Digital Libraries
VietProfs: A Public Directory of the Vietnamese Academic and Research Diaspora
ThanhVu Nguyen
The Vietnamese academic diaspora spans hundreds of universities and research institutes worldwide, yet there has never been a shared, searchable directory for this community. Prospective graduate students looking for advisors who share their background, researchers seeking collaborators, and organizers looking for speakers have had to rely on manual, one-off web searches. To address this need, we built VietProfs (https://vietprofs.roars.dev), an open, searchable directory of Vietnamese and Vietnamese-diaspora faculty and permanent research scientists outside Vietnam. Each profile pairs a portrait and authoritative diacritic name with verified appointment, degree, and honors data, browsable through a fast client-side web interface. This paper covers two topics: the design of the directory itself and the engineering required to keep it current. Part I describes the directory: its goals, eligibility and appointment track rules,
alignment with standard U.S. federal classifications (NCES, NSF, and NIH), profile card design, and current roster insights. Part II reports on automated directory maintenance. Keeping over a thousand records accurate against a constantly shifting web is notoriously difficult. We describe an LLM-assisted maintenance system combining automated search and periodic revalidation with deterministic validation gates, operating under the principle: AI proposes, evidence decides. As of September 2026, the directory includes 1,152 verified records across 492 institutions in 23 countries, covering doctoral cohorts from 1939 to 2026. Aggregate statistics are computed dynamically at runtime, and all changes are audited through public Git history. VietProfs provides a practical community resource while offering a concrete case study in building reliable,
agent-maintained public
datasets.
Read the full abstract ▾
Networking
SESO-ISAC: Service-Aware End-to-End Sensing Orchestration for 6G ISAC
Youbin Jeon, Laeyoung Kim, Myungjune Youn et al. (+1 more)
Unlike conventional communication services, 6G Integrated Sensing and Communication (
ISAC) services require complete end-to-end sensing operations, from data collection to processing, result generation, and exposure. In this article, we propose SESO-
ISAC, a service-aware end-to-end sensing orchestration framework that maps a sensing service request to a complete sensing configuration under the sensing execution context. Rather than treating sensing configuration decisions independently, SESO-
ISAC captures their interdependence across the end-to-end sensing operation, evaluates candidate configurations according to the applicable QoS requirements, and re- evaluates the selected configuration as the sensing execution context changes. Through two representative case studies, we show that the preferred sensing configuration depends on the overall performance across the applicable QoS dimensions and can change during operation.
Read the full abstract ▾
All authors Youbin Jeon, Laeyoung Kim, Myungjune Youn, Sangheon Pack
Distributed Computing
Poseidon: DAG-Guided Parallelism Search for LLM Pre-Training on Heterogeneous Clusters
Xiaosong Chen, Shaoheng Nie, Zhongmin Zhao et al. (+6 more)
With the rapid advancement of accelerator technologies, pre-training large
language models (LLMs) on heterogeneous accelerator clusters has become increasingly crucial for maximizing hardware utilization. Existing systems, however, suffer from inaccurate training time modeling, which undermines the parallelization optimizations built upon it. Moreover, for current approaches, the vast configuration search space makes exhaustive exploration infeasible, forcing a trade-off between search time and training efficiency. To overcome these limitations, we introduce Poseidon, an efficient and scalable LLM training framework designed with heterogeneity awareness. Its core is an explicit training time model based on a directed acyclic graph. Building on this graph, Poseidon employs two efficient, theoretically grounded strategies: stage-level
pruning via early stopping with partial estimation, and layer-to-stage mapping exploiting a ridge-like distribution pattern. These strategies reduce the search space without sacrificing optimal training efficiency. Experiments on heterogeneous clusters show that Poseidon improves training throughput by up to $2.76\times$ over state-of-the-art systems.
Read the full abstract ▾
All authors Xiaosong Chen, Shaoheng Nie, Zhongmin Zhao, Zizhao Mo, Jiapeng Chen, Huanle Xu, Zeren Li, Weiwei Sun, ChengZhong Xu
Artificial Intelligence · Cross-listed from q-fin.TR
Explainable Deep Learning for Price-Trade Dynamics: From Black-Box Forecasts to Effective Parametric Models
Manuel Naviglio and Fabrizio Lillo
Understanding the joint dynamics of prices and trades is central to
market microstructure, where returns and order flow interact through nonlinear and state-dependent mechanisms. Linear models are interpretable but may miss these effects, while deep neural networks improve
forecasting at the cost of transparency. We use neural networks as tools for structural discovery rather than only for prediction. A deep feed-forward network is trained on high-frequency returns and signed volumes for large- and small-tick stocks and compared with a linear VAR
benchmark. The neural network improves predictive performance, especially for returns, revealing nonlinear dependencies beyond the linear specification. Using Shapley-based explainability, we show that the dominant contributions are concentrated at the most recent lags. Model-implied responses are consistent with conditional averages reconstructed from the data. Unlike empirical averages, however, the neural-network decomposition isolates individual regressor contributions to the aggregate dependence. Lagged signed volume generates sign-preserving and saturating effects, consistent with nonlinear price impact and order-flow persistence. Lagged returns act as state variables: when the previous trade does not move the price, the model predicts continuation in the direction of past order flow, whereas non-zero returns generate attenuation or reversal. Building on these findings, we introduce a parsimonious SHAP-inspired nonlinear parametric model. It reproduces the main return-volume dependencies, outperforms the linear VAR
benchmark, and achieves performance comparable to the neural network. A multi-lag extension captures residual longer-
memory effects while preserving interpretability. Overall, explainability offers a route from black-box prediction to economically meaningful parametric models of price and trade dynamics.
