Information Retrieval
Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction
Sofia Gulevskaia, Mikhail Trapeznikov, Aleksandr Poslavsky et al. (+1 more)
Accurate watch-time (WT) prediction is an important requirement for short-
video recommendations. Yet WT distributions are near-zero-inflated, long-tailed and
multimodal. The recent Exponential-Gaussian Mixture Network (EGMN) models the full conditional WT distribution rather than a single point estimate and achieves state-of-the-art performance. Our large-scale reproduction study reveals that EGMN is vulnerable to variance collapse, component redundancy, and inactive components. We propose a Hierarchical Exponential-Gaussian Mixture (HEGM) model that addresses these failure modes through a hierarchical skip-watch decomposition, structured initialization, removal of the forced Gaussian shift and
entropy regularizer and optional KL-based variance regularization for over-parameterized mixtures. Across large-scale industrial and public
datasets, under a fixed-backbone head-replacement protocol, HEGM improves ranking accuracy and threshold-event prediction over reproducible lightweight baselines, while maintaining competitive point-estimation accuracy and substantially improving mixture stability and interpretability. A 1.5-month production A/B test confirms statistically significant engagement lifts. Our code and models are publicly released at https://github.com/rw404/HEGM.
Read the full abstract ▾
All authors Sofia Gulevskaia, Mikhail Trapeznikov, Aleksandr Poslavsky, Alexander D'yakonov
Robotics
Alperen Avan and Jordi Sanchez-Riera
Autonomous indoor
navigation requires both semantic understanding and precise
geometric control. We propose OptiSight, a hybrid framework that combines
Vision-
Language Model
reasoning with deterministic visual servoing through a finite-state Chain-of-Thought architecture. Grounded-SAM localizes open-vocabulary targets, while camera projection geometry converts visual observations into
navigation commands without requiring dense mapping. The VLM is queried only at key decision points, reducing computational overhead while
geometric control handles continuous
navigation. Experiments in AI Habitat demonstrate reliable zero-shot
navigation across diverse indoor scenarios, including obstacle avoidance and semantic ambiguity, while operating within an 8~GB VRAM budget. The source code is available at https://github.com/avanalperen/OptiSight-Python-
Multimodal-CoT-for-Visual-
Reasoning.
Read the full abstract ▾
Computation and Language
FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations
Haofeng Yuan, Jianing Peng, Jieyi Bi et al. (+3 more)
Mixed-integer programming (MIP) lies at the core of operations research and industrial optimization. While large
language models (LLMs) have recently shown promise in automated MIP modeling from natural
language, they prioritize semantic correctness but overlook formulation strength, severely bottlenecking the efficiency of downstream solvers. We propose FormuEvo, an LLM-guided evolutionary framework for automated discovery of solver-efficient MIP formulations. FormuEvo frames MIP formulation design as evolutionary optimization over the symbolic space of MIP formulations, represented as executable modeling programs, by iteratively generating, evaluating, and selecting stronger candidates via LLM-driven crossover, mutation, and repair operations. To move beyond blind exploration, FormuEvo introduces a solver-informed diagnosis mechanism that exploits fine-grained solver statistics as verbal gradients for targeted refinement. Additionally, a structured
memory abstracts prior experience into reusable modeling strategies, avoiding redundant exploration while enabling zero-shot transfer to unseen problems and bootstrapping smaller LLMs. Experiments across diverse linear and non-linear problems demonstrate that FormuEvo discovers formulations that significantly outperform both expert-designed formulations and existing LLM-based approaches, accelerating solvers by up to 5.5$\times$, with distilled knowledge transferring effectively across problems and model scales.
Read the full abstract ▾
All authors Haofeng Yuan, Jianing Peng, Jieyi Bi, Ni Zhang, Shiji Song, Zhiguang Cao
Data Structures and Algorithms
Asymptotically Tight Fractional Online Matching Under Edge Arrivals
David Wajc
In this brief note, we close the asymptotic gap between known upper and lower bounds for fractional online matching under edge arrivals. We prove that the optimal competitive ratio for this problem is $1/2+\Theta(1/n)$. The
algorithm was suggested and analyzed by OpenAI's ChatGPT Sol based on a single
prompt. The presentation was streamlined over a few hours, based on a back and forth discussion with the author, who assumes responsibility for any errors.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.OT
Beyond chlorophyll: machine learning estimates of diagnostic phytoplankton pigments from multispectral ocean colour data
David Moffat, Angus Laurenson, Victor Martinez-Vicente et al. (+4 more)
Phytoplankton play a central role in marine ecosystems and the global carbon cycle, with different groups contributing differently to ocean biogeochemical processes. While standard techniques exist for monitoring phytoplankton concentration from ocean-colour data, their community composition remains difficult to observe at large scales. Chlorophyll-a, widely available from satellite ocean-colour observations, is commonly used as a measure of phytoplankton biomass but provides limited information on taxonomic composition. Accessory pigments, some of which are diagnostic of important phytoplankton groups, offer additional information on community structure, but their
retrieval from ocean-colour data is challenging because of limited spectral resolution and strong covariance with chlorophyll-a. In this study, we evaluate machine learning methods for estimating diagnostic pigment concentrations from multispectral satellite observations. Using a global
dataset of 33,640 High Performance
Liquid Chromatography (HPLC) measurements matched with ESA Ocean Colour
Climate Change Initiative (OC-CCI) reflectance data, we compare Random Forest and TabPFN models trained on multispectral reflectance with baseline models using chlorophyll-a alone. A temporally stratified validation scheme is employed to reduce the effects of autocorrelation. Results show that multispectral models consistently outperform approaches based solely on satellite-derived chlorophyll-a, demonstrating that ocean-colour reflectance contains additional information relevant to pigment discrimination. Improvements vary by pigment, with those strongly correlated with chlorophyll-a showing limited gains, while others exhibit substantial improvement. These findings highlight the potential of machine learning to extract ecologically relevant information from satellite data beyond conventional chlorophyll-based approaches.
