Computation and Language
Likelihood Ranking doesn't Scale Like Prompting in LLMs
Alessandro Bondielli, Lucia Passaro, Davide Bacciu et al. (+1 more)
LLM evaluation is commonly performed either by prompting models to produce answers or by scoring candidate outputs with likelihood-based metrics. In multiple-choice QA, however, standard likelihood-based scoring is still conditioned on the question and answer set, and can therefore leverage the same task-conditioned answer-selection interface used in prompting. We study a complementary protocol based on likelihood ranking of declarative statements constructed from the same question–answer pairs. Across 95 decoder-only models, ranging from 0.1B to 104B parameters, and 10 MCQA
datasets, we find a systematic divergence between declarative-statement likelihood ranking and prompted answering. Statement-likelihood accuracy remains comparatively stable across scale, whereas prompted answering improves sharply with scale and instruction-tuning. These results suggest that likelihood preferences over controlled declarative alternatives and task-conditioned answer selection probe distinct aspects of model behavior, and should not be treated as interchangeable.
Read the full abstract ▾
All authors Alessandro Bondielli, Lucia Passaro, Davide Bacciu, Alessandro Lenci
Robotics
Robo-Harness K1: Harnessing Robot-Use Agents via Perception Augmentation
Zexi Li, Yehang Zhang, Wenqian Li et al. (+12 more)
Foundation
vision-
language models (VLMs) understand objects, instructions, and spatial relations, yet translating this capability into robotic manipulation remains difficult.
Vision-
language-action (VLA) models require extensive demonstrations and may compromise pretrained understanding, while direct RGB-only VLM control is costly and strongly dependent on model capability. We introduce Robo-Harness K1, a
robot-use
agent (RUA) framework that exposes perception as tools. The
agent queries calibrated depth, persistent visual anchors, spatial measurements, and grasp hypotheses, then selects generic motions from the returned evidence. This interface makes 3D geometry accessible without changing the VLM architecture or training a depth encoder. On matched LIBERO-PRO tasks, Gemini 3.7 Flash with K1 reaches 77.8% accuracy, surpassing GPT-6 Astra's 61.1% with an RGB-only harness; K1 further improves Astra to 88.9%. Without target fine-tuning, Gemini with K1 transfers to three RoboSuite arms and dual-arm RoboTwin tasks. On RoboTwin, it achieves 32.0% on Easy and 28.0% on Hard, showing resilience to visual and environmental perturbations. K1 also produces tool-call traces aligned with next-
token training. A Qwen3.5-9B student trained on only 107 teacher episodes reaches 44.2% accuracy on new initial states versus 30.2% for OpenVLA, and 13.9% on held-out task conditions versus 0.0% for OpenVLA. These results suggest that perception-augmented RUAs offer a promising route to sample-efficient, generalizable robotic policies that leverage VLM capabilities through an accessible tool interface.
Read the full abstract ▾
All authors Zexi Li, Yehang Zhang, Wenqian Li, Haojian Huang, Chenxu Wang, Shiyuan Deng, Yangkai Wei, Tianyi Zhang, Binghui Xie, Bohan Zhou, Yifan Chang, Kaiwen Zhou, Ying-Cong Chen, James Cheng, Yinchuan Li
Computer Vision
When Misalignment Becomes Supervision: Structured Label Noise in Supervised Synthetic CT Generation
Valentin Boussot, Cedric Hemon, Caroline Lafond et al. (+2 more)
Supervised synthetic CT (sCT) generation is commonly trained and evaluated as voxel-wise regression against registered reference CT images. In practice, MRI-CT and CBCT-CT pairs are aligned through registration procedures that leave residual misalignments. These residuals are not independent intensity noise but spatially coherent
geometric discrepancies that act as structured label noise. We investigate how this registration-induced bias affects supervised MRI-to-CT and CBCT-to-CT synthesis on 1,784 paired patients covering five anatomical regions. Voxel-wise scores strongly depend on the consistency between the registration used to build the training targets and the one used for evaluation: models score best when both conventions match, showing that networks partly learn the
geometric convention of the registration pipeline and that standard metrics reward it. Training on more anatomically consistent registrations reduces prediction variability and improves out-of-distribution robustness, and CT-only controls show that registration alone produces metric errors in the range of top challenge submissions. To mitigate the limits of voxel-wise supervision, we introduce a perceptual loss computed in the feature space of a pretrained Segment Anything encoder. Compared with MAE-only and VGG-based objectives, it improves downstream
segmentation and yields sharper, more structurally coherent sCT. Perceptual and voxel-wise metrics disagree under imperfect
alignment and agree when the evaluation geometry is reliable. These results identify registration-induced bias as a central confounder in supervised sCT generation and argue for complementing voxel-wise agreement with anatomy-oriented evaluation criteria.
