Machine Learning
An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage
Ioannis Theologitis, Debin Meng, Stylianos Eleftheriadis et al. (+2 more)
Artificial intelligence can support cultural heritage and digital humanities through large-scale
retrieval and analysis of digitized collections. However, cultural heritage data are often distributed across institutions, constrained by ownership and access restrictions, and continuously evolving over time.
Federated Continual Learning (FCL) is well suited to this setting, as it enables models to learn from distributed and sequential data without sharing raw collections. In this paper, we propose FedCurv-DR, a lightweight, regularisation-based FCL strategy. The method accumulates parameter-importance estimates across clients and experiences to protect learned knowledge, while updating them only at fixed intervals to minimize communication and computation overhead. We evaluate FedCurv-DR in a continual learning scenario using the WikiArt image
dataset for genre classification with evolving styles, reporting performance, energy, and
fairness metrics. Our results show that FedCurv- DR reduces forgetting and balances performance,
fairness, and energy efficiency for sustainable AI in cultural heritage.
Read the full abstract ▾
All authors Ioannis Theologitis, Debin Meng, Stylianos Eleftheriadis, Vasileios Lolis, Konstantinos Votis
Discrete Mathematics · Cross-listed from math.CO
Broadcast Domination Number is at Most Twice the Multipacking Number
Sk Samim Islam
For a graph $ G = (V, E) $ with a vertex set $ V $ and an edge set $ E $, a function $ f : V \rightarrow \{0, 1, 2, . . . , diam(G)\} $ is called a broadcast on $ G $. For each vertex $ u \in V $, if there exists a vertex $ v $ in $ G $ (possibly, $ u = v $) such that $ f (v) > 0 $ and $ d(u, v) \leq f (v) $, then $ f $ is called a dominating broadcast on $ G $. The cost of the dominating broadcast $f$ is the quantity $ \sum_{v\in V}f(v) $. The minimum cost of a dominating broadcast is the broadcast domination number of $G$, denoted by $ \gamma_{b}(G) $. A multipacking is a set $ M \subseteq V $ in a graph $ G = (V, E) $ such that for every vertex $ v \in V $ and for every integer $ r \geq 1 $, the ball of radius $ r $ around $ v $ contains at most $ r $ vertices of $ M $, that is, there are at most $ r $ vertices in $ M $ at a distance at most $ r $ from $ v $ in $ G $. The multipacking number of $ G $ is the maximum cardinality of a multipacking of $ G $ and is denoted by $ mp(G) $. It is known that $mp(G)\leq\gamma_b(G)$. In 2014, Hartnell and Mynhardt proved that $\gamma_b(G)\leq 3mp(G)-2$ whenever $mp(G)\geq2$. In 2019, Beaudou, Brewster, and Foucaud improved this bound to $\gamma_b(G)\leq 2 mp(G)+3$ and conjectured that $\gamma_b(G)\leq 2 mp(G)$. We solve their
conjecture by proving that $\gamma_b(G)\leq 2 mp(G)$ for every graph $G$. Our proof is constructive and yields a linear-time $2$-approximation
algorithm for Maximum Multipacking problem which improves the earlier approximation factor $2+o(1)$.
Read the full abstract ▾
Digital Libraries
A large-scale dataset of sub-institution name disambiguation and hierarchical structures from OpenAlex
Zhentao Liang, Jin Mao and Gang Li
Accurate attribution of scholarly work to specific sub-institutional units, such as schools or departments of a university, is crucial for granular research assessment and policymaking. While robust identifiers exist for top-level institutions, standardized data for sub-level units remains scarce due to the linguistic and structural variability of affiliation strings. In this study, we introduce OpenSubAffil, a large-scale
dataset mapping raw affiliation strings from OpenAlex to disambiguated sub-institutional entities and their hierarchical structures. We developed a pipeline integrating named entity recognition (NER) with
embedding-based clustering. Furthermore, we proposed a multi-signal scoring function that synthesizes lexical and co-occurrence evidence to reconstruct the sub-institutional hierarchy. OpenSubAffil comprises mappings for 40 million affiliation strings to 638,843 disambiguated sub-units across 18,635 top-level institutions, together with their hierarchical relationships. Validation against Wikidata
benchmarks and manual investigation show that our method achieves promising performance. Overall, this
dataset bridges the granularity gap between individual researchers and top-level institutions, enabling high-resolution analyses of scholarly output and communication at the sub-institutional level. The OpenSubAffil
dataset is publicly available at https://doi.org/10.5281/zenodo.19602782.