Read the full abstract ▾
All authors David Moffat, Angus Laurenson, Victor Martinez-Vicente, Gemma Kulk, Xuerong Sun, Robert J. W. Brewin, Shubha Sathyendranath
Machine Learning
Test-Time Adaptation for ECG Classification via SQI-Gated Self-Training and Beat-Rhythm Consistency
Wenhan Jiang, Zhipeng Deng, Jiale Zhou et al. (+3 more)
Deep learning models for electrocardiogram (ECG) classification often suffer from significant performance degradation when deployed in unseen domains due to shifts in acquisition devices and patient populations. Test-time adaptation (TTA) offers a practical solution by adapting models using only unlabeled data at inference time. However, existing TTA methods often underperform on ECG tasks, since naive online updates ignore the hierarchical beat-rhythm structure of cardiac cycles and are vulnerable to signal artifacts, which leads to unstable adaptation and model drift. We propose BeatRhythm-TTA, an ECG-tailored TTA framework that explicitly accounts for ECG's noisy observations and structured beat-rhythm semantics under domain shift. First, to handle pervasive ECG artifacts, we introduce a Signal Quality Index (SQI)-gated adaptation scheme that selectively filters out low-quality signals to prevent harmful updates. Second, to leverage ECG's beat-rhythm semantics, we enforce dual-level consistency so the model preserves beat morphology and rhythm dynamics while adapting to shifted acquisition conditions. Extensive experiments on multi-label ECG diagnosis across three adaptation protocols, using PTB-XL as the source domain and CPSC2018/Georgia as two target domains, demonstrate the effectiveness of our method, yielding an average +2.70% relative improvement in Macro-F1 over the best competing method.
Read the full abstract ▾
All authors Wenhan Jiang, Zhipeng Deng, Jiale Zhou, Haolin Wang, Yafei Ou, Yefeng Zheng
Human-Computer Interaction
Beyond the Mirror: Balancing Interaction Modality and Avatar Fidelity in Public 3D Virtual Try-On Systems
Yueqian Guo, Tianzhao Li and Xin Lv
Virtual Try-On (VTON) systems deployed on large public displays face a dual barrier: the physical strain of mid-air interaction and the social inhibition caused by public self-consciousness. This paper presents a real-time 3D avatar system integrating markerless motion capture with dynamic visual fidelity control to investigate and mitigate both barriers. Through a dual-study empirical evaluation, we first decoupled physical fatigue from gesture interaction ($N=20$), demonstrating that interaction fatigue is primarily driven by visuomotor latency rather than the physical act of gesturing; our optimized low-latency gesture pipeline achieved usability comparable to touchscreens while delivering superior immersion and hygiene. Building on these insights, our second study ($N=25$) investigated the "avatar fidelity paradox" via a $2 \times 2$ factorial design manipulating interaction modality (gestures vs. touch) and visual fidelity (photorealistic MetaHuman vs. stylized mannequin). Results reveal that while high fidelity and mid-air gestures independently maximize virtual embodiment ($p < .05$), their combination elicits the highest social awkwardness. Crucially, low-fidelity avatars serve as a "psychological mask" that alleviates public embarrassment during expressive gestures, while mid-air gestures simultaneously act as a compensatory mechanism to preserve perceived try-on trust despite reduced visual realism. Finally, we propose a context-aware fidelity framework to balance
privacy, immersion, and commercial trust in public spatial interactions.
Read the full abstract ▾
Machine Learning
Towards Actionable Surgical Team Dynamics: from Teamwork to Counterfactual Annotations
Vincenzo Marco De Luca, Antonio Longa and Andrea Passerini
Modeling team interactions in high-stakes environments such as operating rooms is critical for understanding how coordination, communication, and individual behaviors shape team performance and safety outcomes. Existing
datasets in this domain are often fragmented across modalities, annotation schemes, and formats, limiting their ability to support integrated analyses of real-world collaborative processes. We address this limitation by introducing an extended
multimodal dataset for
surgical team interaction analysis, built from real operating room recordings. Starting from an existing corpus, we construct an analysis-ready version of the data by providing speaker diarization, transcripts, and multi-level annotations capturing team performance, interaction processes, and individual characteristics. Team performance is assessed using a standardized
surgical teamwork evaluation protocol, while interaction quality and individual attributes are annotated through structured rating schemes covering collaboration, group dynamics, and non-technical skills. To further support the study of coordination breakdowns and performance variability, we introduce counterfactual annotations that describe plausible alternative team outcomes in the presence of observed interaction failures, enabling analysis of how specific behavioral patterns may relate to different trajectories of team performance. In addition, we provide structured temporal and relational representations designed to support computational modeling of teamwork processes and the design of AI-assisted collaborative systems. The
dataset is designed to support the study of how individual actions, interaction patterns, and team-level processes jointly contribute to team outcomes in
surgical settings, providing a unified resource for analyzing collaborative behavior in high-stakes domains.