Read the full abstract ▾
All authors Valentin Boussot, Cedric Hemon, Caroline Lafond, Jean-Claude Nunes, Jean-Louis Dillenseger
Machine Learning
MORE-PLR: multi-output regression employed for partial label ranking
Santo M. A. R. Thies, Juan C. Alfaro and Viktor Bengs
The partial label ranking problem is a supervised learning scenario that aims to fit a preference model that predicts a bucket order defined over a set of labels for a given input instance. This problem generalizes the well-known label ranking problem, which, in practice, is limited to outputting total orders of labels. Existing partial label ranking methods have primarily extended label ranking approaches to handle ties in predictions. This paper proposes using multi-output regression to address the partial label ranking problem, introducing an encoder that, during the learning phase, transforms the (possibly incomplete) rankings with ties of labels to multivariate regression targets, an underexplored perspective in both label ranking and partial label ranking. Moreover, during the inference phase, we introduce several post-hoc layers that convert the multi-output regression results into the output bucket order to effectively implement this approach. This framework provides learning strategies that are competitive with the current state-of-the-art partial label ranking methods, as demonstrated through experimental evaluations.
Read the full abstract ▾
Computer Vision
Segment-Level Risk Discovery in Online Handwriting for Alzheimer's Disease Detection
Changqing Gong, Huafeng Qin and Mounîm A. El-Yacoubi
Online handwriting provides a non-invasive and low-cost behavioral biomarker for Alzheimer's disease (AD) detection, as it reflects both cognitive planning and fine motor control. Existing handwriting-based AD detection methods usually rely on global trajectory features or whole-sample representations, which can be strongly affected by individual writing style, task-specific variation, and acquisition noise. In this paper, we propose NormPaST-Risk, a healthy-normative Paper-Air selective trajectory state-space risk network for interpretable AD detection from online handwriting. Instead of treating the entire trajectory as a single holistic representation, our method reformulates AD handwriting detection as local disease-relevant segment discovery. Specifically, a multi-scale temporal encoder captures stroke dynamics at different temporal resolutions, while a selective Paper-Air state-space encoder models long-range handwriting progression and distinguishes on-paper motor execution from in-air planning and transition behaviors. To explicitly characterize abnormal deviations, a healthy normative branch learns normal handwriting dynamics from healthy controls, and a task-aware multi-expert segment-risk module estimates segment-level AD risk calibrated by hidden-state changes and normative deviations. A weakly supervised segment-level objective further enables high-risk segment discovery without manual segment annotations. Experiments on the DARWIN
benchmark demonstrate that the proposed framework achieves superior AD/HC classification performance compared with existing methods. Moreover, the discovered high-risk segments can be projected back to the original handwriting trajectory, providing interpretable evidence associated with AD-related handwriting variations.
Read the full abstract ▾
Machine Learning
Lightweight Probabilistic Downscaling from a Deterministic Base Model
Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan et al. (+1 more)
Climate data downscaling is the task of increasing the spatial resolution of
climate data, typically by generating fine-resolution regional
climate data from coarse global model output. Recent machine learning (ML) work in the related task of weather
forecasting has seen significant improvements due to newly devised training methods and architectural components, but these have not yet benefited downscaling. We adapt two of these methods to create a family of lightweight probabilistic ML downscaling models built on a modified U-Net backbone and evaluate them on the CORDEX-ML-Bench suite for daily maximum temperature and precipitation across three geographic regions: the Alps, New Zealand and South Africa. We find that a two-stage training curriculum, combining deterministic pretraining with probabilistic tuning, transfers well to downscaling, beating the state-of-the-art for RMSE. Our work provides an advancement towards lightweight, probabilistic downscaling models, reducing the current trade-off between computational intensity and distributional fit.
Read the full abstract ▾
All authors Joseph McLean, Tiffany Vlaar, Sigrid Passano Hellan, Linus Ericsson
Robotics
Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro et al. (+3 more)
Flow-matching
Vision-
Language-Action (VLA) models have emerged as a potential solution for generalist
robot control, designed by combining a pretrained
Vision-
Language Model (VLM) backbone with an action expert that generates continuous
robot actions. While these models exhibit impressive capabilities, due to their very high number of parameters, their computational requirements are often prohibitive for robotics control. To mitigate these inefficiencies, existing methods predominantly skip VLM backbone layers with early exits or reduce denoising steps, while leaving action expert depth untouched. We propose a framework that exposes backbone depth $V$, action expert depth $A$, and denoising steps $D$ as three jointly configurable compute axes in a VLA. Starting from a pretrained VLA, we attach lightweight Exit
Transformers (ET) at intermediate depths in both the backbone and the action expert, trained to distil the last layer of the policy into each exit. Furthermore, we introduce a KV Cache synthesis mechanism that manages the missing keys and values of the skipped backbone layers, allowing the action expert to exit deeper than the backbone. Finally, we show that the optimal compute budget is task-dependent, with different tasks benefiting from different axes and depths. Notably, our method does not require training the original policy from scratch, and for each exit, it increases the number of parameters by only $2.1\%$ for SmolVLA and $4.1\%$ for $\pi_{0.5}$. We validate our approach across two flow-matching VLAs (SmolVLA, $\pi_{0.5}$) and two
benchmarks (LIBERO, Meta-World), revealing complementary effects: $V$ and $A$ respectively reduce FLOPs and latency, while $D$ improves both. Our joint configurations $(V,A,D)$ reduce latency by $79.2\%$ and computation (FLOPs) by $31.8\%$, while improving mean success rate by $5.6\%$.
