator distilled from Gemini into Qwen3-Omni. However, we identify a critical flaw in standard multi-dimensional evaluation: verdict coupling. The judge tends to lazily align all individual dimension scores with its overall preference, collapsing a rich multi-dimensional rubric into a single preference bit. To resolve this, we further propose Decoupled-Live-ProsodyJudge (D-LPJ). D-LPJ eliminates the overall verdict target to prevent blind following, masks uncertain pair-dimensions during Supervised Fine-Tuning(SFT), and introduces a novel span-local GRPO strategy that applies normalized advantages strictly to their corresponding rationale spans. Evaluated on highly curated human-annotated test sets, 10 sample balanced-order LPJ achieves higher point accuracy than a single Gemini call, while D-LPJ successfully produces independent,decoupled dimension judgments. Furthermore, in a Best-of-8 TTS candidate selection tournament, the LPJ-selected utterance falls within the human top-3 in 85.29% of high-confidence cases, demonstrating its efficacy for fine-grained TTS preference optimization.
Read the full abstract ▾
All authors Zifan Guan, Longyu Lu, Junan Zhang, Zhizheng Wu, Meiguang Jin, Junfeng Ma
Machine Learning
QoS-Aware Federated Learning for Multimodal In-Cabin Interaction in Smart Vehicles
Baran Can Gül, Mert Nak{\i}p, Nasser Jazdi et al. (+1 more)
Modern smart vehicles leverage
multimodal sensors, ranging from high-bandwidth
vision systems to low-rate physiological monitors, to provide personalized in-cabin services. However, integrating high-fidelity
multimodal fusion with collaborative training is often hindered by the heterogeneous and time-varying Quality of Service (QoS) constraints of vehicular networks. Standard
Federated Learning (FL) approaches enforce rigid synchronous rounds that fail to account for these resource asymmetries, leading to safety-critical timing violations and energy exhaustion. In this paper, we propose FedQoS, a novel asynchronous, event-triggered FL framework that decouples local computation from global communication via a two-phase gating mechanism. First, we introduce a resource-aware training gate that initializes local learning only when sensing buffers and energy reserves meet safety thresholds, preventing ML tasks from compromising core vehicle mobility. Second, a QoS-aware transmission policy gates uplink updates based on an efficiency score that balances model novelty against instantaneous latency and energy costs. Locally, clients optimize an objective featuring a staleness-aware proximal term that dynamically adjusts the global anchor strength based on update age. Extensive experiments on
multimodal vehicular
datasets demonstrate that FedQoS achieves competitive personalized accuracy with only marginal performance loss compared to FedAvg, while substantially reducing QoS violations, cutting communication overhead by 76.7%, and lowering latency cost by 26.0%, demonstrating a highly favorable accuracy and efficiency balance for real-world vehicular deployments.
Read the full abstract ▾
All authors Baran Can Gül, Mert Nak{\i}p, Nasser Jazdi, Michael Weyrich
Robotics
How Far Can GPT-6-Astra Go? Evaluating Capabilities in Zero-Shot Vision-and-Language Navigation
Guangzhao Dai, Qi Wu and Bin Zhu
We study GPT-6-Astra in a zero-shot
Vision-and-
Language Navigation in Continuous Environments (VLN-CE) system, where it interprets instructions, assesses its surroundings, and proposes actions. The system uses a common observation–decision–execution workflow with direct model API calls, without a packaged
agent harness or
navigation-specific fine-tuning. In this workflow, each request receives selected observations, execution feedback, and retained progress records. Evaluation covers the complete system, including context management and action control. We evaluate the system on 50 of the 100 R2R-CE val-unseen episodes used by Open-Nav. It achieves a success rate of 52.0%, an SPL of 48.9%, and an nDTW of 70.8%. Our analysis highlights three findings. First, recorded responses link landmarks and earlier actions to instructions using observations and supplied history. Second, reviews include requests for additional views and revisions of uncertain judgments. Third, the results suggest a gap between task understanding and autonomous completion: an unfinished crossing is recognized while rotation continues. At termination, 36.0% of episodes succeed with a workflow-accepted STOP, while another 16.0% meet the distance criterion at the step limit. These results highlight a central challenge: translating correct local judgments into sustained progress and appropriate stopping.