Read the full abstract ▾
Computer Vision
Controllable blind deblurring with diffusion models
Imane Si Salah, Emile Cribelier, Thomas Veit et al. (+2 more)
Image acquisition with a camera involves several degradations due to the optical system, sensor, or low-level processing steps. We address blind deblurring in professional photography: we aim to invert unknown isotropic blur without knowledge of the degradation kernel. For such inverse problems,where some high-frequency information is lost, it is challenging to use generative models to produce details that are both photo-realistic and faithful to the input. We propose SuperSharpen, a
diffusion-based blind deblurring method offering explicit control over restoration strength through a blur measure. We compare two conditioning strategies: a ControlNet-style adapter on a frozen backbone, and full finetuning of the
diffusion prior. Our experiments show that finetuning achieves better fidelity with fewer hallucinated details. We validate our approach on synthetic and real-world blur, demonstrating improved perceptual quality and controllable restoration strength.
Read the full abstract ▾
All authors Imane Si Salah, Emile Cribelier, Thomas Veit, Wolf Hauser, Arthur Leclaire
Software Engineering
DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation
Hao Liu, Steven Liu, Xin Zhang et al. (+8 more)
Reproduction test generation, producing a failing-then-passing test that captures a reported bug, is a critical step in automated software engineering. Existing agentic methods treat this as a monolithic loop, despite the task inherently comprising two subtasks of distinct nature: diagnosing the root cause and writing a fail-to-pass test. Without explicit separation, the
agent faces a compound objective with underspecified intermediate goals, leading to goal drift. We propose DPIAgent, a structured agentic framework built on three principles, Divide, Protocol, Isolate (DPI), that mitigates compound-objective ambiguity and goal drift: it Divides the task into single-objective phases of defect exploration and test generation; enforces a handoff Protocol that records the diagnosis and test plan, preventing context loss; and Isolates each phase's action space by tailoring the toolset to its task, preventing irrelevant tools from misleading execution. On SWT-Bench Verified, DPIAgent outperforms seven baselines across three backbone LLMs. With DPI alone it reaches 81.76% success rate on GPT-5, the highest reported among open-source methods, gaining up to 11.88 points over the strongest baseline on GPT-5-Mini; adding test selection further raises it to 86.17%. Our analysis shows that architectural structure and backbone capability are complementary axes rather than substitutes, demonstrating DPI's generalizability across model classes.
Read the full abstract ▾
All authors Hao Liu, Steven Liu, Xin Zhang, Jane Luo, Yu Kang, Jie Wu, Fangkai Yang, Yangyu Huang, Pengfei Gao, Scarlett Li, Yan Lu
Networking
CERTIoT-6G: Continuous Cybersecurity Certification for IoT Devices in 5G/6G Networks
Evangelos Lempesis, Fabio Palmese, Hamed Haddadi et al. (+1 more)
The massive adoption of Internet of Things (IoT) devices across critical domains such as healthcare, smart cities, industrial automation, and critical infrastructure introduces significant cybersecurity and regulatory challenges. Current and forthcoming European regulations, including the Cyber Resilience Act (CRA) and the NIS2 Directive, require manufacturers, operators, and other organizations to ensure secure-by-design devices, continuous vulnerability management, and resilient operation throughout the device lifecycle. Traditional certification mechanisms remain static, manual, and difficult to scale across heterogeneous IoT ecosystems. This paper presents CERTIoT-6G, a Security-as-a-Service (SECaaS) framework that enables automated cybersecurity certification and continuous compliance monitoring of IoT devices operating in 5G and future 6G networks. The framework integrates automated compliance analysis, real-time traffic monitoring, and
adversarial testing capabilities. We validate the CERTIoT-6G framework on different IoT device categories operating in an advanced 5G testbed. Evaluation results reveal critical compliance gaps, particularly in traffic encryption and availability under unstable conditions, and demonstrate that the framework produces actionable verdicts mapped to regulatory requirements across heterogeneous device types. Furthermore, we show that the monitoring pipeline has a negligible impact on live 5G traffic.
Read the full abstract ▾
All authors Evangelos Lempesis, Fabio Palmese, Hamed Haddadi, Anna Maria Mandalari
Computation and Language
The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning
Matthew Perlman, Atharva Nijasure and James Allan
LoRA fine-tuning is standard for adapting LLMs to reranking, but it remains unclear where in the network task-specific relevance behavior is learned and what
attention-level changes accompany that learning. Through ablation and
attention experiments, we identify where LoRA
attention updates to RankLLaMA improve performance and whether those gains coincide with interpretable relevance-oriented
attention patterns such as lexical matching, rarity sensitivity, and query-document interaction. We find that given LoRA fine-tuned MLPs throughout the network, restricting LoRA
attention updates to a compact mid-network region is sufficient for recovering over half of the performance gained by applying LoRA to all
attention layers, and that omitting
attention fine-tuning in this region hurts performance more than elsewhere in the network. Additionally, we show that regions where applying LoRA affects performance the most overlap with regions where fine-tuning increased
attention to axiomatic IR features. Rarity sensitivity, document-query interaction, and several compositional features are highly correlated with gains in ranking performance. Our results support an interpretable, correlational account of how relevance-oriented behavior emerges during LoRA fine-tuning and point toward improved strategies for adapting rerankers.