Read the full abstract ▾
Numerical Analysis
A Comprehensive p-VEM Framework for Advanced Variable Stiffness Plates with Arbitrary Shapes
Paola Pia Foligno, Daniele Boffi, Fabio Credali et al. (+1 more)
This paper presents a comprehensive, high-order (p-version) Virtual Element Method (VEM) framework for the structural analysis of innovative variable stiffness plates. VEM is particularly suited for complex configurations due to its ability to handle arbitrary polygonal meshes, including curved edges. However, its mathematical formulation may hinder its spread in the engineering community. This work illustrates a formulation with an accessible implementation using well-known FEM notation and integrating at the same time a set of new advanced capabilities. Specifically, both standard stabilized and advanced self-stabilized strategies are adopted. To further improve the robustness of VEM in the presence of variable coefficients,
polynomial projections taking into account the coefficients are employed. This approach is referred to as Variable Coefficients-VEM approach (VC-VEM). This unified framework is applied to linear static, free-vibration, and buckling analyses, and validated against analytical solutions and numerical
benchmarks. In particular, plates with cutouts and problems featuring high-gradient solutions are investigated, demonstrating that the proposed comprehensive approach provides a flexible and ready-to-implement tool for advanced structural design.
Read the full abstract ▾
All authors Paola Pia Foligno, Daniele Boffi, Fabio Credali, Riccardo Vescovini
Game Theory
Temporal Fair Division of Indivisible Mixed Manna: Tractable Settings
Kui-Wang Choi, Minming Li and Nicholas Teh
We study temporal fair division of indivisible mixed manna. Items arrive over time and must be allocated irrevocably; an item may be a good for some
agents, a chore for others, and neutral for the rest. We require the cumulative allocation after every round to be envy-free up to one item (TEF1). Although deciding whether a TEF1 allocation exists is NP-hard even for goods, we identify several tractable settings. First, with at most $k$ item types, an online cyclic rule guarantees EF$\lceil k/2\rceil$ after every item arrival. Thus, every instance with at most two types admits an online TEF1 allocation; moreover, when the numbers of
agents and types are fixed, TEF1 existence can be decided in
polynomial time. Second, under agreement after
agent-specific scaling, provided that the scaling factors are known before arrivals begin, an online rule produces an allocation that is EF1 and Pareto optimal after every item arrival. Third, for a two-part arrival sequence with common rankings, we give a rule that is EF1 after every item arrival. Fourth, when the number of
agents is fixed and values are bounded integers, we give an exact pseudo-
polynomial algorithm for deciding TEF1 existence. Finally, for goods, every TEF1 allocation gives each
agent at least $1/n$ of her maximin share after every round; this factor is tight even for identical valuations and two rounds. Deciding whether an exact temporal maximin-share allocation exists is NP-hard for both goods and chores, even with identical valuations, two
agents, and two rounds.
Read the full abstract ▾
Computer Vision
From Street View Imagery to Street Quality Indicators: Vision Language Inference for the Suburban 15-minute City
Joan Perez and Giovanni Fusco
Streetscape quality has become a central concern in contemporary urban planning, particularly within the framework of the pedestrian-friendly 15-minute city, where walkability and public-space quality are increasingly recognized as key determinants of urban performance. However, assessing streetscape qualities across large suburban and peri-urban territories remains challenging due to the time and resource demands of conventional field surveys. This paper presents a planning-oriented assessment of streetscape qualities in the north-eastern periphery of Nice (France) using the latest release of SAGAI (Streetscape Analysis with Generative AI), an open-source workflow that leverages
vision-
language models (VLMs) for large-scale streetscape analysis from Google Street View imagery. The new release addresses limitations of the original framework through improved image acquisition, geographically consistent view generation, support for multiple VLM architectures, consensus-based inference, and an integrated analytical environment. The workflow is applied to several thousand street-level observations to evaluate qualities relevant to pedestrian-friendly urban environments: sidewalk presence, pedestrian entrance density, and vegetation. The resulting maps reveal that the desired streetscape qualities characterize only a fraction of today's suburban streetscapes, mainly in compact developments and traditional suburban faubourgs, while they are particularly lacking on residential hills. The analysis demonstrates the potential of contemporary VLMs to support urban diagnostics in extensive suburban territories where fieldwork would be prohibitively time-consuming. Beyond the case study, the paper illustrates how recent advances in
vision-
language models can contribute to evidence-based planning by enabling scalable, flexible, and interpretable assessments of urban public-space quality.
Read the full abstract ▾
Machine Learning
CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting
Alexander Marusov, Dmitry Anikin, Petr Sokerin et al. (+3 more)
Probabilistic
forecasting models are widely used for time series
forecasting in domains such as energy systems, finance, medicine, and transportation. In recent years, deep generative models have shown strong results on probabilistic
forecasting, yet many conventional approaches struggle to capture internal temporal dependencies, leading to latent representations with limited expressive power. To address this limitation, we propose CLaST, a VAE framework for probabilistic multivariate time series
forecasting. Unlike existing generative models, CLaST learns
embeddings that preserve contextual similarity between observations through our contrastive loss function. Experiments across nine widely adopted
benchmarks demonstrate that CLaST consistently surpasses strong baseline methods. In short-term
forecasting tasks, our approach achieves improvements of up to $16.4\%$ in CRPS and $14.4\%$ in NMAE over the second-best method. Furthermore, in long-term prediction CLaST attains superior overall performance, exceeding the second-best method by up to $48.6\%$ and $25.1\%$ in CRPS and NMAE, respectively.