Read the full abstract ▾
Machine Learning
Learning to Price and Stock Under Contextual and Censored Demand
Zean Han, Zezhen Ding and Jiheng Zhang
To make optimal joint pricing and inventory control decisions is a critical challenge for modern retailers. In practice, retailers face changing
market conditions where demands are influenced by various contextual factors, while simultaneously dealing with the difficulty of lost sales that obscure true demand information. However, existing approaches often fail to account for both contextual information and censored demand observations. We address this gap by presenting a framework where we model demand as a linear combination of basis functions with unknown coefficients, allowing for adaptive pricing and inventory decisions that respond to changing contexts. We propose an efficient
algorithm to achieve regret bound $\mathcal{O}(K\sqrt{T}\log T)$ under concave revenue conditions and $\mathcal{O}(K^{2/3}T^{2/3}(\log T)^{1/2})$ for the general case, with matching lower bounds confirming optimality. Extensive numerical experiments across diverse scenarios demonstrate our
algorithm's effectiveness.
Read the full abstract ▾
Numerical Analysis
Polytopic symmetric interior-penalty approximation of elliptic SPDEs driven by spatial white noise
Tristan Pryer
We analyse symmetric interior-penalty discontinuous Galerkin approximations of
elliptic stochastic partial differential equations driven by spatial Gaussian white noise on quasi-uniform polytopic meshes. The low regularity of the exact random field precludes the usual SIP consistency argument. We instead restrict the same continuum white-noise functional canonically to the discontinuous
polynomial space and separate the error into
stochastic forcing-restriction and deterministic discretisation components. For every fixed
polynomial degree $k\geq1$, we prove the sharp two-sided estimate \[ \|Y-Y_h\|_{L^2(\Xi;L^2(\Omega))} \simeq h^{2-d/2}, \] giving rates $h$ in two dimensions and $h^{1/2}$ in three dimensions. A finite-dimensional lower bound establishes optimality. The analysis allows polytopic elements with arbitrarily many and arbitrarily small faces, including admissible non-convex elements. In two dimensions we also treat polygons with a single reentrant corner. Although the deterministic approximation exhibits an angle-dependent loss of regularity, the singular resolvent contribution is finite rank, and the sharp first-order
stochastic rate is retained. The discontinuous structure yields an exact element-local sampler for the restricted white noise. Numerical experiments on irregular polygonal, non-convex polytopic and reentrant domains support the predicted convergence behaviour.
Read the full abstract ▾
Machine Learning
PhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us
Gal Sapir, Alon Diament, Adva Wolf et al. (+7 more)
Deeply phenotyped cohorts combine clinical, imaging, molecular, and wearable observations across timescales from seconds to years, but heterogeneous analyses are not directly comparable. We present PhenoBench, an executable
benchmark that turns deep-phenotyping measurements into explicit questions and controlled comparisons of information sources and predictive models. It is built around the Human Phenotype Project, with more than 13,000 participants at the initial visit. Each question fixes the target, population, timing, and allowed information; its evaluation contract specifies the split, metric, baseline, and claim boundary. PhenoBench defines 90 clinically grounded tasks across 15 domains and 26 input modalities. Across 160 matched regression comparisons spanning 52 tasks, six pretrained tabular models ranked above the evaluated task-specific baselines, including XGBoost and CatBoost, under a fixed single-
estimator protocol with bounded tuning. Giving each task equal weight, their mean advantage over ridge was 0.0103 $R^2$ (95% task-bootstrap interval, 0.0071-0.0136). We also evaluated 14
language models, collectively covering 40 tasks spanning phenotype recovery, classification, follow-up
forecasting, and participant ordering. Without cohort-specific fitting,
language models made informative predictions on some tasks but showed task-specific capability gaps, shared failures of scale, and rarely surpassed task-specific ridge or logistic regression models fitted on the same input fields. PhenoBench provides a versioned, auditable evaluation system where new questions, measurements, and models can be added without redefining existing comparisons.
Read the full abstract ▾
All authors Gal Sapir, Alon Diament, Adva Wolf, Doron Yaya-Stupp, Dikla Gelbard Solodkin, Dana Azouri, Anat Etzion-Fuchs, Guy Lutsker, Eran Segal, Hagai Rossman
Artificial Intelligence
LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies
Zheng Lu, Haoran Liao, Wanqi Zhong et al. (+9 more)
Vision-
Language-Action (VLA) policies leverage pretrained
vision-
language models (VLMs) to guide action generation for
robot control. VLMs provide hierarchical visual-semantic representations that evolve across layers, from local visual geometry to abstract,
language-aligned semantics; different manipulation tasks may therefore require different mixtures of layer representations. Meanwhile, the action module maintains intermediate representations that evolve throughout action computation and may provide useful information for subsequent decisions. However, existing VLA interfaces offer limited flexibility in representation access: VLM information is exposed through fixed layer assignments for each action layer, while intermediate action states are only propagated implicitly through residual streams without explicit reuse. We introduce LayerRoute, an action-conditioned representation routing interface that enables adaptive access to VLM layers and action representations. The Layer Mixture Router dynamically forms mixtures of cached VLM representations, while Action-State Reread reuses earlier action representations. Across diverse simulation and real-world
benchmarks, LayerRoute consistently improves StarVLA-$\pi$ and $\pi_{0.5}$, achieving up to 7.2 gains on LIBERO Long with only 0.31% / 3.87% additional parameters. Ablation studies validate the benefit of action-conditioned layer routing, while routing analyses reveal structured allocation patterns across action layers and task settings.