Read the full abstract ▾
Systems and Control
Artificial intelligence-based predictive fuel blending control for flare gas mitigation
Josip Kir Hromatko, Šandor Ileš, Rube Huljev et al. (+1 more)
This paper describes a fuel blending
algorithm based on artificial intelligence and model predictive control. A gas-fired power plant was modeled using physical laws and on-site measurements. A neural network is used to calculate the methane number of the fuel and determine the fuel blending ratio limits so that the methane number is within the limits specified by the engine manufacturer. A model predictive controller adjusts the final blending ratio to meet safety requirements and minimize operating costs. The
algorithm was tested in simulations with different scenarios and a reduction in both the operating costs and amount of flaring was observed.
Read the full abstract ▾
All authors Josip Kir Hromatko, Šandor Ileš, Rube Huljev, Velibor Vučković
Computer Vision
Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline
Eugenia Moris and José Ignacio Orlando
Developing competitive deep learning baselines for medical imaging remains a highly iterative process requiring literature review, implementation, experimentation, and expert refinement. Existing automation approaches typically optimize isolated components, such as architecture search or hyperparameter tuning, rather than the complete baseline development process. We present an agentic AI Scientist workflow that combines literature-guided
reasoning, automated code generation, and hypothesis-driven experimentation to generate competitive baseline models for medical imaging challenges. The framework is evaluated on four public
benchmarks spanning
segmentation, classification, and detection. Across all tasks, the Experimentation Pipeline consistently improves validation performance, achieving competitive leaderboard results, including 6th place on both PUMA tracks (15 teams) and 31st place on MILK10k (125 teams). On MIDOG25, the resulting model also demonstrates strong domain generalization across scanners, tumor types, and species. Using the same workflow across all challenges without task-specific redesign, we demonstrate that skill-based, literature-guided agentic workflows can substantially reduce the engineering effort required to develop competitive medical imaging baselines.
Read the full abstract ▾
Computer Vision
IntentQA: Intent Question Answering in Videos by Cognitive Context Reasoning
Jiapeng Li, Ping Wei, Wenjuan Han et al. (+2 more)
Video understanding requires intelligent
agents to transcend mere recognition of visual facts and comprehend the underlying intents behind human actions (often termed the "dark matter" of social intelligence). To bridge the gap between visual observation and intent
reasoning, we introduce a novel task, IntentQA, and contribute a large-scale VideoQA
dataset specifically tailored for this purpose. However, recognizing that standard metrics may overestimate capabilities due to
dataset biases, we go beyond simple accuracy to rigorously evaluate model robustness. We augment the
benchmark by generating five distinct contrast sets via Large
Language Models (LLMs) and introducing a "Contrast Performance Decline" metric. We propose the X-CaVIR (eXplainable Context-aware
Video Intent
Reasoning) framework, which leverages three types of "Cognitive Context" to enhance
video analysis: i) Situational Context via a cross-modal
Video Query
Language (VQL) module, ii) Contrastive Context via a Contrastive Learning module, and iii) Commonsense Context via a Commonsense
Reasoning module. Crucially, to overcome the opacity of traditional black-box models, we refine the integration of LLMs within X-CaVIR by employing a transparent pipeline that synergizes
video captions with VQA model outputs. This approach not only improves performance by effectively utilizing rich commonsense knowledge but also renders the
reasoning process explicitly interpretable. Extensive experiments demonstrate the effectiveness of our components, the superiority of X-CaVIR over state-of-the-art baselines, and its stability against perturbations on the contrast sets.
Read the full abstract ▾
All authors Jiapeng Li, Ping Wei, Wenjuan Han, Song-Chun Zhu, Lifeng Fan
Computer Vision
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
Wenqi Liu, Shijie Ma, Yunxiao Wang et al. (+21 more)
Open-world
video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the
video and its parametric
memory. While Thinking-with-
Videos enables active temporal perception and Deep Research supports multi-step information seeking, the two capabilities are typically developed in isolation. We introduce VideoRover, a unified
Video Deep Research framework that iteratively coordinates
video cropping,
multimodal search, and webpage browsing. Given a
video-question pair, VideoRover uses each tool result to select the next action, so localized
video clips guide external
retrieval and retrieved evidence triggers further
video inspection and verification. To develop this capability, we construct an automated data curation pipeline, producing 26K verified SFT trajectories and 3K challenging RL instances. We also introduce VideoRover-Bench, a
benchmark stratified by
video duration and research difficulty. Experiments on VideoDR and VideoRover-Bench show that our VideoRover-8B-RL achieves performance comparable to proprietary models in the direct-answer setting without tool use while outperforming larger open-source models equipped with the same tool suite. Ablation studies and training dynamics further validate the complementary roles of active
video grounding, external
retrieval, and long-horizon reinforcement learning.