Read the full abstract ▾
All authors Alexander Marusov, Dmitry Anikin, Petr Sokerin, Vitaliy Pozdnyakov, Ilya Kuleshov, Alexey Zaytsev
Machine Learning
Systematic Evaluation of TabPFN-TS and Chronos-2 for Zero-Shot Heat Load Forecasting in District Heating Networks
Ben Spoek, Karim K. Ben Hicham, Kai Derzsi et al. (+3 more)
District heating energy hubs require reliable heat load forecasts for efficient operational scheduling.
Forecasting models trained on historical data may require retraining as networks evolve. Zero-shot time-series foundation models and in-context
forecasting therefore offer a promising alternative: they can adapt at inference time from recent observations rather than by repeated retraining. This study systematically evaluates TabPFN-TS and Chronos-2 for probabilistic heat load
forecasting in two German district heating networks and compares them with trained baselines. We assess whether TabPFN-TS, whose underlying model is pretrained entirely on synthetic tabular rather than time-series data, can capture complex district heating dynamics. We analyze
covariate choice, context length, temporal resolution, and forecast horizon on selected operating weeks, evaluate the selected configuration over the full year, and assess cross-network transfer. The principal
benchmark assumes perfect weather forecasts; a separate sensitivity analysis uses retrospective weather predictions. Hourly 24-hour
forecasting with a 12-week rolling context and ambient temperature provides a parsimonious configuration; longer context windows do not improve accuracy. Both TSFMs outperform all trained baselines in deterministic accuracy in the full-year
benchmarks. Chronos-2 achieves the best deterministic scores, with TabPFN-TS remaining close: their CVRMSE values on the main data set are 12.48% and 13.07%, respectively. Chronos-2 also achieves lower continuous ranked probability scores in both networks, with TabPFN-TS remaining close. a TSFM-based Multi-Resolution Residual-Correction Forecaster combines an hourly base forecast with short-term high-resolution corrections. Relative to direct high-resolution
forecasting, it generally reduces errors in total heat demand over 12-hour periods and recorded prediction times.
Read the full abstract ▾
All authors Ben Spoek, Karim K. Ben Hicham, Kai Derzsi, Philipp Althaus, Alexander Mitsos, Dirk Müller
Artificial Intelligence
Contrastive Mixed Prompt Learning for Incomplete Multimodal Sentiment Analysis with Unseen Modality Combination
Kaixin Xu, NaiJin Liu, Yulin Kang et al. (+8 more)
Incomplete
multimodal sentiment analysis has garnered significant
attention in recent years. Existing approaches typically assume that data is missing at random or are designed specifically for certain missing patterns, ignoring the modality combination inconsistency between training and testing phases. However, in real-world scenarios, the testing phase often encounters modal combinations that were not present during the training phase, which leads to insufficient generalization capabilities and unstable performance. In this paper, we introduce the problem of Incomplete
Multimodal Sentiment Analysis with Unseen Modality Combinations (IMSAUMC), aiming to enhance model generalization for unseen modality combinations. To address this challenge, we propose the model named $\textbf{C}$ontrastive $\textbf{M}$ixed $\textbf{P}$rompt $\textbf{L}$earning ($\textsf{CMPL}$) for IMSAUMC. It introduces a label-guided contrastive feature learning mechanism to learn robust and discriminative cross-modal representations. Additionally, we design modality-combination
prompts with a soft router to facilitate better learning of various modality combinations. Furthermore, we introduce three
prompt contrastive learning strategies, which enable effective learning of
prompts corresponding to unseen modality combinations, thereby significantly strengthening the model's generalization capabilities in diverse testing scenarios. Extensive experiments on three widely used
datasets demonstrate that $\textsf{CMPL}$ achieves more than a 5% improvement in accuracy compared to state-of-the-art approaches.
Read the full abstract ▾
All authors Kaixin Xu, NaiJin Liu, Yulin Kang, Tangyue Jin, Zixuan Yu, Wenxi Zhao, Yibei Liu, Qianle Zhang, Yangyang Wu, Mengying Zhu, Meng Xi
Data Structures and Algorithms
The Greedy Superstring Algorithm Achieves Ratio 2 for Strings of Length 6 Already
Nikolai Chukhin, Alexander S. Kulikov, Ivan Mihajlin et al. (+1 more)
In the Shortest Common Superstring (SCS) problem, one is given a set of strings and is asked to find a string of minimum length containing each of the input strings as a substring. The greedy superstring
conjecture states that the following natural greedy
algorithm has approximation ratio $2$: while there is more than one string, select the pair of strings with the maximum overlap, merge them, and add the merged string back to the set. The greedy
algorithm works in linear time and is probably the simplest possible approximation
algorithm for SCS. If the
conjecture holds, then the greedy
algorithm also surpasses the approximation guarantees of the best known approximation
algorithms. The
conjecture is open for $40$ years already and even the approximation ratio $\rho_k$ in the special case in which input strings have length $k$ has not yet been found: for all $k \ge 3$, $2-1/k \le \rho_k \le \min\{(k+1)/2, 3.396\}$. We prove that already for strings of length $6$, the approximation ratio of the greedy
algorithm is at least $2$: $\rho_k \ge 2$ for all $k \ge 6$. We also show that $\rho_3=9/5$, thus completely characterizing the worst-case behavior of the greedy
algorithm for strings of length $3$.