Read the full abstract ▾
Systems and Control
The Small-Talk Effect in Practical Synchronization of Heterogeneous Oscillating Dynamics
Finn Voland, Vincent Schmidtke, Zonglin Liu et al. (+1 more)
This paper investigates multi-time scale commu- nication schemes in synchronization of heterogeneous Lienard oscillator systems. Existing results rely on global exchange of information for all networked systems at discrete time instants, providing limited flexibility in adjusting the trade-off between communication rate and synchronization performance. A scheme to investigate how global updates are complemented by more frequent local interactions within a sub-network is thus proposed in this paper. For a prescribed bound on the synchronization error, conditions are derived under which the global and local update rates can be selected as design parameters. A numerical example illustrates the beneficial effect of the local interactions.
Read the full abstract ▾
All authors Finn Voland, Vincent Schmidtke, Zonglin Liu, Olaf Stursberg
Robotics
Sarvesh Prajapati, Ananya Trivedi, Lorena Maria Genua et al. (+3 more)
Collecting real-world
navigation data for mobile
robots typically requires platform-specific teleoperation, making large-scale collection expensive and difficult to scale. We introduce Universal
Navigation Interface (UNI), a
robot-free data collection paradigm that uses a four-wheeled rollator walker (rollator) and smartphone to collect physically constrained human demonstrations. Because the rollator cannot climb stairs, negotiate uncut curbs, or pass through narrow gaps, demonstrations are naturally biased toward wheeled-feasible routes. Using UNI, we collect 37.2 km of real-world
navigation data and recover metric trajectories that directly supervise goal-conditioned
navigation models. Fine-tuning visual-
navigation models on UNI reduces trajectory prediction error by 17.4-24.8% on held-out UNI demonstrations. Evaluation on other
navigation datasets shows benefits that vary by
dataset and metric. We further demonstrate closed-loop transfer to a powered wheelchair in curb, staircase, and curb-cut scenarios. These results support low-cost physical proxies as a practical source of
navigation supervision collected without the target
robot.
Read the full abstract ▾
All authors Sarvesh Prajapati, Ananya Trivedi, Lorena Maria Genua, Drake Moore, Bruce Maxwell, Taskin Padir
Artificial Intelligence
Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents
Yichao Jin, Yushuo Wang, Yuxuan Han et al. (+7 more)
Straight-through processing (STP) on extracted key-value fields from financial documents without human review requires a calibrated probability together with a bounded guarantee on the residual error of the auto-approved tier. The emergence of modern
Vision Language Models (VLMs) provides an out-of-the-box capability for extracting the key-values, but their verbalized confidence signals are unreliable and weakly track field correctness. This paper introduces a decomposed confidence layer along three interpretable channels, including perception, layout, and validation. Together with a final conformal risk control, the score can be used for reliable STP of financial documents. The method is validated on three public
datasets covering real invoices, synthetic invoices, and ad-buy forms, using two different VLM families (Qwen3.6-27B and Gemini-3.1-Flash-Lite). Our decomposed score consistently improves the separation of correct from incorrect extractions, substantially raising the AUROC from 0.54-0.74 for VLM verbalized signals to 0.90-0.99 with contributions from all three designed channels. Crucially for industrial deployment, this enables usable STP. The native VLM confidence signals could clear only 0.1%-7.0% of fields under risk control at a target error of <10%. In contrast, the proposed method auto-approves 49-72% of fields while holding the empirical error of the accepted tier at or below the target.