Read the full abstract ▾
All authors Wenqi Liu, Shijie Ma, Yunxiao Wang, Meng Liu, Qile Su, Han Liu, Bohan Hou, Zeyu Wang, Xuanyu Zheng, Changyi Liu, Tianke Zhang, Haonan Fan, Kaiyu Jiang, Yingxin Li, Jiankang Chen, Xu Wang, Hongyi Fu, Jianxiong Wang, Bin Wen, Tingting Gao, Han Li, Jianhua Yin, Yinwei Wei, Xuemeng Song
Systems and Control
Admissible Unit Range of Plug-and-Play Distributed Energy Resource (DER) Systems Under Delay: A Scalable Design Framework
Haruhisa Ichikawa, Shinji Yokogawa, Yuusuke Kawakita et al. (+1 more)
This paper addresses the fundamental design problem of plug-and-play distributed energy resource (DER) systems, which are emerging as a scalable solution for integrating distributed generation through user-driven connection of modular units. In such systems, the number of connected units is not fixed but dynamically varies due to user operation and system conditions, requiring stability and operational constraints to be guaranteed over a range of system sizes rather than for a single configuration. To address this challenge, we propose the Plug-in DER Orchestrated Grid (PDOG) and develop a normalized analytical framework in terms of normalized delay and aggregate loop gain. This formulation enables explicit characterization of the stability boundary together with a lower bound derived from the no-reverse-power constraint, defining a feasible region for system operation. By mapping this feasibility condition into the number of DER units, the admissible range of connectable units is obtained as a function of delay. The analysis reveals a fundamental trade-off: while the theoretical stability limit increases with normalized delay, implementation-induced gain amplification reduces the practical hosting capacity. As a result, the admissible system size exhibits a non-monotonic dependence on delay, and a feasibility boundary may emerge beyond which no admissible system size exists. These results provide explicit design guidelines for determining the number of DER units under delay and implementation constraints, establishing a new paradigm in which system scalability is explicitly constrained and engineered.
Read the full abstract ▾
All authors Haruhisa Ichikawa, Shinji Yokogawa, Yuusuke Kawakita, Yoshito Tobe
Computation and Language
Flesch-Kincaid Readability Depends Only on the Topic Distribution in Long Texts under Topic Models
Yo Ehara
Flesch Reading Ease (FRE) and the Flesch-Kincaid Grade Level (FKGL) are widely used readability scores for English computed from the same two document statistics, yet their stability on long documents need not imply invariance to lexical composition. Surprisingly, under a topic model with an explicit sentence-boundary
token, both scores converge almost surely to deterministic functions of the document topic distribution through just two scalar rates: in the long-text limit, all score variation is mediated by topical composition rather than any residual readability signal. The theory covers both formulae, while the experiments evaluate FKGL. In a fixed admixture with rank[1, q, s] = 3, fibres through interior topic vectors are locally (K-3)-dimensional, whereas regular iso-score level sets are locally (K-2)-dimensional and curved. In out-of-fold evaluation on two balanced corpora, Brown and the written BNC, a topic vector inferred from one document half's content words predicts the other half's FKGL at r = 0.779 and 0.884, respectively. On Brown, adding the topic prediction to genre and mean content-word syllable count yields $\Delta R^2$ = 0.002, with a confidence interval spanning zero; on the BNC, the corresponding split-half increment is 0.024, positive in four of five K = 100 fits (median 0.021). Because inferred topics may also absorb genre, register, and style, we do not interpret these results as evidence about human readability or causal effects.
Read the full abstract ▾
Symbolic Computation
Least-Squares and Low-Rank Approximation for Linear Relations Using a Diagrammatic Language
Júlia de Araújo Mota, Iago Leal de Freitas, Lucas Rufino et al. (+1 more)
We employ the machinery of linear relations to the study of optimization problems in linear
algebra. We first show that the relational version of the pseudo-inverse can be realized through a generalization of the least-squares problem. This allows one to prove that the pseudo-inverse realizes the solution of certain relational optimization problems. Our main result is showing that a certain truncation of this pseudo-inverse defines a solution to a relational version of the classical low-rank approximation problem which recovers both the Eckart-Young
Theorem and several optimization problems involving pairs of
matrices and vector spaces.
Read the full abstract ▾
All authors Júlia de Araújo Mota, Iago Leal de Freitas, Lucas Rufino, João Paixão
Neural and Evolutionary Computing
Mycelial Search: A Graph-Structured Metaheuristic for Continuous Optimisation
Mohammad Mahdi Dehshibi
Continuous optimisation methods need to balance sharing information and maintaining alternative search directions. In this paper, we introduce Mycelial Search (Myco), a graph-structured metaheuristic designed around active tips, community-weighted flow, adaptive cord plasticity, and anchor-based injection. Candidate solutions form an evolving spatial graph in which a Louvain partition distinguishes within-community from cross-community information exchange. Adaptive cord plasticity subsequently modifies active tip-to-tip edges according to their
alignment with the local flow. An anchor-based injection mechanism supplements the graph-driven tip dynamics. We evaluated Myco on the CEC 2022 single-objective bound-constrained
benchmark suite at dimensions $D=10$ and $D=20$, using 30 independent runs per
algorithm-function pair. The comparison includes eleven established optimisers from several search families. Myco reaches competitive results on selected functions across both dimensions. The ablation analysis further shows that community structure regulates the range of graph-based information exchange, whereas cord plasticity controls the persistence of local directional influence. These findings indicate that graph-structured local interaction can support continuous optimisation, while its effectiveness depends on landscape structure and information transfer across local search regions.