Read the full abstract ▾
All authors Nikolai Chukhin, Alexander S. Kulikov, Ivan Mihajlin, Alexander Smal
Artificial Intelligence
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
Yansen Han, Shengyi Liao, Yuanxing Zhang et al. (+2 more)
Preference optimization is a standard
alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven updates modify transport trajectories without an inherent constraint to the pretrained data
manifold and can move terminal samples off the pretrained support. We formalize this failure mode as
manifold drift. Theoretically, we show that optimal flow matching recovers the terminal data distribution, whereas a preference update leaves the pretrained
manifold whenever its induced terminal displacement has a nonzero normal component. As a remedy, we propose ThermoDPO, a temperature-controlled objective that anchors pairwise preference optimization on preferred samples. Across temperature regimes, this objective connects rejection sampling fine-tuning and FlowDPO and controls a pointwise reconstruction-based surrogate for
manifold distance. To counteract diminished signals at low temperatures, we further introduce a weighted variant, ThermoDPO-weighted. On the main toy
benchmark, ThermoDPO-weighted attains a StrictScore of 0.899, compared with 0.629 for FlowDPO and 0.857 for FlowDPO+RFT. On SD3.5-M at CFG = 4.5, it improves OCR by 47.5% and the average of four metrics by 16.0%.
Read the full abstract ▾
All authors Yansen Han, Shengyi Liao, Yuanxing Zhang, Pengfei Wan, Tao Lin
Artificial Intelligence
ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting
Rui Wang, Yeteng Wu, Xianlin Zhang et al. (+1 more)
Understanding object dynamics requires not only predicting future trajectories but also examining whether a model captures the physical properties that govern motion. However, existing
benchmarks rarely expose object-level physical properties as explicit evaluation targets alongside trajectory
forecasting. To address this gap, we introduce ExPhy, a multi-object trajectory
forecasting benchmark containing 24,000 simulated physical scenes with explicit object-level labels for mass, friction, and restitution. ExPhy provides observed and future trajectories together with an in-distribution (ID) split and two out-of-distribution (OOD) splits over physical parameters (OOD-Parameter) and initial states (OOD-Initial) for jointly evaluating trajectory
forecasting and physical property estimation. We further instantiate PhyODE, a physics-guided model with an explicit property interface that estimates physical properties from observed trajectories and uses them for differentiable future rollout. On the long-horizon OOD-Initial setting, PhyODE reduces ADE and FDE by 33.1% and 31.0%, respectively, compared with the strongest baseline. Zero-shot evaluation on ComPhy further assesses cross-
benchmark transfer. Property-level analyses reveal that accurate trajectory
forecasting does not necessarily imply accurate recovery of the underlying physical properties. Code and data are available at https://github.com/Zest86/ExPhy.
Read the full abstract ▾
All authors Rui Wang, Yeteng Wu, Xianlin Zhang, Mengshi Qi
Information Theory
Real Interference Alignment for Active IRS-Aided Systems: A Rate-Profile Learning-Based Approach
Junda Liao, Quanzhong Li and Qi Zhang
With additional spatial degrees of freedom provided by the active intelligent reflecting surface (IRS), interference
alignment (IA) can be achieved at low cost. In this letter, we propose a real IA scheme for an active IRS-aided system. The proposed scheme only requires the IRS to know the instantaneous channel coefficients under the assumption of blocked direct links. To maximize the achievable sum rate subject to individual minimum rate requirements and transmission power constraints, we propose a rate-profile learning-based
algorithm. The
algorithm uses offline-trained achievable rate profiles to decouple the original problem into multiple feasibility subproblems, which are then solved by generalized
eigenvalue decomposition. Simulation results demonstrate that our proposed
algorithm outperforms the conventional weighted minimum mean square error
algorithm, while requiring significantly less program execution time.
Read the full abstract ▾
Machine Learning
Scale-Aware Pretraining of Time Series Foundation Models via Multi-Patch Token Alignment and Hybrid Masking
Taihua Chen, Xiang Ma, Yixin Zhang et al. (+3 more)
Pretraining time series foundation models across heterogeneous
datasets necessitates effective handling of varying sampling frequencies. Current methods either employ
dataset-specific patch sizes and separate FFNs, leading to fragmented representations, or enforce a fixed patch size that neglects inherent temporal variations. To address this, we propose SATS, featuring a scale-aware
token alignment mechanism that treats patch size as an explicit notion of scale. By incorporating a contrastive-inspired
alignment regularizer, SATS aligns representation spaces across scales while preserving distinct modeling capacities. Furthermore, a hybrid masking strategy combining random and contiguous masking is introduced to capture multi-scale temporal structures. Experimental results on LSTF
benchmarks demonstrate that SATS achieves a 9.2% improvement in MSE and an 8.3% gain in GIFT-Eval MASE compared to competitive baselines. Notably, SATS consistently delivers SOTA performance while achieving a 65.6% increase in model efficiency over advanced baselines, highlighting its effectiveness and scalability in time series pretraining.