Read the full abstract ▾
All authors Riccardo Andrea Izzo, Rimvydas Rubavicius, Gianluca Bardaro, Subramanian Ramamoorthy, Matteo Matteucci, Alessandro Suglia
Artificial Intelligence
An auditable conditional-strategy framework for open-ended decision-making in complex lung cancer
Daoyun Wang, Zhicheng Huang, Huaiyuan Sun et al. (+39 more)
Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must make explicit how patient conditions govern pathway eligibility, deferral and redirection. MedGPT Clinical Explorer (MCE) organizes alternatives, decision-changing unknowns, safety constraints and fallback into a conditional strategy for clinician review. To evaluate this representation in physician-authored strategies, multidisciplinary experts established case-specific references for 40 cases within a purposive 100-case corpus, and 250 physicians from 98 institutions produced 2,250 strategies under unaided,
retrieval-reference and MCE-assisted conditions. MCE-assisted strategies expressed more applicable clinical requirements, measured by the Admissible Pathway Attainment Score (APAS; 0-100), than unaided strategies (adjusted difference, 12.87; 95% CI, 11.18-14.55) and
retrieval-reference strategies (5.22; 3.52-6.93). With the same knowledge base available in the
retrieval-reference and MCE-assisted conditions, the additional content centered on candidate pathways, decision-critical information and safety constraints. Physicians' whole-strategy acceptability judgments correlated with APAS (Spearman's rho = 0.671), while a complementary relationship audit assessed whether candidates, conditions and subsequent actions were coherently connected. Together, these findings identify two complementary dimensions of open-ended decision support: coverage of clinically relevant content and coherent links among pathways, conditions and subsequent actions. MCE provides a shared decision object that makes consequential omissions and pathway contingencies visible before action; prospective studies should evaluate its effects on clinical workflow and patient outcomes.
Read the full abstract ▾
All authors Daoyun Wang, Zhicheng Huang, Huaiyuan Sun, Jiaqi Xu, Xiaowei Xu, Zhibo Zheng, Zhongxing Bing, Yuxiao Lin, Yicheng Liang, Chao Gao, Bowen Xue, Kai Zhang, Song Xu, Wanpu Yan, Hui Xia, Lin Li, Xiang Yan, Mu Hu, Qianli Ma, Zhiqiang Xue, Xiaofang Liu, Zhihai Han, Nan Zhang, Chuanhao Tang, Tongmei Zhang, Lan Song, Zhaohui Zhu, Xuan Zeng, Shafei Wu, Hui Guan, Lei Deng, Huaxia Yang, Zeliang Lian, Wubin Sun, Yongxin Wang, Xiaohui Shen, Binlin Wang, Tiantian Gu, Yu Cui, Li Zhang, Shirui Wang, Naixin Liang
Logic in Computer Science
Scenes: A Meta-Logical Algebra for Mutable State
Simon Foster, Carlos Isasa and Christian Pardillo Laursen
Modelling of mutable state spaces and precisely describing how variables are manipulated in a program is a fundamental problem in compositional verification. Though we can make use of the embedded abstract syntax of a program for such analysis, this runs contrary to the shallow-
embedding approach, and hampers efficient proof automation. On the other hand, lenses and prisms provide an elegant algebraic foundation for modelling state, which provide sufficient structure to provide meta-logical program analysis, but without requiring a deep
embedding. Nevertheless lenses, as complex algebraic objects, cannot easily be combined, complemented, or collected in sets. In this paper we contribute an accompanying algebraic structure called the scene, which allows us to characterise the set of variables, or coordinates, in a state space. Scenes intuitively correspond to sets of lenses, but like lenses they are purely semantic algebraic objects. We demonstrate that scenes provide us with sufficient structure to characterise the lens-based meta-logical properties, like independence and equivalence. Moreover, we introduce the notion of a scene space, analogous to a vector space, which allows us to recover a set-like algebraic structure. Finally, we show how scenes allow us to characterise the free and bound variables of expressions and programs, without any need for syntax, and demonstrate their use for
reasoning about programs by deriving
reasoning principles for the parallel composition operator.
Read the full abstract ▾
Machine Learning
On the second-order optimization for spiking neural networks
Ngoc Phu Doan and Ihsen Alouani
Spiking Neural Networks (SNNs) offer an energy-efficient alternative to conventional neural networks by exploiting sparse, binary spikes, and event-driven computation. However, the training of SNNs remains challenging, as spiking activations create a sharp loss landscape that hinders training, and diagonal-
curvature optimizers such as the Adam family may fail to capture this geometry. The extension of
curvature-based optimization methods to SNNs is further complicated by the sparse, discrete, and temporally recurrent nature of their underlying dynamics. To address these limitations, we propose SpiKFAX, a second-order optimization method that formulates a computationally tractable, Kronecker-factored approximation of the Fisher information
matrix specifically adapted to the structure of SNNs. Empirical evaluation across five architectures and seven
datasets demonstrates that SpiKFAX consistently yields improvements in test accuracy and training stability relative to other popular optimizers.