Read the full abstract ▾
Machine Learning
Beyond Point Predictions: Uncertainty-Aware Satellite Poverty Mapping for Public Policy
Markus B. Pettersson, James Bailie, Mohammad Kakooei et al. (+2 more)
Despite their critical importance for policy and research, high-resolution poverty data remain limited across much of Africa. Machine learning (ML) with earth observation (EO) imagery has recently emerged as a way to supplement these data by predicting (i.e., estimating) poverty where it has not been directly measured. Yet to be used reliably, decision-makers and analysts need assurances that they will not be misled by the errors in these predictions. To meet this need, we develop an uncertainty-aware EO-ML method for poverty mapping based on simultaneous
quantile regression and a novel form of conformal prediction. Using a spatiotemporal
transformer trained on sequences of Landsat and nighttime-light images, we produce prediction intervals for neighborhood-level International Wealth Index estimates across Africa which are statistically guaranteed to achieve their desired coverage rates. While our method's point-prediction performance matches the state of the art, its prediction intervals are wider than might be expected given its high $R^2$ of $0.75$. However, other models of similar accuracy likely suffer from comparable uncertainty, pointing to an inherent limitation: even with its remarkably high explanatory power, EO-ML cannot naively be relied upon for policy-making, such as when designing poverty-targeting programs. To handle this challenge, we develop a procedure to efficiently allocate aid using both ground-truth surveys and model predictions while provably ensuring the risk of excluding eligible neighborhoods remains below a prespecified level. In simulations, this approach delivers substantially more aid per eligible recipient than other strategies, thereby demonstrating that EO-ML can indeed be a reliable supplement to traditional data sources.
Read the full abstract ▾
All authors Markus B. Pettersson, James Bailie, Mohammad Kakooei, Eagon Meng, Adel Daoud
Robotics
ROS2SmolVLA: Enabling Small Vision-Language-Action Models for Integration into Industrial-Grade Lightweight Robots
Nils Mandischer, Noah Böckmann, Ludwig Holl et al. (+1 more)
Industrial demand changes the paradigms of production. Due to smaller batch sizes and more variations in products, companies face a growing challenge to adopt more adaptive production systems. In particular,
robot-based automation is usually static and fails to respond to constantly changing processes.
Vision-
Language-Action (VLA) Models are a promising opportunity to mitigate this challenge by generating
robot actions based on the observed system state. However, current research either focuses on large models that cannot be computed on premise, creating compliance and security challenges, or use lab-grade
robot hardware that obscures exploitation in real industrial settings. In this work, we adapt Hugging Face's SmolVLA for Universal
Robots lightweight
robots. Further, we release the open-source repository ROS2SmolVLA that implements an interface for ROS 2 to SmolVLA, and makes it applicable for industrial-grade hardware. By this, we allow a lenient adoption into lab and industrial environments. We validate the functionality of SmolVLA for a Universal
Robots UR10e using a pick-and-place task and give implementation guidelines. Our findings support that SmolVLA is a well-suited option for small-sized tasks that need to be computed on premise.
Read the full abstract ▾
All authors Nils Mandischer, Noah Böckmann, Ludwig Holl, Lars Mikelsons
Artificial Intelligence
Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning
Zixuan Wang, Yanrui Miao, Zhengxi Lu et al. (+6 more)
Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rollout, letting the policy explore from a state closer to success. Its effectiveness hinges on the guidance depth: how much of the trajectory to keep. Existing methods treat this depth as a deterministic scalar. Scheduled approaches share one value across samples and ignore per-task heterogeneity; per-sample probing estimates it separately at the cost of extra rollouts. We find that useful guidance occupies a band of depths whose informativeness profile is approximately Gaussian around the band center, rather than concentrating at a single optimal point. We propose
Agent-G$^2$, a Gaussian guidance framework that draws the depth per task from a Gaussian whose center and spread are estimated online from rollouts already collected for policy optimization, requiring no probe rollouts or learned depth predictor. The center combines a global baseline with per-cluster difficulty, and the spread tracks within-cluster variance. We evaluate
Agent-G$^2$ on ALFWorld and WebShop on Qwen2.5-1.5B / 7B-Instruct.
Agent-G$^2$ outperforms the strongest hint-based, hint-free, and Aux-RL baselines on ALFWorld by 2.3 / 3.9 / 7.4 points at under one-third the rollout cost of per-sample probing.