Read the full abstract ▾
All authors Taihua Chen, Xiang Ma, Yixin Zhang, Tailin Zhan, Manyu Sun, Lizhen Cui
Computer Vision
Point-Based 3D Reconstruction from Sparse Views under Known Illumination
Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad et al. (+3 more)
Sparse view 3D reconstruction is commonly addressed with neural implicit surfaces or dense point-based representations such as Gaussian splatting. Surface-aware splatting methods improve extracted geometry through oriented primitives and regularization, while RadiosityGS incorporates differentiable light transport through a radiosity inspired finite-element surfel formulation. We propose a differentiable point rendering method based on opacity-bearing beta surfels. An opacity explicit adjoint light transport formulation provides gradients for surfel geometry and appearance parameters, allowing physically based light transport to constrain reconstruction. Across five synthetic objects reconstructed from ten posed views, our method achieves the lowest mean symmetric Chamfer distance among the evaluated baselines and reduces mean Chamfer distance by 28.5% relative to the strongest point-based baseline while using only 267 surfels on average, approximately ~161 fewer primitives. Directional Chamfer results further show improved accuracy and competitive completion relative to related point-based methods. These results show that, in the controlled direct illumination setting, compact beta surfels combined with transport-based optimization can recover surfaces without relying on the tens to hundreds of thousands of primitives used by the evaluated baselines.
Read the full abstract ▾
All authors Magnus Kaufmann Gjerde, Joakim Bruslund Haurum, Jeppe Revall Frisvad, Markus Worchel, J. Andreas Bærentzen, Thomas B. Moeslund
Information Retrieval
SCoRD: Semantic-Assisted Continual Retriever-Reranker Distillation for LLM-Based Recommendation
Seunghyun Baek, Gyuseok Lee, Seunghan Lee et al. (+3 more)
Recommendation systems increasingly adopt a two-stage pipeline, where an ID-based retriever retrieves candidates and an LLM-based reranker refines their rankings. To improve
retrieval quality, reranker-to-retriever
distillation is commonly used to transfer the reranker's knowledge to the retriever. For practical deployment, however, this pipeline must continually adapt to evolving interests and incoming interactions. A naive solution is to repeatedly update the LLM reranker and distill its latest knowledge, but this incurs prohibitive costs. Updating the retriever alone is cheaper, but its limited capacity makes adaptation from sparse data difficult. We propose SCoRD, a continual knowledge
distillation framework for LLM-based reranking pipelines under a non-stationary data stream. SCoRD introduces a semantic
reasoning assistant that distills the LLM's ability to infer underlying user intents into reusable intent-level guidance. It selectively distills reranker knowledge to the retriever on low-confidence sequences, guides retriever-only updates without repeated LLM inference, and feeds retriever-derived representations and intent-drift signals back to the reranker. Experiments on real-world
datasets show that SCoRD enables effective and efficient retriever-reranker co-adaptation.
Read the full abstract ▾
All authors Seunghyun Baek, Gyuseok Lee, Seunghan Lee, Wonbin Kweon, Dong Wang, SeongKu Kang
Neural and Evolutionary Computing
The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation
Hadi Al Mubasher and Mariette Awad
A recurring pattern in neural computation is the reintroduction of dynamical and biological structure into models originally simplified for scalable optimization. Early feedforward networks reduced biological
neurons to threshold or rate-like summation units, an abstraction compatible with global-gradient training at scale. Since then, forward computation has diversified: modern architectures carry recurrent state, retrieve from long contexts through
attention and associative
memory, compress histories through structured state-space dynamics, evolve in continuous time, settle to implicit
equilibria, and communicate through sparse spikes. Training has diversified less. Scalable learning remains concentrated around backpropagation, backpropagation through time, adjoint methods, implicit differentiation, and surrogate-gradient variants. We call this asymmetry the forward-backward disconnect and develop a taxonomy spanning neural model families along three coupled axes: state-dynamics structure, credit-assignment mechanism, and biological grounding. Forward and learning grounding are treated separately, and the unit of analysis is the architecture-learning configuration rather than the architecture name alone. Across static, recurrent,
attention-based, state-space, continuous-time, implicit, spiking, biologically plausible, and neuromorphic families, forward dynamics have diversified while the highest demonstrated scales remain concentrated in global or closely gradient-derived error-propagation mechanisms. Closing this disconnect requires better
alignment among state dynamics, credit assignment, and computational substrate.
Read the full abstract ▾
Machine Learning
Green BOA: Determining the environmental break-even point for ML-based data compression
Caterina Doglioni, Thomas Elliott, Akshat Gupta et al. (+3 more)
We summarise the outcome of two summer internship projects based at the University of Manchester, focused on the break-even point in terms of environmental sustainability for ML-based data compression
algorithms. Using the example of a ML-based lossless compression
algorithm, we compare estimates for the carbon-equivalent of the infrastructure needed for ML training and inference with the carbon-equivalent savings from reduced disk storage requirements, and discuss their break-even point.