Read the full abstract ▾
Computer Vision
A Hybrid CNN–State-Space–Attention Backbone with Joint-Embedding Predictive Pretraining for 12-Lead ECG Classification
Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal et al. (+2 more)
Automatic 12-lead electrocardiogram (ECG) classification requires representations that jointly capture local waveform morphology, long-range temporal dynamics, and cross-lead dependencies, yet integrating these properties within a single efficient architecture remains challenging. This paper introduces a hybrid CNN-SSM-
Attention backbone for 12-lead ECG classification. A convolutional stem performs early waveform tokenization and temporal reduction, mixed state-space and depthwise-convolutional blocks model temporal dynamics and local morphology, and a late self-
attention stage enables global
token interaction at reduced resolution. To improve transfer from unlabeled data, we further develop an ECG-oriented Joint-
Embedding Predictive Pretraining (JEPA) framework. Unlike ViT-based JEPA methods that mask patch
tokens before the encoder, the proposed method samples span masks at the latent temporal resolution and projects them back to the waveform domain, then predicts clean latent targets from a momentum encoder without waveform reconstruction. Experiments on CPSC2018, Chapman-Shaoxing, and PTB-XL, with pretraining on approximately 350K unlabeled CODE-15 recordings, show that the proposed backbone provides strong supervised baselines under a compact parameter budget. JEPA pretraining further improves transfer, particularly in reduced-label settings and under both full fine-tuning and LoRA-based adaptation. Code: https://github.com/yakoubbazi/Hybrid_ECG_Jepa
Read the full abstract ▾
All authors Yakoub Bazi, Sarah Aljuhani, Mohamad M. Al Rahhal, Mansour Zuair, Naif Alajlan
Robotics
Free-Init: Scan-Free, Motion-Free, and Correspondence-Free Initialization for Doppler LiDAR-Inertial Systems
Mingle Zhao, Jiahao Wang, Tianxiao Gao et al. (+2 more)
Robust initialization is crucial for online systems. In the letter, a high-frequency and resilient initialization framework is designed for
LiDAR-inertial systems, leveraging both inertial sensors and Doppler
LiDAR. The innovative FMCW Doppler
LiDAR opens up a novel avenue for robotic sensing by capturing not only point range but also Doppler velocity via the intrinsic Doppler effect. By fusing point-wise Doppler velocity with inertial measurements under non-inertial kinematics, the proposed framework, Free-Init, eliminates reliance on motion undistortion of
LiDAR scans, excitation motions, and map correspondences during the initialization phase. Free-Init is also plug-and-play compatible with typical
LiDAR-inertial systems and is versatile to handle a wide range of initial motions when the system starts, including stationary, dynamic, and even violent motions. The embedded Doppler-inertial velocimeter ensures fast convergence and high-frequency performance, delivering outputs exceeding 10 kHz. Comprehensive experiments on diverse platforms and across myriad motion scenes validate the framework's effectiveness. The results demonstrate the superior performance of Free-Init, highlighting the necessity of fast, resilient, and dynamic initialization for online systems.
Read the full abstract ▾
All authors Mingle Zhao, Jiahao Wang, Tianxiao Gao, Chengzhong Xu, Hui Kong
Robotics
FMCW-LIO: A Doppler LiDAR-Inertial Odometry
Mingle Zhao, Jiahao Wang, Tianxiao Gao et al. (+2 more)
Conventional
LiDAR-inertial odometry (LIO) or simultaneous localization and mapping (SLAM) methods heavily rely on
geometric features of environments, as
LiDARs primarily provide range measurements instead of motion measurements. From now on, however, the situation changes thanks to the novel Frequency Modulated Continuous Wave (FMCW) Doppler
LiDARs. FMCW Doppler
LiDARs not only offer the point range with high resolution but also capture the instant point Doppler velocity through the Doppler effect. In the letter, we propose FMCW-LIO, a novel and robust LIO, leveraging intrinsic Doppler measurements from FMCW Doppler
LiDARs. To correctly exploit Doppler velocities, a motion compensation method is designed, and a Doppler-aided observation model is applied for on-
manifold state estimation. Then, dynamic points can be effectively removed by the Doppler criteria, deriving more consistent
geometric observations. FMCW-LIO eventually achieves accurate state estimation and static mapping, even in structure-degenerated environments. Extensive experiments in diverse scenes are performed and FMCW-LIO outperforms other
algorithms on both accuracy and robustness.