Read the full abstract ▾
All authors Zixuan Wang, Yanrui Miao, Zhengxi Lu, Teng Pan, Yiwen Qiu, Hongxing Li, Peng Qiu, Ruiqing Zhang, Yongliang Shen
Neural and Evolutionary Computing
Spicing up Genetic Netlist Generation with LLMs
Stefan Uhlich, Yağ{\i}z Gençer, Andrea Bonetti et al. (+4 more)
Analog
circuit topology synthesis remains challenging because useful designs occupy a tiny fraction of a combinatorial search space, and small structural changes can induce highly nonlinear changes in behavior. Evolutionary
algorithms are attractive because they can optimize over discrete
circuit topologies using only black-box evaluations, but they often require many SPICE simulations and may converge prematurely. We introduce LLM-SPICEMixer, a hybrid synthesis framework that augments genetic netlist generation with IGEL (Inspiration-Guided
Evolution with LLMs), an LLM-based proposal operator. During search, IGEL
prompts an LLM with high-performing
circuits from the elite set and instructs it to generate a new SPICE netlist, which is then evaluated by SPICE and selected using the same reward mechanism as conventional genetic operators. Thus, the LLM contributes structured
topology proposals while simulation remains the source of truth. We evaluate LLM-SPICEMixer on a challenging
benchmark task: synthesizing transistor-level
circuits that implement a discriminant function for Iris classification. Compared with the genetic framework without LLM guidance, LLM-SPICEMixer improves the median final training reward by 8.4% and the median validation-selected test reward by 8.8%. The best validation-selected
circuit achieves 93.3% test accuracy at the nominal tt corner and 85.9% average test accuracy across 17 process, voltage, and temperature corners.
Read the full abstract ▾
All authors Stefan Uhlich, Yağ{\i}z Gençer, Andrea Bonetti, Arun Venkitaraman, Chia-Yu Hsieh, Eisaku Ohbuchi, Lorenzo Servadei
Artificial Intelligence
EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models
Xuetong Li and Gaofeng Liu
Vision-
language model safety
benchmarks typically evaluate only final responses: whether a model refuses, warns, or complies. This outcome-level view cannot tell whether a model is safe for the right
multimodal reason. Safelooking behavior may reflect keyword-triggered refusal, missed visual hazards, or over-refusal of benign-sensitive inputs. We introduce EviSafe, an evidence-grounded framework for VLM safety that jointly evaluates natural user-facing behavior, explicit grounding in textual and visual evidence, and behavioral sensitivity to counterfactual changes in safety-critical evidence. EviSafeBench instantiates the framework as a controlled
benchmark with 1,181 gold image-text scenarios and 2,452 targeted counterfactual variants across eight safety domains and eight risk-source types. Each scenario includes a gold safety decision, evidence annotations, a safe-response policy, and counterfactual interventions. The three-probe protocol queries models with natural-response, evidencereporting, and counterfactual-response
prompts, then scores them using an evidence-aware judge. Across eleven evaluated VLMs, natural severity accuracy ranges from 27.6% to 52.8%, relaxed diagnostic consistency from 6.1% to 29.3%, and unsafe-to-safe counterfactual transition success from 30.4% to 58.4%. These gaps show that the evaluated VLMs are not reliably safe for the right
multimodal reason and motivate evaluation beyond refusal counts.
Read the full abstract ▾
Computation and Language
Beyond the Stability-Exploration Dilemma: Environmental Regularization for LLM Policy Optimization
Xianlei Zhou, Xiangdi Meng, Yu He et al. (+7 more)
Policy optimization (PO) for Large
Language Models faces a stability–exploration trade-off, currently mediated by an action-side Policy-KL regularizer. This puts practitioners in a double bind: keeping Policy-KL constrains response behavior and consumes the action-side exploration budget, while dropping it leaves the optimization without an explicit drift control. We argue for an alternative that breaks the dilemma by moving regularization to the input side. As training progresses, the distribution over training queries induced by the current policy drifts unchecked from its pre-RL reference distribution. Concretely, Environment-Regularized Policy Optimization (ERPO) introduces a Query-KL (QKL) term that bounds this query distribution shift, together with a
dataset-static reference-derived per-query weight that biases each per-query update toward queries typical under the reference. The QKL gradient flows strictly through the query likelihood; the response score function used by policy-gradient
estimators does not appear in the QKL term, so QKL exerts no direct gradient pressure on the response distribution—exploration is preserved. ERPO plugs into GRPO/PPO/REINFORCE-style pipelines without additional forward passes. On six mathematical
reasoning benchmarks, ERPO replaces the standard Policy-KL regularizer while achieving effective control over query distribution drift, delivering stronger accuracy and substantially more stable behavior under high-temperature decoding and long-horizon training. Our source code are available at https://github.com/AlibabaResearch/ERPO
Read the full abstract ▾
All authors Xianlei Zhou, Xiangdi Meng, Yu He, Tianyu Qi, Shuyan Guan, Xianli Zhang, Jian Zhang, Xin Li, Qika Lin, Jun Liu
Programming Languages
Hazel Prover: A Classroom Proof Assistant for Learning Structural Induction
Matthew Keenan, Nishant Kheterpal, Jean-Baptiste Jeannin et al. (+1 more)
Proof assistants offer instant feedback and incremental proof scaffolding to users. Both of these features have long held promise in improving mathematics education in classroom settings, where manual grading is costly, and students often struggle with knowing how to proceed in their proof. However, they have been difficult to deploy in classroom settings due to two main concerns: (i) students struggle with the intricacies of full-scale proof assistants; and (ii) proof assistants are ineffective in support of student learning, and knowledge transfer to on-paper assessments without the tool. We present Hazel Prover, a classroom proof assistant for teaching equational and inductive
reasoning, with a design informed by criteria encompassing ease-of-use of the tool, student engagement with underlying mathematical ideas, transfer to pen-and-paper proof, and classroom logistics. We synthesized these criteria from observations made in prior deployments of proof assistants to the classroom. We engaged in an iterative design and evaluation process, deploying Hazel Prover in two different classes and conducting in-depth analyses of fine-grained usage logs, survey data, and student exam responses. Our analysis demonstrates that students were able to learn to use the tool effectively, and that students became more capable with inductive proof as they progressed through problems. However, the first design did not effectively achieve transfer to pen-and-paper proofs. We hypothesized that this was due to the tool offering too much help to students in the equational
reasoning steps. Based on this negative result, we enforced more manual student engagement with equational steps, which led to more effective transfer in the second deployment. We believe that our analyses offer generalizable insights relevant to the designers of future classroom proof assistants for a variety of mathematical domains.