Read the full abstract ▾
All authors Yichao Jin, Yushuo Wang, Yuxuan Han, Kwan Ching Yee Sonia, Weiyang Song, Chiu Jin-Chun Kent, Wong Chong Hwee, Wong Tiong Kiat, Kenneth Zhu Ke, Jingyuan Zhao
Robotics
AnyViewDex: View-Invariant Dexterous Manipulation from RGB Observations
Soham Patil, Om Sanjay Gunjal, Sourabh Bhosale et al. (+3 more)
Visuomotor policies for multi-fingered dexterous manipulation are highly sensitive to camera viewpoint shifts. To achieve view invariance, recent methods increasingly rely on explicit 3D modalities like RGB-D or point clouds, which can introduce hardware dependencies, calibration requirements, and vulnerability to sensor noise during real-world deployment. In this work, we show that view-invariant control can be achieved without explicit test-time 3D sensing by encoding
geometric knowledge into the visual representation during simulation. We present AnyViewDex, an asymmetric training pipeline that combines multi-view contrastive
alignment with privileged 3D
geometric supervision. By regressing absolute 3D object coordinates during simulated training, this auxiliary objective provides a
geometric grounding signal that mitigates the spatial collapse of the globally pooled contrastive
embedding. At deployment, the policy operates zero-shot using only uncalibrated
monocular RGB and proprioception. We validate this approach across both reinforcement learning and student-teacher
distillation. In hardware evaluation on an xArm7 with a 16-DoF LEAP Hand, AnyViewDex reaches 76.7% grasping success across eight unseen objects and six uncalibrated viewpoints (480 trials; 2,400 across all ablation conditions), indicating that geometrically grounded
monocular policies transfer zero-shot without test-time depth. Project Page: https://anyviewdex.github.io/
Read the full abstract ▾
All authors Soham Patil, Om Sanjay Gunjal, Sourabh Bhosale, Arhan Chavare, Ramandeep Singh Hora, Spandan Roy
Computer Vision
AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention
Yuang Tu, Runjia Tan, Yujie Yan et al. (+2 more)
Robotic reward models evaluate task execution from visual observations, but their predictions can change with camera viewpoint and occlusion even when the underlying task state is unchanged. Adapting a pretrained reward model to a local task therefore requires accounting for how that task is observed. We introduce AnyviewMeter, a geometry-conditioned adaptation framework for robotic reward models that represent task progress as a scalar reward signal. It combines low-rank fine-tuning with
token-aligned Plucker rays and synchronous block
attention: ray conditioning incorporates camera geometry into visual features and
attention queries and keys, while block
attention fuses synchronized views inside the pretrained decoder. The framework supports both single-view reward prediction and joint multi-view evaluation through parameter-efficient adaptation of a pretrained Robometer model. On PickCube, single-view adaptation improves progress prediction in every camera group and reduces mean absolute error under a changed field of view by approximately 21% relative to RGB fine-tuning. Across simulated manipulation tasks, joint multi-view prediction reduces progress error by 41-69% compared with averaging single-view RGB predictions and improves temporal ordering in approximately 88% of task-camera groups. On real tasks with fixed and wrist-mounted cameras, mean absolute error decreases by approximately 21% relative to averaged RGB fine-tuning. These results support camera geometry and joint visual evidence as useful components of task-specific robotic reward adaptation.
Read the full abstract ▾
All authors Yuang Tu, Runjia Tan, Yujie Yan, Jinghan Hu, Chen Lv
Computation and Language
Design of the IBM Granite 5.0 TurboCTC ASR Model
Brian Kingsbury, George Saon, Masayuki Suzuki et al. (+5 more)
We describe the architecture, training methodology and inference speedups of Granite 5.0 Turbo CTC, a 470 million parameter encoder-only model with an excellent speed-accuracy tradeoff. The architecture uses pyramidal temporal subsampling within Conformer blocks using strided depthwise convolutions, block-diagonal (chunk-wise) self-
attention, and conditioning on intermediate predictions from the middle layer. Training highlights are the use of only publicly available data, the novel use of a
Muon optimizer, and balanced data sampling. Inference speedups include replacing 1 x 1 convolutions with linear layers and optimizing the
attention computation in the Conformer blocks. Collectively, these result in a model that is on the speed-accuracy Pareto frontier of the Open ASR leaderboard for English short-form ASR while being twice as fast as the fastest competitor. The model can be used under a permissive license and downloaded from https://huggingface.co/ibm-granite/granite-
speech-5.0-470m-turboctc.