Read the full abstract ▾
All authors Caterina Doglioni, Thomas Elliott, Akshat Gupta, Hanzila Hussain, Sanjiban Sengupta, Zhengkai Sun
Artificial Intelligence
Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees
Yu Chen, Ruishuo Chen, Xun Wang et al. (+2 more)
Loading reusable skill documents into a bounded context window has become a primary way large
language model (LLM)
agents acquire task-specific capabilities, which makes skill selection a first-order determinant of task performance and
token cost. Yet current
agents score skills independently by semantic relevance and assemble the set by top-$k$ or greedy packing, with no quality guarantee or cost awareness on the selected set. Redundant or poorly chosen skills then waste scarce context
tokens and can even degrade performance. In this paper, we present a theory-grounded and practical framework for budgeted skill selection. We give the first model of how skill sets shape execution outcomes, capturing complementary capability coverage and diminishing returns from redundancy through a monotone submodular benefit, while accounting for context degradation with a linear
token penalty under a hard budget. Based on this model, we develop Best Prefix Selection (BPS), a
polynomial-time
algorithm, and prove, to our knowledge, the first performance guarantee for skill selection: a bicriteria $(1-1/e,1)$ approximation whose benefit coefficient is optimal in
polynomial time. We construct a controlled testbed based on BigCodeBench to isolate the effect of skill selection on execution success. On it, BPS with a learned capability encoder reaches a success rate of 0.65, and the strongest baselines need at least 28% more
tokens to reach 0.60.
Read the full abstract ▾
All authors Yu Chen, Ruishuo Chen, Xun Wang, Zhuoran Li, Longbo Huang
Computer Vision
STEP: Score-Based Temporal Energy for Human Pose Video Anomaly Detection
Jakub Micorek, Mateusz Koziński and Horst Possegger
Skeleton-based
Video Anomaly Detection (VAD) offers a robust,
privacy-preserving solution for identifying abnormal behaviors. To model the distribution of normal static and moving poses, recent methods train Energy-Based Models (EBMs) via Denoising Score Matching (DSM). However, directly injecting noise, required for training, into raw joint coordinates creates physically impossible poses, and this structural collapse severely worsens as the temporal window expands. To address this, we introduce STEP, a simple framework that utilizes Principal Component Analysis (PCA) to project pose sequences into a compact, whitened PC-space. Learning the data density within this well-behaved PC-space ensures that the injected noise translates into physically plausible variations, which allows the model to process longer
video sequences without the performance collapse of raw coordinate baselines. Additionally, to mitigate inherent pose estimation inaccuracies arising from occlusions or motion blur, we integrate a sequence-level weighting mechanism based on the
estimator's confidence scores. Operating at real-time computational efficiency, our simple and lightweight framework outperforms the previous skeleton-based state-of-the-art by 12.2% (90.1% AUROC) on the challenging UBnormal
dataset and achieves highly competitive results by improving on the ShanghaiTech
benchmark.
Read the full abstract ▾
Cryptography and Security
COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense
Roshan Sood, Onat Gungor and Tajana Rosing
LLMs remain vulnerable to
prompt injection attacks, where
adversarial instructions embedded in user inputs or external content manipulate model behavior and bypass safeguards. Existing defenses are predominantly static, relying on fixed
alignment objectives or attack-specific filtering mechanisms that require redesign as new attack strategies emerge. While recent lifelong
alignment methods address shifting user preferences, they do not account for adaptive adversaries that continually evolve to exploit weaknesses in previously learned defenses. This limitation is particularly important in real-world deployments, where evolving attack distributions necessitate continual adaptation without sacrificing robustness to previously encountered threats. We present COPA, a continual preference optimization framework that treats
prompt-injection defense as a lifelong learning problem. Instead of one-time
alignment, COPA incrementally incorporates feedback from newly observed attacks via GRPO-based optimization and uses margin-weighted experience replay to retain defenses against prior attack classes. This enables continuous adaptation to emerging threats while mitigating catastrophic forgetting and preserving general-purpose model capabilities. Across lifelong
prompt injection attack streams, COPA reduces attack success rate by up to 6.3x and 4.4x on average compared to state-of-the-art defenses. These results highlight continual preference optimization as an effective paradigm for defending LLMs against adaptive adversaries.
Read the full abstract ▾
Computation and Language
HealMed: Multilingual Evaluation of Large Language Models in Medicine
Yingjian Chen, Fan Gao, Sherry T. Tong et al. (+41 more)
We present HealMed, an expert-reviewed
benchmark for
multilingual evaluation of large
language models in medicine. HealMed contains 1,000 examples in each of nine
languages, drawn from nine
datasets and covering three task formats: MCQA, NLI and open-ended QA. The
benchmark was developed over two years by 23 physicians and medical experts based across nine countries and regions. Each translation was evaluated and revised by two experts fluent in English and the corresponding target
language. On HealMed, performance declined most in low-resource
languages, although the size of the gap varied markedly across
languages and models. The strongest proprietary models were the most stable across
languages, whereas many open-source and medically specialized models showed larger and less consistent gaps. Medical specialization alone did not ensure
multilingual robustness. Furthermore, expert revision could either raise or lower measured performance, indicating that translation quality materially affects cross-
language evaluation results.