Read the full abstract ▾
All authors Zheng Lu, Haoran Liao, Wanqi Zhong, Yunhe Ni, Lijie Wang, Xingjie Fan, Zhisheng Chen, Yantang Qu, Meijia Chen, Tianyu Xin, Zirui Song, Yiming Li
Computer Vision
Report of the 8th LSVOS Challenge: Complex and Multimodal Video Object Segmentation
Chang Liu, Henghui Ding, Lingyi Hong et al. (+36 more)
This report summarizes the 8th Large-scale
Video Object
Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates
video segmentation in three complementary settings: complex semi-supervised
video object
segmentation on MOSEv2, text-guided referring
video object
segmentation on MeViSv2-Text, and audio-guided referring
video object
segmentation on MeViSv2-Audio. We describe the tasks and evaluation protocols and review the methods of the top three teams in each track. Across the nine leading solutions, foundation
segmentation models are combined with target-aware
memory,
multimodal reasoning, explicit target-existence verification, agentic interaction, and corrective tracking. These systems illustrate a broader transition from single-model mask propagation toward modular pipelines that reason about object identity, query validity, and temporal reliability.
Read the full abstract ▾
All authors Chang Liu, Henghui Ding, Lingyi Hong, Ning Xu, Linjie Yang, Yuchen Fan, Canyang Wu, Jinrong Zhang, Xusheng He, Ce Bian, Xianjing Han, Jianlong Wu, Mingqi Gao, Sijie Li, Jungong Han, JeongRae Kim, Chaehyun Kim, Changwon Lim, Jungyoon Lee, Gyuil Lim, Doeon Kim, Seong-heum Kim, Pranjal Aggarwal, Sean Welleck, Yiwen Ren, Jianing Liu, Yingxin Wang, Kexin Zhang, Licheng Jiao, Lingling Li, Xu Liu, Jinxing Zhou, Suiyi Zhao, Yanghao Zhou, Ruohao Guo, Liangtao Shi, Jinxia Xie, Xiantao Hu, Ting Liu
Machine Learning
Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment
Sieun Hyeon and Jaeyoung Do
Retraining-free MoE compression reduces deployment
memory by
pruning or merging experts, but often treats the compressed checkpoint as the final artifact. We argue that this view is incomplete: compressed MoE checkpoints are better understood as compressed initializations that benefit from a tiny post-compression adjustment stage. Across two MoE LLM backbones, four
pruning/merging methods, three expert-retention ratios, and 28
benchmarks, we compare LM fine-tuning and teacher-based KD under matched small-data budgets and measured GPU costs. Using only 3,000 C4 examples and a single epoch of adjustment, Full FT recovers 37.3% of the original-to-compressed performance gap on average. Moreover, LM fine-tuning is more cost-effective than standard
token-level KD, and full-parameter adjustment gives the strongest cost–recovery trade-off among the tested scopes. These results suggest that retraining-free compression should be paired with small post-compression adjustment to recover a substantial portion of the performance lost during compression.
Read the full abstract ▾
Computer Vision
NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometry
Yicheng Lin, Zhipeng Fei, Yuxiu Xu et al. (+3 more)
Sparse optical flow provides stable inter-frame correspondence, playing a key role in Visual Odometry (VO) and Visual-Inertial Odometry (VIO). Classical optimization-based methods, such as Lucas-Kanade (LK), perform well under small displacements but are sensitive to large motions and illumination changes. Modern regression-based learning methods, while more robust in complex scenes, are often computationally heavy and lack explicit
geometric consistency, making them less suitable for efficient VO/VIO front-ends. To bridge this gap, we propose a hybrid neuro-symbolic framework that combines the strengths of both paradigms. Our method uses a Convolutional Neural Network (CNN) to extract robust feature representations, which is fed into a differentiable LK optimizer to estimate optical flow in an end-to-end trainable manner. Through implicit differentiation, gradients are propagated across the iterative solver, enabling joint optimization of feature extraction and flow estimation. The resulting system integrates seamlessly into existing VO/VIO pipelines and runs in real-time on embedded platforms. Experiments show that our method outperforms conventional optimization-based flow in challenging conditions such as dynamic lighting and low texture, while also achieving higher accuracy and lower latency than purely regression-based alternatives. When deployed in a VIO system, our method demonstrates significant performance improvement, achieving an average error reduction of 42% on challenging
datasets while enhancing tracking stability. The code is publicly available.
Read the full abstract ▾
All authors Yicheng Lin, Zhipeng Fei, Yuxiu Xu, WenDong Chen, Cong Li, Bin Han
Machine Learning
FedSubMuon: Communication-Efficient Federated LLM Fine-Tuning via Structured Subspace Muon
Shaolong Chen, Youming Tao, Shuzhen Chen et al. (+3 more)
Federated fine-tuning adapts large
language models (LLMs) to decentralized client data, but its scalability in cross-device training is often limited by the high communication cost.