Read the full abstract ▾
All authors Mingle Zhao, Jiahao Wang, Tianxiao Gao, Chengzhong Xu, Hui Kong
Computer Vision
Shadow Reduction in Ultrasound Imaging Using Differentiable Simulation and Radiance Field Decomposition
Valentin Bacher, Pak Hei Yeung, Bernhard Kainz et al. (+4 more)
Acoustic shadows from bone and other highly attenuating tissues obscure clinically important structures in ultrasound. In fetal
brain imaging, skull-induced artefacts disproportionately degrade the hemisphere closer to the transducer (proximal), limiting symmetric assessment of the two hemispheres. Existing correction methods require raw scanner data, impose restrictive assumptions on tissue properties, or rely on generative models that may hallucinate anatomy. We present RFlash, a physics-informed post-processing method that decomposes beamformed ultrasound images into explicit attenuation and scatter-intensity maps using a differentiable radiance-field formulation of image formation. Attenuation-adaptive re-rendering then removes the dependence of the signal at each depth on the intervening tissue, equivalent to virtually advancing the transducer into the tissue. Across 1,261 3D fetal
brain volumes, 143 real 2D curvilinear abdominal scans, and 1,200 simulated 2D linear-probe liver scans, RFlash reduces shadow-related intensity differences more effectively than classical Hughes-Duck attenuation correction. For a gestational-age model trained on the distal hemisphere (further from the transducer) and applied to the proximal hemisphere, prediction error decreases by 5.1 days (40%) relative to the original images. The estimated attenuation maps also yield shadow-confidence maps that improve random-forest bone-shadow
segmentation over the image alone and receive greater SHAP importance than an existing neural confidence-map baseline, suggesting greater physical consistency. RFlash requires neither hardware modification nor access to raw scanner data and supports 2D and 3D acquisitions with linear and curvilinear probes, making it widely applicable allowing clinicians to use our method on their already acquired scanners and images.
Read the full abstract ▾
All authors Valentin Bacher, Pak Hei Yeung, Bernhard Kainz, Madeleine K. Wyburd, Nicola K. Dinsdale, Michael Gray, Ana I. L. Namburete
Artificial Intelligence · Cross-listed from eess.AS
WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection
Kwok-Ho Ng, Tingting Song, Bingwen Feng et al. (+1 more)
The acoustic front-end determines which forensic cues a
speech deepfake detector can exploit. The wavelet scattering transform (WST) provides stable multiscale coefficients with explicit coordinates, yet direct flattening obscures the parent relation between paths. We introduce WST-Graph, reconstructing these paths as a sparse modulation-carrier grid for an AASIST graph backend. Modulation-level normalization and length-aware adaptive local
attention pooling produce fixed relative-time representations while retaining the acoustic axes before learned adaptation. This yields a waveform-to-graph interface with a fixed, parameter-free WST. Our configurations remain competitive with AASIST while using approximately 60% fewer trainable parameters and show clear gains on selected out-of-domain
benchmarks. These results underscore the value of preserving parent-child relations within the carrier-modulation
topology when constructing a compact, physically grounded interface for graph-based
speech deepfake detection. Code will be released at https://github.com/saki-ciallo/wst-graph.
Read the full abstract ▾
All authors Kwok-Ho Ng, Tingting Song, Bingwen Feng, Zhihua Xia
Computation and Language
BanglaTurn: A Benchmark and Whisper-Based Model for End-of-Turn Detection in Bangla Speech
Mizbaul Haque Maruf
This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational
speech, and a model trained on it. The corpus holds 35,374 samples of 3 to 15 s of podcast
speech, labelled for turn state by combining speaker diarization with an LLM pass, with every label then checked by a human annotator. The model pairs a Whisper encoder with task-specific classification heads. On a class-balanced test set drawn from a held-out podcast, it reaches 84.33% accuracy (95% CI 80.3 to 88.1) against 69.28% for the Smart-Turn v3 baseline, and lowers the false negative rate from 51.57% to 7.55% at the cost of a higher false positive rate. We report what encoder layer fine-tuning, multi-scale pooling and INT8 quantization each contribute, and latency stays within 165 to 191 ms end to end on CPU.
Read the full abstract ▾
Computation and Language
From Policy Documents to Structured Survey Responses: Evaluating Large Language Models for Policy Monitoring
Carolyn Cole, Matthias Deschryvere, Toqeer Ehsan et al. (+1 more)
Science, technology, and innovation policies are crucial for competitiveness, yet their diversity and scale make them difficult to map and monitor consistently. Existing approaches rely heavily on manual survey efforts, which are costly and challenging to scale across countries. Large
language models (LLMs) enable new possibilities for extracting and structuring information from long and unstructured policy documents. This paper presents an application of LLMs as "AI respondents" for generating structured survey responses from policy texts. We develop a data extraction pipeline based on long-context in-context learning to map information from public web sources into predefined survey categories, including policy instruments, target groups, and thematic areas. The pipeline integrates a validation step using a secondary LLM to assess relevance and evidence, alongside comparisons with human-provided responses. Using a multi-country
dataset, we evaluate the
alignment between LLM-generated and human-generated outputs through overlap measures and cross-validation. Results show that LLMs achieve high agreement for structured indicators (84-95%), while differences remain in free-text fields, where models tend to provide more detailed procedural descriptions. These findings highlight the potential of hybrid human-AI workflows for policy monitoring, improving both efficiency and scalability while maintaining the need for human validation and contextual interpretation.