Read the full abstract ▾
All authors Brian Kingsbury, George Saon, Masayuki Suzuki, Hong-Kwang J. Kuo, Takashi Fukuda, Samuel Thomas, Vishal Sunder, Avihu Dekel
Robotics
Safety-Critical Scenarios Emerge from Initial Scenes
Yin Wu, Jiarong Wei, Carl Esselborn et al. (+4 more)
Safety-critical driving scenario generation has largely focused on manipulating the behavior of surrounding
agents while starting from an initial scene from driving data. This assumption can limit the space of discoverable failures, since driving data can provide little opportunity for meaningful interaction. For example, in the Waymo Open Motion
Dataset, 20.44% of recorded slices feature a stationary ego vehicle that never moves, and 30.39% of initial frames contain no nearby traffic participants within 10 meters. We instead study safety-critical scenario generation as an initialization problem: given agnostic black-box driving policies, we learn to generate realistic initial scenes that are more likely to evolve into critical interactions. We propose AdvScene, a conditional latent
diffusion model that is trained in two stages. Starting from pretraining on naturalistic driving data, we post-train the
adversarial-
agent generation branch using reinforcement learning with feedback from closed-loop simulator rollouts. Conditioning on ego driving displacement prevents the ego from remaining static, and RL finetuning induces criticality directly with non-differentiable safety-critical metrics. Experiments on the Waymo
dataset across 12 combinations of ego and traffic policies show that our AdvScene substantially increases the rate of ego-fault collision events and TTC<3s events.
Read the full abstract ▾
All authors Yin Wu, Jiarong Wei, Carl Esselborn, Shubham Phoolari, Ahmed Abouelazm, Daniel Slieter, J. Marius Zöllner
Social and Information Networks
Competing for a Finite Pool of Attention in Social Media? How a New Geopolitical Conflict Reshapes Engagement in Bluesky
Kamand Kalashi, Arash Badie-Modiri, Ali Salloum et al. (+3 more)
Major geopolitical crises can rapidly reshape online public
attention. Yet population-level increases in discussion volume about a new crisis reveal little about how users accommodate this new demand for
attention. We study the onset of the Iran-US-Israel conflict, triggered on 28 February 2026, using longitudinal repost activity from Bluesky across four consecutive approximately three-month windows spanning the period before and after its onset; the data comprise 91.0 million unique posts and 645.5 million repost observations. We find that the new conflict reorganized participation through both reallocation among existing conflict participants and substantial activation of previously low-conflict-active users, while some previously active users reduced their conflict-related participation.
Attention redistribution differed substantially across pre-existing interests: Iran-US-Israel and Israel-Palestine
attention showed strong positive co-movement with little systematic relative replacement, whereas Other Political and Non-Political content more consistently lost
attention share, and Russia-Ukraine exhibited weaker, heterogeneous replacement. Finally, disruption of users' broader
attention allocation was substantially more prevalent among users with established
attention to geopolitical conflicts than in the overall or Non-Political populations. Together, these findings show that a newly emerging conflict reorganizes online
attention through turnover in who participates, selective co-attendance or replacement across topics, and disruption of broader
attention patterns concentrated among users already engaged with geopolitical conflicts.
Read the full abstract ▾
All authors Kamand Kalashi, Arash Badie-Modiri, Ali Salloum, Juhi Kulshrestha, Talayeh Aledavood, Mikko Kivelä