Muon is an optimizer that improves optimization performance by orthogonalizing momentum for
matrix-valued parameters. Existing
federated Muon methods demonstrate the benefit of
matrix-aware optimization in
federated learning, but still require transmitting full layer-size updates and optimizer state. A natural way to reduce communication is to directly apply
Muon to LoRA factors, but this changes the optimized object and weakens
Muon's
matrix-aware update geometry. We propose FedSubMuon, a communication-efficient
federated Muon fine-tuning method that optimizes compact coefficient
matrices within shared structured subspaces. This design keeps
Muon on a single
matrix-valued trainable object, while reducing the client upload to compact coefficient
matrices. We further introduce FedSubMuon-GT, an accuracy-oriented extension that uses projected gradients to adapt tracked subspace bases toward task-relevant gradient directions. Experiments on instruction tuning and mathematical
reasoning show that FedSubMuon-GT achieves the best overall accuracy on four of five
dataset-model pairs, while FedSubMuon performs best under all matched communication budgets. On Dolly-15K, the closest communication baseline requires 5.5 times and 1.4 times more total communication on Llama-1B and Qwen-4B, respectively.
Read the full abstract ▾
All authors Shaolong Chen, Youming Tao, Shuzhen Chen, Falko Dressler, Qingqing Ye, Di Wang
Machine Learning
ACE: Adapter Consolidation across Experts for Parameter-Efficient Fine-Tuning of MoE LLMs
Ahin Lee, Sehyun Yun, Joonha Park et al. (+1 more)
Parameter-efficient fine-tuning (PEFT) of mixture-of-experts (MoE) models commonly attaches a separate low-rank adapter to each expert. This expert-wise design fragments adaptation in three ways: capacity is split across narrow low-rank updates, gradient supervision becomes sparse and imbalanced under sparse routing, and execution is decomposed into many small GEMMs. We find that such expert-wise separation is often unnecessary, as subsets of LoRA adapters become functionally similar during fine-tuning, revealing redundancy among expert-specific adapters. Based on this redundancy, we propose ACE (Adapter Consolidation across Experts), which groups redundant experts and replaces their expert-specific adapters with group-shared higher-rank LoRA modules under the same PEFT budget. ACE further introduces grouped adapter execution, which consolidates fragmented expert-wise adapter computations into fewer, larger group-level GEMMs. Across evaluations covering 12
datasets and four MoE backbones, ACE achieves the highest observed mean accuracy among the parameter-matched PEFT methods on the three backbones with complete baseline coverage, while providing $1.31\times$ to $1.48\times$ wall-clock training speedup over expert-wise LoRA without increasing peak
memory. Our code is available at https://github.com/UbiquitousAILab/ACE.
Read the full abstract ▾
All authors Ahin Lee, Sehyun Yun, Joonha Park, Taesik Gong
Artificial Intelligence
Generating Instance Generators in PDDL Planning
Nicola J. Müller, Naya Rudolph, Katharina Stein et al. (+3 more)
PDDL, the de-facto standard
language in the AI Planning community, is designed to specify planning domains: sets of instances that share the same predicates and action schemas. Yet it does not provide any means to specify the actual instance set, i.e., legality constraints on initial states and goal conditions, as well as possibly domain subset constraints specifying an instance subset we are interested in. One consequence of this is that instance generation has always been ad-hoc, with manually written domain- and subset-specific instance generators. Recent work has started to address this, through
reasoning and learning methods that however suffer from scalability limitations. Here we introduce an alternative approach, leveraging LLMs to generate instance-generation programs, with built-in soundness guarantees through prescribed checks. We show that these automatically generated instance generators return large numbers of sound and diverse instances efficiently.
Read the full abstract ▾
All authors Nicola J. Müller, Naya Rudolph, Katharina Stein, Jörg Hoffmann, Ayal Taitler, Timo P. Gros
Computation and Language
DPH Parser: A Bottom-Up Grammar-Driven Parser for Joint Constituency and Dependency Analysis
Hussein Ghaly
This paper presents Dependency-Phrase Hierarchy Parser (DPH Parser), a grammar-driven bottom-up unsupervized parsing framework inspired by Generalized Phrase Structure Grammar (GPSG) and Head-driven Phrase Structure Grammar (HPSG). The parser incrementally constructs constituency structures using a compact inventory of feature-based syntactic rules while deriving dependency relations through explicit head annotations. The system combines probabilistic POS tagging, recursive phrase projection, and weighted parse hypotheses to process realistic and partially noisy text input. Unlike purely neural and data-driven parsers, the resulting syntactic derivations remain explicitly interpretable. We evaluated parser performance on English corpora from the Universal Dependencies (UD) project using Unlabeled Attachment Score (UAS) as the main parsing metric, comparing the outcomes against Stanza and spaCy parsers. For a small inventory of syntactic rules, DPH parser achieved UAS values of 53.32% & 52.58% (UD Devset/Testset respectively). For the same data, Stanza achieved 89.12% & 88.67% while spaCy achieved 56.91% and 58.59%. Although the current system does not yet approach the accuracy of modern neural parsers, the results demonstrate the feasibility of applying transparent rule-based bottom-up parsing to realistic treebank data while jointly producing constituency and dependency structures.