Read the full abstract ▾
All authors Carolyn Cole, Matthias Deschryvere, Toqeer Ehsan, Arash Hajikhani
Numerical Analysis · Cross-listed from math.OC
Policy iteration for Hamilton-Jacobi-Isaacs equations with control constraints and comparison with Hamilton-Jacobi-Bellman equations
Sudeep Kundu and Karl Kunisch
Convergence of the bilevel policy iteration
algorithm for the value function, satisfying the Hamilton-Jacobi-Isaacs (HJI) equation, is analyzed in the presence of control constraints. Both first and second-order HJI equations corresponding to the deterministic and
stochastic systems are considered. For numerical tests, a semi-implicit upwind scheme for backward HJI PDEs is applied and a thorough comparison between the solutions to first and second-order Hamilton-Jacobi-Bellman (HJB) equations is presented for both the unconstrained and the constrained control cases.
Read the full abstract ▾
Artificial Intelligence
Epistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination
Mehdi Nasiri, Mohammad Saeed Arvenaghi, Sadegh Vaezi et al. (+1 more)
Multi-
agent large
language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens of multi-
agent systems theory, several shortcomings come to light: a lack of social intelligence, the absence of coordination mechanisms among
agents, unknown emergent behavior, and interactions between
agents that are bounded by natural
language. We address two of these gaps: the absence of social behavior and the lack of mechanisms for inter-
agent coordination. We introduce Epistemic Probabilistic
Language Agents (EPLA), a neuro-symbolic architecture for multi-
agent coordination under uncertainty. A Symbolic Guard provides structured diagnostic feedback. The LLM generates typed actions, and the Guard controls their execution against an authoritative symbolic state. We formalize the epistemic layer in a gossip testbed through epistemic lottery gossip models, which combine view-based call histories with
agent-indexed probability weights. We argue that implementing such a formalism can address shortcomings of agentic LLMs.
Read the full abstract ▾
All authors Mehdi Nasiri, Mohammad Saeed Arvenaghi, Sadegh Vaezi, Ebrahim Ardeshir-Larijani
Networking
NebulaSD: Many-for-Many Speculative Decoding
Junhao He and Hongyang Du
Speculative decoding accelerates Large
Language Model (LLM) inference by using a lightweight draft model to propose candidate
tokens for parallel verification by a target model. Drafting and verification, however, exhibit different service characteristics and favor different batch configurations, making fixed draft-target coupling inefficient under concurrent workloads. Existing distributed designs can physically separate the two stages, but often retain request or batch affinities that prevent their capacities from being shared globally. We present NebulaSD, a many-for-many, or M-for-N, speculative decoding system that organizes draft and target workers into independently schedulable resource pools and dynamically reconstructs stage-specific batches from shared request pools. Such dynamic reassignment removes fixed worker locality, requiring request states to be made available at newly selected workers without introducing migration stalls. NebulaSD addresses this challenge through worker-triggered batch reconstruction and asynchronous KV-state preparation overlapped with model execution. We evaluate NebulaSD from both system and scaling perspectives, showing that dynamic pooling improves request-round processing rate by 50.4% over a physically disaggregated baseline and 72.6% over co-located execution on a four-GPU deployment while substantially increasing effective GPU utilization. Profile-driven simulations further show approximately proportional compute-side capacity scaling under idealized state movement.
Read the full abstract ▾
Artificial Intelligence
Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses
Artur Jordao
The public visibility of Artificial Intelligence (AI) is growing rapidly, driven by the positive impact of its applications across diverse fields of knowledge. In this new chapter, courses that cover the foundations of AI and machine learning become essential for understanding their role and potential in contemporary society. Therefore, understanding fundamental concepts and elementary
algorithms through the close integration of theory with practice is essential in AI courses. In this essay, we report our experience designing machine learning exercises for automated assessment tools in programming. It is worth mentioning that we are not developing a novel form of automated grading system. Instead, we propose a perspective that frames machine learning problems as input-output assessment tasks. From this perspective, each exercise admits a unique and deterministic answer and enables automated programming assessment tools (e.g., VPL for Moodle, Codeforces, and MOJ) to effectively support AI education. We believe this essay can encourage instructors to foster educational innovation by adopting more dynamic and interactive approaches to AI courses that integrate theory and practice. Importantly, this essay does not introduce an innovation in the use of AI for education; rather, it introduces an innovative approach to improving the learning of AI, particularly, machine learning.
Read the full abstract ▾
Computation and Language
Parts-of-Speech as Emergent Categories in SAE Latent Space
Alessandro Bondielli, Lucia Passaro, Serena Auriemma et al. (+1 more)
Sparse AutoEncoders (SAEs) offer a promising way to inspect
language model representations, but it is still unclear what kind of linguistic structure their latents expose. We use part-of-
speech (PoS) categories as a controlled test case to study whether morpho-syntactic information is encoded by individual latents or by structured groups of features. We find that PoS distinctions are highly recoverable from SAE activations, but do not align with one-to-one latent / category mappings. This recoverability is not reducible to lexical memorisation, and Open and Closed PoS classes differ substantially. Categories are supported by compact groups of sparse latents, with substantial variation across tags. These groups remain stable on held-out data, while also showing overlap between related categories. Our results show that SAEs localise morpho-syntactic information in a distributed and category-dependent form rather than through atomic grammatical features.