Read the full abstract ▾
All authors Yingjian Chen, Fan Gao, Sherry T. Tong, Haoyu Zhang, Aosong Feng, Kevin W. Jin, Xing Wu, Jinghui Lu, Abdul Samad, Akbar Faruqi, Cesar Caraballo, Cibele Brandão, Dhruva Gupta, Eunji Jeon, Gabriel Madera-Santiago, Geon Lee, Hugo Toshio Itikawa, Insook Cho, Isabelli Martins, Isarar Siddique, Israr Ahmed, Jihyo Kwak, Kanyakorn Veerakanjana, Luis Guilherme Cardoso, Minjin Kim, Piyalitt Ittichaiwong, Renee Dua, Santiago Gudiño-Rosales, Xiujie Chen, Zeo Lapalus, Zixin Xu, Michihiro Yasunaga, Rex Ying, Heuiseok Lim, Jaewoo Kang, Chanjun Park, Hang Jiang, Ethan Goh, Hyunjae Kim, Edison Marrese-Taylor, Yusuke Iwasawa, Yutaka Matsuo, Qingyu Chen, Irene Li
Systems and Control
Validation of a driver model for energy consumption simulations of road vehicles
Luigi Romano, Michele Godio, Fredrik Bruzelius et al. (+1 more)
The energy performance of road vehicles has traditionally been evaluated using driving cycles, in which a prescribed speed profile is tracked either in simulation or by a physical vehicle. Recent research has proposed an alternative framework based on operating conditions, where the driving environment is described in terms of factors such as road topography, legal speed limits, traffic, and weather, rather than by an explicit speed profile. This paper addresses the complementary problem of driver modeling, necessary to translate the operating conditions to a speed profile. A simple driver model designed to be compatible with the operating-condition framework and evaluates its ability to reproduce realistic driving behavior is investigated. Validation of the model is done through a controlled driving-simulator study vehicle log files collected during real-world operation and are used to identify the model parameters and assess the model's predictive performance. The results suggest that this simple model can be efficient in reproducing major effects of driver behavior, while further research is required to fully assess its validity.
Read the full abstract ▾
All authors Luigi Romano, Michele Godio, Fredrik Bruzelius, Pär Johannesson
Information Theory · Cross-listed from math.AC
Generalized Hamming weights of codes arising from complete intersection
Eduardo Camps Moreno, Flavio Salizzoni and Rodrigo San-José
We provide a positive answer to a
conjecture proposed by Tohǎneanu and Van Tuyl regarding the minimum distance of codes whose underlying set of points is a reduced complete intersection. Despite the technical nature of the
conjecture, we show that it follows directly from a not-well-known refinement of the classical Bézout bound for overdetermined
polynomial systems. For completeness, this paper presents a self-contained proof of this refined bound. Furthermore, we show that using the same approach, it is possible to obtain a bound on the generalized Hamming weights of such a code and, more generally, to control the minimum distance of the codes obtained by evaluating forms of degree $d$ on the points of a zero-dimensional complete intersection.
Read the full abstract ▾
Robotics
Learning Highly Dynamic Skills Transition for Quadruped Jumping Through Constrained Space
Zeren Luo, Jiahui Zhang, Yimin Han et al. (+4 more)
Although legged animals are capable of performing explosive motions while traversing confined spaces, replicating this behavior in quadrupedal
robots has been a longstanding challenge. Here, we propose a hierarchical reinforcement learning pipeline that empowers the
robots to perform aggressive locomotion through constrained obstacles–a narrow gate. The imitation learning technique is used to train the low-level policy, which mimics the behaviors of real animals and forms a set of diverse skills. The high-level controller, having an awareness of the capability of low-level skills and acquiring the gate information via
vision-based detection, determines the suitable maneuvers with collision-free trajectories to traverse it dynamically. Notably, we also verify that this framework can be extended to other highly dynamic tasks. This is one of the first works that perform autonomous and agile aerial gate traversal tasks on ground-walking
robots, extending the lifelike agility of legged
robots to match that of their biological counterparts.
Read the full abstract ▾
All authors Zeren Luo, Jiahui Zhang, Yimin Han, Ji Ma, Minghao Lu, Ioannis Havoutis, Peng Lu
Systems and Control
Harmonic Stability of Power Systems: A Control-Theoretic Definition and Assessment Criteria
N. Bhoir, A. Sarkar, J.E. Machado et al. (+1 more)
Harmonic interactions have become a defining dynamic stability phenomenon in converter-based power systems (CBPSs). However, a formalization of the notion of harmonic stability in the context of nonlinear dynamical systems is not available thus far. In this paper, we propose a definition of harmonic stability formulated as a combination of two standard stability notions, namely, bounded-input bounded-output (BIBO) and internal stability properties with respect to any nominal periodic trajectory. Moreover, we rigorously show that the local harmonic stability of any nominal periodic trajectory of nonlinear CBPSs is implied by the stability properties of its linear time-periodic (LTP) approximation. In addition, to enable computationally tractable stability assessment, we develop a framework based on harmonic state-space (HSS) representations of LTP models. In particular, we provide time-invariant linear
matrix inequality (LMI) conditions to certify harmonic stability. The proposed methodology is illustrated on a grid-following converter system, where the HSS-based analysis numerically confirms harmonic stability around the periodic operating trajectory.