Read the full abstract ▾
Computation and Language
Don't Lose Entities from Retrieval to Generation: Dual Entity Recovery RAG for multi-hop QA
Heechang Lee and Dong-Young Lim
Retrieval-augmented multi-hop question answering (QA) decomposes a query into sub-questions and decomposes the corpus into smaller
retrieval units such as sentences. Both forms of decomposition improve the pipeline, but we show that both share the same vulnerability, the loss of entity information, and that this loss breaks the pipeline at two separate points. The first point is
retrieval, where a sub-question loses the entity resolved at the previous hop, leaving the retriever with nothing to match against. The second point is harder to see, because
retrieval still appears to succeed. Once a passage is split into sentences, an isolated sentence loses the context that grounds its pronouns, so even with the correct sentence in hand the LLM cannot tell which entity the sentence is about. We isolate this second point as a distinct failure mode that we call lost-in-generation, and a
retrieval-controlled experiment shows that it degrades answers even when the gold evidence is fixed in the context. We then propose Dual Entity Recovery RAG (DER-RAG), which keeps the grounding entity explicit from
retrieval through to generation with two lightweight components, a two-way query decomposition that carries the resolved entity across sub-questions and a subject entity prefix attached to each sentence at generation time. DER-RAG needs no graph construction, no corpus modification, and no fine-tuning, yet on three multi-hop QA
benchmarks it matches or exceeds strong baselines, including graph-based methods that depend on costly offline structures.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from math.OC
The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimization
Tianxi Zhu, Yi Xu and Xiangyang Ji
Stochastic min-max optimization has attracted increasing
attention due to its applications in modern machine learning, while existing theoretical studies mainly rely on the bounded variance assumption for
stochastic gradients. Under heavy-tailed noise, where
stochastic gradients only possess a finite $p$-th moment for $p\in(1,2]$, gradient clipping or normalization is commonly believed to be necessary to guarantee convergence. In this work, we revisit
stochastic min-max optimization under heavy-tailed noise and provide a comprehensive theoretical study of
stochastic gradient descent ascent (SGDA). We first show that vanilla SGDA, without any modification to its update rule, can converge under heavy-tailed noise in both nonconvex-strongly-concave (NC-SC) and nonconvex-concave (NC-C) settings, establishing the first convergence guarantees for SGDA in these regimes. Beyond unregularized problems, we further investigate regularized
stochastic min-max optimization, where directly incorporating gradient normalization into proximal updates is nontrivial due to the incompatibility between normalization and proximal structures. We overcome this difficulty by developing new clipping-free
algorithms, i.e., Stoc-TRGDAM and Stoc-TRGDmax, and they both can achieve the optimal dependence on the target accuracy without using gradient clipping.
Read the full abstract ▾
Artificial Intelligence
Explaining AI Agents Through Execution Traces
Vittoria Vineis, Fabiano Veglianti, Lorenzo Antonelli et al. (+3 more)
AI
Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human oversight. This creates a pressing need for reliable and auditable explanations of what an
agent did and why. However, traditional Explainable AI (XAI) methods fall short of providing the process-level transparency required for such interactive, multi-step systems, motivating a paradigm shift toward approaches specifically designed for AI
Agents. To address this gap, we present a post-hoc XAI framework that transforms a lengthy
agent's execution trace into a structured report and a faithful natural-
language explanation explicitly grounded in its observable behavior. Because it relies solely on execution traces, the framework applies across different
agent architectures, environments, and tasks. Human and automated evaluations across multiple
benchmarks and architectures show that our framework produces high-quality, trace-faithful explanations while reliably identifying unsupported claims, unjustified actions, and evidence gaps, outperforming naive LLM-generated explanations.
Read the full abstract ▾
All authors Vittoria Vineis, Fabiano Veglianti, Lorenzo Antonelli, Claudia Di Carlo, Matteo Silvestri, Gabriele Tolomei
Robotics
SCoCaT: Success Conditioned Constrained Reinforcement Learning for Spacecraft Docking
Aman Arora, Ricard Marsal I Castan, Matteo El-Hariry et al. (+1 more)
Termination-based constrained reinforcement learning is attractive for safety-critical robotic deployments: it avoids online optimization at inference, scales easily to many constraints via a single scalar per constraint, and is simpler to implement than commonly used Lagrangian methods. Instead of pricing violations through summed cost penalties, this approach makes violations structurally unprofitable by shortening the effective horizon for each violation. We identify a structural failure mode of this method class on terminal-
navigation tasks: reaching a precise goal configuration while satisfying safety constraints that tighten along the final approach. When the goal sits inside the region close to where the constraints become active, the survival-weighted objective makes dwelling outside the goal region strictly preferable to entering, producing high constraint compliance with low task completion. We formalize this pathology and show that a minimal augmentation to off-the-shelf RL
algorithms like PPO resolves this “feasibility collapse”. We empirically demonstrate that adding a dense per-step success signal via an auxiliary value critic improves the task completion rate while maintaining safety-critical constraint compliance. Validation across two representative spacecraft platforms: a 6U-CubeSat spanning the mass and degree-of-freedom envelope of operational proximity operations, and a floating platform testbed for zero-shot sim-to-real transfer in our laboratory, supports the generality of these findings.