Read the full abstract ▾
All authors Alessandro Bondielli, Lucia Passaro, Serena Auriemma, Alessandro Lenci
Computer Vision
Domain Recentering and Confidence-Weighted Prior Calibration for Vision-Language Models
Youngeun Seol, Jimin Shin, Heeseo Yoon et al. (+1 more)
Vision-
language models such as CLIP achieve strong zero-shot classification, yet under distribution shift, visual
embeddings drift from fixed text
embeddings. Training-free calibration avoids the per-sample optimization of
prompt learning, but prior feature calibration gives each image the full bias of one hard cluster. We propose Domain Recentering with Confidence Calibration (DRC), a training-free method adapting CLIP from a set of unlabeled target images. DRC fits a Gaussian mixture once and subtracts from each
embedding a posterior-weighted average of component means. It then removes residual class preference with a log-prior correction, estimating the prior from confidence-weighted predictions. Among compared methods, DRC achieves the highest average accuracy on cross-domain
datasets, exceeding zero-shot CLIP by 4.13 and 5.07 points with ViT-B/16 and ResNet-50, with gains over CLIP also holding under ImageNet distribution shifts.
Read the full abstract ▾
All authors Youngeun Seol, Jimin Shin, Heeseo Yoon, Uiwon Hwang
Numerical Analysis
A Regularization Based Computational Method for Quantum Incommensurate Problems
Zhenan Ding, Yan Li, Aihui Zhou et al. (+1 more)
Quantum incommensurate systems have attracted widespread interest due to their unique physical properties. Related studies have made notable progress in recent years. To gain deeper insight, it is both significant and challenging to study a broader range of physical observables for these systems, which requires a comprehensive understanding of their spectral properties and wavefunction behavior. Based on the regularized model recently proposed, this work introduces a regularization framework, rendering physical observables for incommensurate systems mathematically well-defined and computationally accessible with theoretical guarantees. Based on this framework, taking the density of states and the electron density as representative examples, we establish their mathematical characterization, derive their planewave approximations, and provide a rigorous convergence analysis. Numerical experiments validate the effectiveness of our method, demonstrating its practical applicability for generic 1D and 2D incommensurate systems.
Read the full abstract ▾
All authors Zhenan Ding, Yan Li, Aihui Zhou, Yuzhi Zhou
Robotics
C-space Analysis using Tropical Geometry
Abhilash Nayak
Configuration space~(C-space) of a mechanism is a real variety describing the set of feasible configurations that it can attain. To understand the behavior of a mechanism, it is crucial to identify and scrutinize especially the singular points of its C-space. They usually appear when the variety intersects itself, leading to different branches of motion. There exist many approaches to detect those intersections if they are transversal. However, the problem remains challenging if there are tangential, cuspidal, inter-dimensional or a combination of these intersections. This paper exploits an approach acquired from tropical geometry to analyze the neighborhood of any point on C-spaces of 1-degree-of-freedom~(dof) mechanisms. This is done by finding the approximate rational parametrization of the curve(s) passing through the given point using Puiseux series. The proposed approach is shown to succesfully detect the transversal branchings in two foldable four bar mechanisms and a cusp in the configuration curve of the double Watt mechanism.
Read the full abstract ▾
Computer Vision
Learning a Flow to Self-Supervised Representations
Yuling Jiao, Wensen Ma, Houduo Qi et al. (+1 more)
We introduce Flow-Based Distribution Matching (FBDM), which learns self-supervised representations through non-
adversarial velocity regression. The encoder and auxiliary field are trained jointly by regressing analytic velocities along spherical paths from learned representations to reference targets. Both augmented views share a reference target, with a capacity limit on each reference center and an explicit view-
alignment loss. A structured reference supports more components than the auxiliary flow dimension while retaining
geometric separation. The auxiliary field is discarded after pretraining; only the backbone is retained downstream. On three ResNet-18
benchmarks with matched auxiliary parameter counts, FBDM provides 2.17 to 2.36 times higher per-epoch training throughput than critic-based Distribution Matching (DM), with about 0.21 GiB additional peak allocated GPU
memory. Experiments show that FBDM is competitive with existing SSL methods from CIFAR to ImageNet and performs comparably to DM on their shared
benchmarks. Under stated conditions, our population analysis bounds nearest-centroid classification error on the initial normalized pretraining representation by the FBDM loss.
Read the full abstract ▾
All authors Yuling Jiao, Wensen Ma, Houduo Qi, Defeng Sun
Computation and Language
ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts
Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi et al. (+5 more)
ArGuard is a shared task on harmful content detection in Arabic memes and LLM
prompts. It includes two tracks: Track A focuses on
multimodal hate detection in Arabic memes, while Track B addresses harmful
prompt detection for Arabic LLM safety evaluation. In total, 58 teams registered, 35 participated in the final evaluation, and 27 submitted system-description papers. Participating teams explored models such as AraBERT, Jais, and Qwen3-VL. The best systems achieved macro-F1 scores of 0.823 on A1, 0.419 on A2, 0.984 on B1, and 0.790 on B2. Fine-grained meme classification in A2 was the most challenging setting, partly due to sparse labels and train-test distribution shifts.