Read the full abstract ▾
All authors Matthew Keenan, Nishant Kheterpal, Jean-Baptiste Jeannin, Cyrus Omar
Cryptography and Security
FIDES: A Concordance Protocol for LLM-Generated Trading Strategies
Arther Tian, Alex Ding, Simon Wu et al. (+1 more)
An LLM asked for a trading strategy returns three artifacts at once: a natural-
language rationale, an executable implementation, and once run, a track record. Whether these are the same object is rarely checked. We present FIDES, a measurement protocol that treats them as three views to be reconciled rather than one deliverable to be graded. Through dual delivery, a single model call returns both a natural-
language strategy with an explicit claimed edge and a self-contained strategy(df) function. FIDES executes the code in a sandbox against a lag-one out-of-sample backtest and scores three concordance gaps: say to do, do to real, and say to result. On 8
liquid US ETFs across four models plus a two-stage elicitation arm, 40 strategies, 2023 to 2024 out-of-sample, three findings stand out. First, concordance does not predict profit: only 2 of 40 strategies beat buy-and-hold, and a plain sma(50,200) rule outperforms every model's mean Sharpe. Second, self-assessment is badly calibrated: 32 of 40 strategies claim to beat buy-and-hold and exactly one does. Third, swapping the
language-code judge for a second model flips say to do on more than half of items. Injecting Close.shift(-1) drops do to real by 0.33 on average, while our runtime future-information probe fired on neither clean nor injected code. We frame FIDES as a protocol for measurement fidelity, not a claim about
market performance.
Read the full abstract ▾
All authors Arther Tian, Alex Ding, Simon Wu, Aaron Chan
Databases
Teach Your DBMS to LIKE Strings: Fast and General Pattern Matching for Wildcard Joins and Filters
Lam-Duy Nguyen, Pascal Ginter, Duc-Tam Nguyen et al. (+2 more)
Nowadays, modern applications do more than just store text – they need to derive meaningful insights from it. To do that, they usually rely on wildcard queries with LIKE predicate to extract patterns. However, modern database management systems (DBMSs) handle these wildcard operations poorly, resorting to nested loops for joins and expensive interpreted evaluation for filters. To address the former, we propose a new join
algorithm based on the Aho-Corasick
algorithm, which significantly reduces the time complexity. For wildcard filtering, we leverage the code-generation infrastructure to improve performance: we generate specialized code for the LIKE predicate, eliminating the overhead of interpreting the pattern per tuple. Our experimental results show that the new wildcard join
algorithm significantly outperforms both baseline DuckDB and Umbra, achieving speedups of up to 30.6x and 114.75x, respectively. The new wildcard filter approach likewise outperforms both baselines, achieving a speedup of 13.3x in a filter-focused stress
benchmark. We believe these two techniques will play key roles for high-performance text analytics in modern query engines.
Read the full abstract ▾
All authors Lam-Duy Nguyen, Pascal Ginter, Duc-Tam Nguyen, Thomas Neumann, Viktor Leis
Robotics
Design of a Biomimetic Joint-Covering Skin with Tissue-Like Structure to Enhance Proprioception in a Musculoskeletal Humanoid
Akihiro Miki, Shun Hasegawa, Yoshimoto Ribayashi et al. (+2 more)
Proprioception in musculoskeletal
humanoids is typically estimated primarily from muscle sensing, while the role of cutaneous deformation around joints remains insufficiently explored. In biological systems, mechanoreceptors distributed within soft tissue complement muscle feedback and support reliable joint state estimation. This study presents the design of a biomimetic joint-covering skin with a tissue-like layered structure that integrates pressure- and stretch-sensitive elements within the joint-covering tissue. The proposed skin is implemented on the musculoskeletal
humanoid Musashi-W, and its independent proprioceptive capability as well as its integration with muscle sensing are evaluated. Experimental results show that the proposed skin alone achieves joint angle estimation with an average error of approximately 3 degrees. Furthermore, integration with muscle sensing improves estimation accuracy. Owing to its joint-covering structure, the skin may mechanically mitigate the influence of external disturbances on the muscles, and the integration of multiple modalities suggests the possibility of contributing to the identification of external stimuli that are difficult to interpret using muscle sensing alone. This work presents a design methodology for biomimetic joint-covering skin and demonstrates that such tissue-structured skin can serve as an effective approach for extending proprioceptive systems in musculoskeletal
humanoids.
Read the full abstract ▾
All authors Akihiro Miki, Shun Hasegawa, Yoshimoto Ribayashi, Kento Kawaharazuka, Kei Okada