Read the full abstract ▾
All authors Aman Arora, Ricard Marsal I Castan, Matteo El-Hariry, Miguel Olivares-Mendez
Machine Learning
Calendar-Structured Sparse Principal Component Analysis for Interpretable Multi-Periodic Electricity Consumption Profiles
Carlos Quesada-Granja, Tony Castillo-Calzadilla and Carlos Rizo-Maestre
Long-term electricity-consumption profiles exhibit several simultaneous periodic structures, including daily, weekly, and annual cycles. This work introduces Calendar-Structured Sparse Principal Component Analysis (Calendar-SPCA), a structured representation-learning method that incorporates this known multi-periodic geometry directly into a low-dimensional factorization. The method represents the feature domain as the Cartesian product of cyclic calendar axes and combines an L1 loading penalty with graph total variation, producing sparse, locally coherent, and directly interpretable latent factors. In this study, Calendar-SPCA is applied to the interpretable analysis of long-term electricity-consumption profiles and evaluated on two independent public smart-meter
datasets, GoiEner and Low Carbon London, with different population sizes and temporal resolutions. A factorial experiment characterizes the effects of sparsity and calendar coherence and examines robustness across sample size, latent dimensionality, and repeated fits. At rank 15, Calendar-SPCA retains 96.92% and 82.90% of the explained variance of rank-matched principal component analysis (PCA) in GoiEner and Low Carbon London, respectively, with mean loading sparsities of 61.95% and 81.50%. Comparisons with classical sparse PCA and sparse PCA with total variation (SPCA-TV) show that Calendar-SPCA organizes latent factors into interpretable structures over the daily, weekly, and annual calendar axes while preserving substantial low-rank information.
Read the full abstract ▾
Artificial Intelligence
OmniStepBench: Deployment-Aware Agent Evaluation across Modalities and Task Complexity
Yu Liu, Zhilin Liu, Zhiwei Yang et al. (+7 more)
As large
language models evolve from question-answering systems into general-purpose
agents, evaluation must move beyond static answer correctness to assess
multimodal perception, multi-step execution, tool use, and artifact delivery. However, existing
benchmarks are often tied to specific task types, execution environments, or scoring protocols, limiting their comparability, interpretability, and reliability for deployment decisions. We introduce OmniStepBench, a
benchmark for deployment-aware
agent evaluation across modalities and task complexity. Built on a shared OpenClaw execution environment, OmniStepBench organizes 233 tasks selected and adapted from 22 source
benchmarks into a $2\times3$ workload
matrix defined by input modality and execution form, and evaluates them under a unified contract-based protocol with evidence-based score
auditing. We evaluate 30 commercial API models and 12 locally deployed open-weight models (42 models in total) over 9{,}218 applicable model–task runs, reporting accuracy and
token consumption alongside reference costs for API models. Results show workload-dependent rankings, distinct accuracy–cost trade-offs between text and
multimodal tasks, and competitive but weaker overall performance from local models. These findings support deployment decisions based on workload profiles, deployment mode, and accuracy–cost trade-offs rather than a single aggregate score.
Read the full abstract ▾
All authors Yu Liu, Zhilin Liu, Zhiwei Yang, Shaojie Zhang, Zheyuan Deng, Tingwei Huang, Zhenbo Luo, Lei Jiang, Yanbing Liu, Pei Fu
Computer Vision
GradeTrap: Authority Cues in Images Shift VLM Judgments Despite Explicit Instructions to Ignore Them
Deep Dessai
As
vision-
language models (VLMs) become increasingly capable and are deployed in consequential real-world settings, they must evaluate evidence independently rather than defer uncritically to human authority. We introduce GradeTrap, a controlled evaluation that places two social cues in direct conflict: a student answer, which should attract sycophantic agreement, and a conflicting answer attributed to a peer, teacher, or official answer key, which should attract authority-based deference. Models produce free-form answers while being explicitly instructed to solve independently and ignore all student answers, feedback, and grading marks. We test the models on 60 synthetic real-world trade-off scenarios. Five neutral trials establish a stable model-relative preference, followed by three repetitions of six experimental cues including controls. On the 45-item common intersection across Gemini 3.5 Flash-Lite, GPT-5.6 Luna, and Claude Haiku 4.5, a generic second-answer control yields 5.4% conflicting-answer selection. Relative to that control, pooled within-item changes show no reliable peer-review effect, a 6.9-point teacher-review effect, and a 19.5-point official-key effect. In contrast, a displayed conflicting student answer alone compared to a displayed student reference answer alone only raises selection from 2.2% to 5.2%. Official-key provenance therefore redirects judgements more than a student answer or the generic second-answer control, despite an explicit ignore instruction and an opposing student answer given along with the official key. Effects vary in magnitude across the three models.
Read the full abstract ▾
Numerical Analysis
Crouzeix–Raviart–Marini realisation of computable a priori $L^2$-error bounds on anisotropic meshes
Hiroki Ishizaka
We consider conforming $\Pone$ and lowest-order Crouzeix–Raviart (CR) approximations of the Dirichlet Poisson problem in two and three dimensions. We obtain computable a priori $L^2$-error bounds on anisotropic simplicial meshes without a global $H^2$-regularity assumption. For piecewise constant data, the Marini relation gives an equilibrated lowest-order Raviart–Thomas (RT) flux from the scalar CR solution. The square of the resulting Marini constant is the largest generalised
eigenvalue of a problem involving only scalar conforming and CR
matrices. Combined with the elementwise Poincaré constant, it controls both the conforming and CR errors. The CR $L^2$ estimate uses positivity of the discrete CR–conforming gap operator rather than a nonconforming Aubin–Nitsche argument. We also derive an exact decomposition of the Marini defect into the CR–conforming energy gap and an explicit
geometric term with no aspect-ratio factor. On the algebraically graded L-shaped mesh family considered here, $q>3/2$ yields $\kappa_{M,h}=O(h)$ and computable $O(h^2)$ $L^2$-operator bounds.