Read the full abstract ▾
All authors N. Bhoir, A. Sarkar, J.E. Machado, J. Schiffer
Artificial Intelligence
ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance
Yiyang Luo, Yihang Jiang, Qijun Xie et al. (+4 more)
LLM
agents in financial
markets may cite rules yet still submit orders that violate executable constraints or misread surveillance evidence. We introduce ReguSim, a controlled financial-compliance environment, and ReguBench, a target-marked monitoring
benchmark, to separate four artifacts: stated
reasoning, attempted action, execution enforcement, and monitor evidence. In trader runs with DeepSeek V4 Pro and Gemini 3.5 Flash, visible rules reduce but do not eliminate rejected actions, and incentive or persona framing shifts behavior. A bridge study shows that trader rationales can mislead an independent monitor unless enforcement evidence is shown. In monitoring, simple structured baselines either match or exceed
prompt-only LLMs. The results frame financial compliance evaluation as an audit of rule-grounded actions and evidence use, rather than a single compliance score.
Read the full abstract ▾
All authors Yiyang Luo, Yihang Jiang, Qijun Xie, Liang Lan, Lin Willian Cong, Anyi Rao, Yunya Song
Computer Vision
Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training
Shangbo Yuan, Jie Xu, Xiaofeng Zhu et al. (+1 more)
Recently, open-vocabulary 3D object detection (3D-OVD) has gained increasing
attention for its ability to detect unseen objects in 3D scenes. Existing approaches typically adopt a two-stage pipeline that first discovers novel objects using foundation models and then trains a 3D-OVD model based on these discovered objects. Although effective, this pipeline often suffers from inaccurate localization and mismatched classification during the discovery stage, which subsequently limits the performance of the model training stage. To address these limitations, we advocate for improving both the reliability of novel object discovery and the robustness of model training, and propose an innovative framework. Specifically, for reliable discovery, our co-
distillation strategy distills high-quality novel objects by applying Hungarian matching over a comprehensive score that incorporates
geometric consistency, structural objectness, and semantic certainty. To enhance robust model training, we further propose a dual-guidance learning scheme, incorporating a scene-awareness-guided uncertainty regularization for the regression head and an LLM-guided hierarchical
alignment for the classification head, effectively mitigating the negative effects of imprecise 3D bounding boxes and semantic ambiguity. Extensive experiments on SUN RGB-D and ScanNetV2 demonstrate that our method achieves significant performance gains over state-of-the-art approaches. Code is available at https://github.com/shangboyuan/Co-3DGT
Read the full abstract ▾
All authors Shangbo Yuan, Jie Xu, Xiaofeng Zhu, Na Zhao
Computation and Language
Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction
Zhifa Geng, Subin Huang, Hao Guo et al. (+3 more)
Multimodal sentiment analysis aims to infer affective states by integrating
language, visual, and acoustic cues. However, real-world
multimodal inputs are often incomplete or corrupted, which can weaken cross-modal complementarity and introduce misleading information into downstream fusion. Existing proxy-based methods for incomplete MSA commonly rely on one-shot proxy construction to compensate for degraded
language information, but the generated proxy may be coarse or unreliable at initialization. Prematurely injecting such a proxy into
multimodal reasoning can propagate initial errors and compromise sentiment prediction. To address this limitation, we propose an iterative proxy correction framework for robust incomplete MSA. Our method constructs a
language-oriented proxy from non-
language modalities and progressively refines it under
multimodal context through gated residual correction. The corrected proxy is then adaptively fused with the observed
language representation according to an estimated
language reliability score, allowing the model to balance proxy-based compensation and trustworthy linguistic evidence. In addition, we introduce a stage-wise latent correction objective that uses the complete
language representation as a training-time semantic anchor to stabilize the proxy refinement trajectory. Extensive experiments on MOSI, MOSEI, and SIMS under diverse missing-modality settings demonstrate that the proposed framework consistently outperforms competitive baselines and achieves robust sentiment prediction under incomplete inputs.
Read the full abstract ▾
All authors Zhifa Geng, Subin Huang, Hao Guo, Junjie Chen, Sanmin Liu, Chao Kong
Robotics
PVRA: A Pointwise Key-point Voting Framework for Robotic Assembly
Kulunu Samarawickrama and Roel Pieters
Modern computer
vision has enabled partial autonomy in robotic assembly manipulation. However, performing autonomous manipulation of a progressive assembly demands a more specific set of skills, in addition to perceiving the objects. Through a comparative analysis of research in the associated domains, we deduce that object-centric perception must advance towards learning assembly dependencies to predict meaningful actionable outputs for autonomous assembly manipulation. Subsequently, we present a 3D keypoint-based modular learning framework to learn assembly dependencies to infer actionable outputs given a RGB-D input of an assembly scene. We train and evaluate our trained network on an assembly pose estimation
dataset and compare it against object-centric baselines with an augmented set of metrics for progressive assemblies.
Read the full abstract ▾