Read the full abstract ▾
All authors Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Hamdy Mubarak, George Mikros, Abul Hasnat, Wajdi Zaghouani
Computer Vision
SEE Challenge 2026: Event-Guided Brightness Adjustment Across a Broad Illumination Range
Yunfan Lu, Mingchao Xu, Hanyu Zhou et al. (+9 more)
Event cameras provide a high dynamic range and preserve brightness-change cues in lighting conditions where conventional RGB frames may be noisy or saturated. To
benchmark event-guided restoration across a broad illumination range, we organized the SEE Challenge 2026 with the Event-Based
Multimodal Vision Workshop at ECCV 2026. The task conditions restoration on one or more RGB frames, synchronized events, and a scalar target-brightness statistic provided by the organizers. It uses SEE-600K, which contains 610,126 image-event observations from 202 real-world scenes spanning low-light, normal-light, and high-light conditions with illumination variations of up to 1,000$\times$. The challenge follows an open-system protocol: participants may use different temporal contexts, architectures, pretrained weights, test-time augmentation, and post-processing strategies. PSNR determines the ranking, and SSIM is reported as a secondary metric. Around 70 teams registered interest and 15 valid CodaBench submissions were received. Six distinct teams completed organizer-side identity and technical verification, provided method descriptions, checkpoints, inference code, and instructions, and are included in the verified open-system ranking reported here. Beyond the ranking, this report analyzes exposure subsets, semantically distinct test cases, a shared failure pattern, system design choices, and inference strategies. The top systems obtain closely spaced average scores, while the best-performing method varies across cases and metrics; under severe underexposure, all verified systems retain visible local errors.
Read the full abstract ▾
All authors Yunfan Lu, Mingchao Xu, Hanyu Zhou, Shaoyu Liu, Haoyue Liu, Peiqi Duan, Shihan Peng, Yinqiang Zheng, Boxin Shi, Gim Hee Lee, Hui Xiong, Davide Scaramuzza
Artificial Intelligence
The Last Human Gate: Forward Deployed Engineering for Governance Automation
Jeremy Canale
Enterprise governance requires decisions, evidence, and accountable authority; it does not require every review task to retain its current human implementation. We develop a task-substitution framework for Digital Governance Frameworks (DGF), treating each gate as an executable contract. Substitution requires sufficient accessible information, valid decision and authority checks, and a reduction in total human work after exceptions, verification, correction, and maintenance are counted. We derive a residual-work threshold and show why automating most cases can still increase labor. Forward deployed engineering connects these conditions to an architecture for
agents, rule engines, evidence services, and escalation. DGF-Bench supplies controlled evidence from 300 synthetic projects and 899 evaluable model-project runs. Gemini 3.8 Flash, GPT-5.6 Luna, and DeepSeek v4.1 Flash achieve strict gate success of 94.98%, 83.29%, and 74.18%; complete-route success is 76.92%, 42.33%, and 24.67%. A deterministic control passes all 1,700 gates given the supplied rules and structured facts, locating the comparison in execution of a supplied decision kernel. Evidence audits and 135 repeated runs distinguish correct decisions from reliable execution. A document counterexample establishes an information-sufficiency obstruction. These results support the technical feasibility of replacing human execution of specified governance-review tasks with
agents and software. The framework specifies a workforce test based on the complete human effort required at fixed output and quality; the present measurements concern review performance. Sources, dossiers, traces, and analyses are public.
Read the full abstract ▾
Sound
Speech Block Influence: Component-Specific Layer Scoring for Pruning Speech LLMs
Siyu Yao, Du Q. Huynh, Lian Xu et al. (+1 more)
Speech LLMs are costly to deploy in resource-constrained settings. Layer
pruning can cut this cost, but existing scoring metrics transfer poorly to
speech LLMs: they assume a decoder-only architecture with homogeneous
token sequences, whereas
speech LLMs add encoder and adapter components and process
multimodal sequences. We propose
Speech Block Influence (SBI), the first layer-importance scoring framework designed for
speech LLM
pruning that consists of two component-specific scores: SBI-Enc measures the effect of encoder-layer removal at the adapter's output to better reflect downstream impact; SBI-Dec measures layer-wise input-output similarity over text-
token positions only to avoid audio-
token dominance. Across three
speech LLMs, SBI improves
pruning robustness, with stronger encoder performance at higher
pruning rates and more reliable decoder layer selection by scoring text
tokens rather than the audio-dominated full sequence. We further find that text-only calibration yields decoder rankings highly correlated with those from
speech-text calibration, suggesting a cheaper alternative to measure decoder layer importance.
Read the full abstract ▾
All authors Siyu Yao, Du Q. Huynh, Lian Xu, Mark Reynolds