Read the full abstract ▾
Computer Vision
DriveZero: End-to-End Driving Beyond Human Demonstrations
Hao He, Chengcheng Hu, Zirun Su et al. (+17 more)
Most end-to-end autonomous-driving systems learn by imitating human driving logs, leaving their learned behavior constrained by the quality and behavioral coverage of the recorded trajectories. This report presents DriveZero, an end-to-end system that learns driving behavior beyond human demonstrations. It decomposes driving into a perception model and an action model, pretrains each in the regime best suited to it, and combines them into one end-to-end planner. The two models call for different learning recipes: perception must understand the world, and benefits from massive and diverse visual data; action must interact with it, and requires closed-loop feedback. On the action side, we introduce DriveRL, a mixed-
agent closed-loop reinforcement-learning framework. It converts real driving logs into interactive worlds, where a privileged teacher policy is trained with PPO through closed-loop rollouts. For the perception model, DriveVFM consolidates multiple frozen
vision foundation models, including DINOv3, SigLIP2, SAM and Depth Anything V2, into a single backbone from raw images alone, requiring no task-specific annotations. DriveZero then unifies the two: a camera-only planner that distills the frozen DriveRL teacher through its rolled-out trajectories. The goal-conditioned teacher can moreover be queried under augmented driving intents, yielding diverse, goal-consistent supervision that logged data cannot provide. On nuPlan, DriveRL with value-guided test-time action search achieves a mean score of 93.57 across the Val14, Test14-hard, and Test14-random community splits in both non-reactive and reactive modes, exceeding the Log-Replay expert on all three splits. DriveZero achieves state-of-the-art performance on NAVSIMv1, NAVSIMv2 and the closed-loop HUGSIM
benchmark without any human trajectory supervision.
Read the full abstract ▾
All authors Hao He, Chengcheng Hu, Zirun Su, Heng Zhang, Haisong Liu, Jinke Li, Haochen Tian, Zhenwei Shen, Hongyang Li, Zhichao Li, Yunchen Yang, Bochao Huang, Siyu Zhang, Kuangye Chen, Xiongjie Zhang, Wentao Dai, Hengchen Dai, Siyuan Liu, Zehao Huang, Naiyan Wang
Machine Learning
Data Quality Rule Generation with LLMs
Anna-Christina Glock, Thomas Hütter, Johannes Fürnkranz et al. (+3 more)
The validation of data, such as customer and employee data, is an important task in many organizations. Errors in data can have severe consequences. For example, a wrong drug unit in a patient record can lead to life-threatening medication errors, and a missing street number in an address to failed deliveries. Companies often employ rule-based enterprise data quality (DQ) tools, which allow domain experts to specify rules to validate the data over time. While rule-based DQ tools are computationally efficient and provide explainable reports, maintaining a comprehensive rule set manually is challenging, as domain experts often overlook essential rules, especially in complex domains and large data volumes. Hence, closing these gaps remains an open problem in practice. In this paper, we address the challenge of automated DQ rule generation. For this, we formalize a generalizable generate-filter framework and introduce LeDQeR, an LLM-based DQ rule generation approach. First, a large
language model (LLM) generates candidates rules from an observed dirty data tuple for a given rule-based DQ tool syntax. Second, we apply four filter techniques that ensure the (i) executability, (ii) correctness, and (iii) generalizability, and avoid (iv) redundancy of the generated rules. An extensive experimental evaluation suggests that LeDQeR is able to produce effective and compact rule sets for various
datasets and error types.
Read the full abstract ▾
All authors Anna-Christina Glock, Thomas Hütter, Johannes Fürnkranz, Wolfram Wöß, Christine Dominka-Kiss, Lisa Ehrlinger
Software Engineering
SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness
Yizhuo Zhang, Bo Kang, Yi Yang et al. (+3 more)
Autonomous
agent systems increasingly depend on reusable skill abstractions for consolidating experiential knowledge and domain expertise. These artifacts typically bundle free-form instructions with heterogeneous resources. However, ensuring their correctness remains challenging. Their failure modes transcend conventional code defects to subtle semantic inconsistencies such as intent conflicts, which manifest as silent failures masked by the underlying model. Moreover, skill correctness must be grounded in intended task boundaries and generalizability. We propose SkillSpec, a Hoare-style framework that formulates skill correctness as a specification
reasoning problem. It transforms a heterogeneous skill repository into a unified graph representation that aligns descriptions, instructions and code artifacts. For each node, SkillSpec derives an ExpectSpec from the surrounding declared intent, and infers FactSpecs from encoded behavior under partially disclosed intent. An intent mask regulates access to holistic, lineage, neighborhood, and local views to balance the bias introduced by excessive context against unsupported inference caused by insufficient context. SkillSpec jointly reasons over these views to flag candidate defects, and automatically validates them in an isolated sandbox. On 515 real-world skills from SkillsBench and widely downloaded repositories, SkillSpec identified 763 manually confirmed defects across 239 skills, achieving 61.2% precision. The node-level analysis across multiple model families shows that specification
reasoning is consistently reliable for code nodes, whereas plain-text nodes remain a major bottleneck. Most defects arise at the boundaries between declared intent and implementation, demonstrating that explicit specifications provide a practical foundation for skill quality assurance in real-world
agent ecosystems.
Read the full abstract ▾
All authors Yizhuo Zhang, Bo Kang, Yi Yang, Zhiyu Duan, Zhouteng Ye, Shunkun Yang
Computer Vision
Image-Scale Robustness and Visual Recognition Performance: A Cross-Architecture Analysis
Anish Monsley Kirupakaran
The sensitivity of visual recognition models to changes in image scale is well established, yet the factors governing this sensitivity across heterogeneous architectures remain unclear. In this work, we investigate whether scale robustness exhibits a common quantitative structure across modern
vision models. We evaluate 20 pretrained ImageNet-1K classifiers spanning seven architectural families, including convolutional, mobile, efficient, and
Transformer-based architectures. By systematically reducing input image scale, we construct scale-accuracy response curves and define a characteristic scale as a compact measure of the onset of substantial recognition degradation. We then examine the relationship between characteristic scale and baseline recognition accuracy, model parameter count, architectural family, and representation stability. A strong inverse association is observed between baseline accuracy and characteristic scale (Pearson r = -0.890, R^2= 0.792, p < 10^-6). This relationship remains stable under bootstrap resampling, leave-one-architecture-out analysis, and leave-one-family-out analysis. In contrast, parameter count provides negligible additional explanatory power after controlling for baseline accuracy (p = 0.80), while architectural family does not provide significant incremental explanatory power. Furthermore, characteristic scale shows essentially no association with representation stability (r = -0.003, p = 0.991). These results indicate that, across the studied models, scale robustness is strongly organized by baseline recognition performance rather than simply by model size, architectural family, or representation stability. The study provides an empirical framework for characterizing scale robustness across
vision architectures and identifies a reproducible accuracy-scale regularity that warrants further theoretical investigation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from math.CA
A solution to the Erdős Problem #1040
Ioannis Tzachristas
For a compact set $K\subset\mathbb{C}$, let $\vartheta(K)$ be the infimum of the planar areas of the unit lemniscates of all monic
polynomials with zeros in $K$, allowing arbitrary degree and repeated zeros. We prove that $\vartheta(K)=0$ whenever $\operatorname{cap}(K)=1$, with no regularity assumption on $K$. The proof uses a centered harmonic
polynomial that is positive on all but a set of arbitrarily small area in the
polynomial hull of $K$. A
Fourier average of exterior harmonic measures realizes this
polynomial as the logarithmic potential of a signed measure having bounded density with respect to the
equilibrium measure. A positive perturbation and an $L^1$ approximation by empirical measures then produce the required
polynomials. This extends the smooth-boundary result of Krishnapur, Lundberg, and Ramachandran to arbitrary compact sets of capacity one. Together with the capacity-greater-than-one
theorem of Ghosh and Ramachandran and an elementary argument for unbounded sets, it follows that $\vartheta(F)=0$ for every closed infinite set $F\subset\mathbb{C}$ of transfinite diameter at least one, answering the vanishing question in Erdős Problem 1040.
Read the full abstract ▾
Computation and Language
Generating Adversarial Texts for Machine Translation via GRPO
Florian Zogaj, Jakob Hütteneder, Giovanni De Muri et al. (+3 more)
As machine translation (MT) systems continue to improve, standard
benchmarks become less informative for exposing remaining weaknesses. Traditional methods for creating challenging test sets rely on expensive manual creation or curation, while automated approaches struggle to produce sets with the necessary translation difficulty and linguistic diversity. We propose a scalable reinforcement-learning-based approach for rewriting existing source texts into instances that are more difficult to translate for MT systems. We fine-tune a large
language model with Group Relative Policy Optimization (GRPO), using reward signals based on translation difficulty together with constraints for semantic similarity, grammaticality, and approximate length preservation. On WMT25, our approach substantially reduces average COMET translation quality from 0.63 to 0.48, while preserving grammaticality and readability, whereas the base model remains at 0.64. Evaluations on the unseen WMT19-WMT24
benchmarks confirm that this behavior generalizes beyond the training data, and human evaluation further shows that the rewrites substantially lower translation quality while incurring a moderate drop in naturalness and only a small change in grammaticality. We release our code to support reproducibility.
Read the full abstract ▾
All authors Florian Zogaj, Jakob Hütteneder, Giovanni De Muri, Federico Villa, Aryan Sood, Vilém Zouhar
Robotics
FALCON-S: Fixed-wing ground-effect Aerodynamics Simulator and Flight Control Learning Suite
Matteo El Hariry, Pedro Lima, Andrej Orsula et al. (+2 more)
We present a modular, high-fidelity simulation framework for the development and benchmarking of flight control strategies in fixed-wing aerial
robots operating near the ground. Unlike existing simulators that rely on simplified or hover-oriented dynamics, our framework models full 6DoF rigid-body physics, semi-empirical ground-effect aerodynamics, actuator dynamics, sensor noise, and environmental disturbances. This physical realism, combined with modular component design, enables systematic analysis of low-altitude flight behavior under realistic conditions. The simulator supports both CPU and GPU backends via Torch and NVIDIA Warp, enabling high-throughput parallel execution suitable for large-scale reinforcement learning training and optimal control rollouts. A unified interface accommodates a range of controllers (both RL and optical control
algorithms) across tasks such as altitude regulation and trajectory tracking. Cross-validation with X-Plane and JSBSim is also supported to facilitate engineering integration and visual fidelity.
Read the full abstract ▾
All authors Matteo El Hariry, Pedro Lima, Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez