Artificial Intelligence
AgentFactory: Towards Automated Agentic System Design and Optimization
Enci Zhang, Haofeng Wang, Yuesheng Zhu et al. (+2 more)
Large
Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated
reasoning and complex task execution. However, current approaches to manually designing and optimizing agentic systems heavily rely on manual effort, limiting their adaptability and scalability. Recent work has explored the automated optimization of workflow designs. However, these approaches often overlook the crucial role of model capabilities and focus on single performance metrics, failing to address real-world deployment constraints. In this paper, we present AgentFactory, a framework that jointly optimizes both foundation models and workflow structures in agentic systems while considering multiple objectives including performance, cost, and efficiency. AgentFactory leverages advanced LLMs as optimizers to navigate the vast search space of possible configurations, employing a three-stage optimization pipeline to automatically discover effective combinations of fine-tuned models and optimized workflows. Through an iterative optimization process, our framework systematically explores and evaluates different agentic system designs, adapting to task-specific requirements while maintaining operational efficiency. We evaluate AgentFactory across eight
benchmarks spanning five domains, including general
reasoning, coding, mathematics, medicine, and finance. Our experiments demonstrate that AgentFactory consistently outperforms both manually designed methods and existing automated approaches, achieving an average improvement of 9.1% across all
benchmarks, with particularly significant gains in domain-specific tasks (19.6% on MedQA and 18.7% on FinEval). These results establish AgentFactory as a promising approach for developing more capable and efficient agentic systems through automated optimization.
Read the full abstract ▾
All authors Enci Zhang, Haofeng Wang, Yuesheng Zhu, Xiaole Cui, Guibo Luo
Machine Learning
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion
Satoshi Hayakawa
Uniform-state discrete
diffusion models update all
tokens in parallel while keeping every position revisable. Even when the commonly used top-$p$ rule leaves only one candidate at a position, that choice affects only the current reverse step and can be revised at the next sampling step. We ask what changes when selected hypotheses instead become persistent context for later predictions. We therefore propose committed reveal sampling (CRS), a training-free sampler that stores selected argmax
tokens and inserts them into subsequent model inputs. Our analysis separates persistent context from truncation. Within one reverse step, adaptive top-$p$, randomized or not, reproduces the update induced by a visible
token only when a likelihood-ratio ordering holds, while in a simple latent-mode model, keeping the selected
token visible helps later parallel predictions agree on the same sequence-level choice. Empirically, paired experiments on Duo-distilled then separate this persistent effect from single-step top-$p$ restriction and scalar temperature scaling. Under the same finalization rule, CRS without top-$p$ truncation reaches lower generative perplexity (GenPPL) than fixed $p=0.95$ and $p=0.9$ baselines across budgets of 8–64 function evaluations (NFE). At 64 NFE, the comparison at matched unigram
entropy also gives lower GenPPL for CRS, shifting the GenPPL–
entropy tradeoff under this metric. Base Duo shows the same direction in a descriptive comparison, while other diversity and continuation metrics can rank these operating points differently. A distributional distance to held-out text (SOL) under a fixed GPT-2-Large representation also decreases with persistent context at the same late top-$p$ threshold. These results identify support restriction and persistent context as distinct controls of that tradeoff.
Read the full abstract ▾
Computers and Society · Cross-listed from physics.soc-ph
Behavioral calibration of mobile-phone GPS data for population-representative analyses
Nicolò Alessandro Girardini, Unchitta Kan, Eduardo López et al. (+3 more)
Mobile phone mobility data have transformed the study of human behavior, but demographic and behavioral biases can compromise their representativeness and distort population-level inference. Existing calibration approaches primarily address demographic and geographic representativeness, leaving behavioral discrepancies largely uncorrected. Here we introduce the Behavioral Population (BePop) framework, which jointly calibrates mobility data to representative demographic and behavioral distributions using census data and time-use surveys. BePop embeds mobility sequences into behavioral profiles and estimates person-level weights that align both population composition and daily activity patterns. Across three U.S. metropolitan areas, the framework consistently improves agreement between GPS-derived mobility and representative behavioral distributions, including time allocation, activity transitions, and mobility motifs. Calibration also substantially alters downstream mobility indicators, demonstrating that behavioral biases can propagate into commonly used mobility measures. Our results establish behavioral representativeness as a critical complement to demographic calibration and provide a general framework for population-representative mobility inference.
Read the full abstract ▾
All authors Nicolò Alessandro Girardini, Unchitta Kan, Eduardo López, Bruno Lepri, Lorenzo Lucchini, Simone Centellegher
Computer Vision
ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives
Nikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos et al. (+1 more)
We introduce ViTAMINS, a method that integrates synthetic hard negatives into unsupervised
vision transformer pretraining to improve representation quality. Our approach is thoroughly benchmarked on ImageNet and transfer learning, image
retrieval, copy detection, and image,
video segmentation tasks. Notably, our proposed negatives give rise to emergent properties, where learned representations contain explicit information about the semantic content of an image and serve as excellent classifiers (up to +11.3% over baselines). ViTAMINS achieves these benefits through simple modifications to existing contrastive frameworks and outperforms competing methods while being more resource efficient, e.g., our ViT-B surpasses V-JEPA with ViT-L. Our findings motivate reconsidering contrastive learning as a simpler yet powerful alternative to dominant generative and self-
distillation approaches.
Read the full abstract ▾
All authors Nikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos, Tania Stathaki
Computers and Society
Causal Evidentiary Governance for High-Risk Machine Learning Systems
Samah Kareem and Bar{\i}ş Çeliktaş
Machine learning systems deployed for credit, hiring, and resource distribution are increasingly subject to regulatory oversight from policies such as the EU AI Act and GDPR. Current
fairness governance practices rely on observational
fairness metrics, post-hoc explainability, and immutable audit logs, but provide limited support for causal attribution and efficient evidentiary verification. We introduce Causal Evidentiary Governance (CEG), a framework in which regulated institutions commit to a versioned directed acyclic graph (DAG) that partitions causal pathways into allowable and disallowed groups. The Causal Harm Rate measures prediction variation attributable to disallowed causal pathways. Each decision is accompanied by a signed Decision-Evidence Packet (DEP), cryptographically binding the prediction to a digest of the published DAG and path-specific attributions. DEP digests can be appended to a Merkle tree to enable logarithmic-cost inclusion proofs. We validate CEG through a two-layer empirical methodology using demographic summaries from four years of PMA credit supervisory data to construct 10,000 synthetic credit applicants across four strategic DAG counterfactuals. Causal Harm Rate isolates injected causal effects more clearly than demographic parity or equalized odds. Cross-model validation and ablation studies assess robustness. Evaluation on the German Credit
dataset shows that harm associated with specific causal pathways can be substantially understated by associational
fairness metrics. Finally, a proof-of-concept implementation demonstrates operationally plausible throughput and highlights relevant performance tradeoffs.
Read the full abstract ▾
Artificial Intelligence
Data-Driven Persona-Conditioned Agents for A/B Test Simulation
Ziyad Benomar, Weronika Łajewska, Leonardo Perelli et al. (+1 more)
A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measurement. We propose a simulation framework that predicts A/B test outcomes using LLM-powered
agents conditioned on data-driven personas grounded in real user behavioral signals. Unlike prior work that relies on synthetic or rule-based personas, our
agents are constructed from anonymized behavioral data - activity patterns, engagement signals, and inferred demographics - enabling more faithful population modeling. We frame A/B test simulation as a structured question task and systematically study (i) question design formats, (ii) the impact of persona data source and domain
alignment, (iii) the trade-off between per-persona behavioral depth and population diversity, and (iv) efficient population subsampling. On a
benchmark of 40 A/B tests spanning two metric types, our best configuration achieves 0.75-0.80 directional accuracy depending on the test metric, demonstrating that data-driven personas are a viable path toward fast, low-cost experiment pre-screening.
Read the full abstract ▾
All authors Ziyad Benomar, Weronika Łajewska, Leonardo Perelli, Saab Mansour
Programming Languages
A Dynamic Intermediate Representation for Hybrid Quantum-Classical Programs
Alex Rice, Chris Heunen and Tobias Grosser
Quantum compilers typically follow the
circuit model, representing programs as fixed sequences of gates. This static view breaks down in hybrid
quantum-classical applications, where gate choices depend on runtime data or measurement results. We introduce a new Intermediate Representation (IR) that elevates gates to first-class values, enabling their dynamic creation, composition, and control. This unified representation allows classical computation to steer
quantum behaviour, capturing phenomena including
stochastic gate selection, adaptive error correction, and measurement-driven computation within a single framework. Case studies in noise modelling, randomised compilation, error correction, and measurement-based
quantum computing show that our IR expresses these programs compactly and supports optimisations that were not possible in the
circuit model. Evaluation on a
benchmark suite of hybrid
quantum-classical programs indicates that our IR represents programs compactly and facilitates compiler analysis and transformation.
Read the full abstract ▾
Cryptography and Security
MultiGait: A Multi-Sensor Multi-Perspective Multi-Session Biometric Inference Benchmark and its Dataset
Julian Todt, Felix Morsbach, Philip Dissert et al. (+1 more)
A lack of suitable
datasets has limited the research into the
privacy risks of novel smart city sensors, such as thermal cameras, depth cameras, and
lidar. Given the number of unsubstantiated
privacy claims and their potential widespread deployment into many people's everyday life, understanding the
privacy risks of these sensors – in isolation and in like-for-like comparisons – is crucial. With MultiGait, we collected the first multi-sensor, multi-perspective, multi-session gait-focused
dataset, for the corresponding, and additional more far-reaching investigations. The
dataset, validated with multiple state-of-the-art recognition systems, comprises various walking modes and annotated personal attributes for 199 individuals, to ensure the benefit for advanced studies including cross-sensor recognition and anonymization at the edge. MultiGait represents a foundation for rigorous
privacy investigations, demonstrated through an extensive identity inference
benchmark across eight sensors, four perspectives, and three recording sessions. Our
benchmark incidentally reveals that sensors often assumed to be
privacy-friendly do still entail considerable identity inference risks, while the poor cross-session generalization of existing methods underscores an important research gap.
Read the full abstract ▾
All authors Julian Todt, Felix Morsbach, Philip Dissert, Thorsten Strufe
Artificial Intelligence
Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees
Molly Wang
Recursive LLM
agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a branch receive authority to act? We distinguish sandbox spawning, in which external controls prevent the specified harm, from capability activation, in which a selected branch crosses an irreversible-action boundary. Progressive Risk Vesting (PRV) holds a trajectory-level risk budget in escrow and debits it as branches are activated. We prove an anytime harm bound for adaptively generated trees. Branch outcomes may be dependent, but each local certificate needs to remain valid conditional on the full pre-activation history, including the information used to select the request. When activation gates, branch charges, and compute constraints are held fixed, delayed vesting preserves every policy available under irrevocable spawn charging. Marginal risk estimates can still fail after branch selection. In a stylized branching model, trajectory harm changes as the authority reproduction number $\mathcal{R}_A$ crosses one. As local risk $p$ approaches zero, trajectory harm is proportional to $p$ below criticality, proportional to $\sqrt{p}$ at criticality, and retains a positive floor above it. A finite-type occupancy model yields risk and compute shadow prices. For nested fanout modes with decreasing marginal value per unit risk, these prices produce a threshold rule. Branching calculations and a split-sample experiment illustrate the results. These synthetic studies do not estimate safety in deployed
agents. The analysis suggests a design rule: search broadly in the sandbox and grant recursive authority sparingly, with an explicit risk charge.
Read the full abstract ▾
Machine Learning
The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow
Raphaël Berthier
The central flow of Cohen et al. (2025) is an empirically accurate continuous-time model of gradient descent at the edge of stability in deep learning, However, its derivation is heuristic. We propose a perturbative regime in which the central flow is the limit of gradient descent: we assume that the loss decomposes as $f = g + \varepsilon h$; in the limit $\varepsilon \to 0$, the dynamics of gradient descent with learning rate $\eta$ converge to the gradient flow of $h$ constrained to the minimizers of $g$ of sharpness at most $2/\eta$. Our approach is formal rather than rigorous; it treats gradient descent as a singularly perturbed dynamical system in $\varepsilon$. Three timescales emerge: a fast timescale of oscillations along the sharpest direction, an intermediate timescale of the self-stabilization mechanism, and a slow timescale of the dynamics along the minimizers of $g$-the central flow. Using the method of multiple scales, a classical formal method from singular perturbation theory, we derive the expansion of the dynamics in $\varepsilon$: the central flow emerges as the leading-order term in the expansion, while the self-stabilization mechanism appears in the next-order term. We study this mechanism beyond previous analyses: with a single
eigenvalue at the edge of stability, we compute the slow drift of the energy of the fluctuations; with several
eigenvalues at the edge of stability, we derive the self-stabilization system and explain why fluctuations persist.
Read the full abstract ▾
Logic in Computer Science
On Synthesis of Metric Interval Temporal Logics
Hsi-Ming Ho, Shankaranarayanan Krishna and Khushraj Madnani
Automated mining of formal specifications is vital for verifying real-time systems. However, existing passive learning approaches remain restricted to deterministic specifications or limited fragments of Timed Regular Expressions (TRE). To our knowledge, this paper presents the first framework to tackle precise passive learning for an expressive timed logic, Metric Interval Temporal Logic (MITL) without relying on predefined templates or restricted logic fragments. Our approach formally reduces the timed learning problem into a scalable untimed one. By identifying quantitative timing differences between positive and negative traces, we synthesise precise timed constraints and inject them as new Boolean atomic propositions. This embeds timing into the alphabet, delegating the complex formula evaluation to highly optimised, off-the-shelf untimed LTL tools. Crucially, our framework is complete, guaranteeing a separating specification can always be found. We evaluate our implementation across several
benchmarks, demonstrating the effectiveness of our approach.
Read the full abstract ▾
Numerical Analysis
Randomized inexact block triangular preconditioners for double saddle-point systems in PDE-constrained optimization
Siqi Liang and Na Huang
We develop a new class of inexact block triangular preconditioners for double saddle-point systems arising from PDE-constrained optimization. The proposed preconditioners are constructed through
matrix factorization techniques while preserving the inherent block structure of the original systems. A comprehensive spectral analysis of the preconditioned
matrices is provided, yielding explicit bounds for both real and nonreal
eigenvalues. To enable efficient construction of the inexact preconditioners, randomized strategies are introduced to select the required subblocks. We establish high-probability bounds for the expected approximation error, with the error estimates explicitly characterized in terms of the
eigenvalues of the associated
matrices. Numerical experiments demonstrate the effectiveness, robustness, and scalability of the proposed preconditioners, and validate the efficiency of the randomized construction strategies.
Read the full abstract ▾
Information Retrieval
Web Price Extraction: State of the Art and an Adaptive Browserless Implementation
Evgeniia Kositsyna and Jorge Lloret-Gazo
Price extraction from websites is a key task for
market monitoring, price comparison, and business analytics in e-commerce. Existing approaches can be broadly divided into four groups, and understanding their trade-offs in accuracy and scalability is essential for selecting suitable extraction strategies. Classical methods rely on manually written wrappers and rule induction from labeled pages, offering high accuracy but adapting poorly to structural changes and requiring considerable maintenance effort. Browser-based methods, using tools such as Selenium and Puppeteer, handle dynamic JavaScript content but consume large computational resources and scale poorly. Browserless approaches retrieve HTML directly via HTTP requests, offering significant gains in speed and cost, but rely on rules calibrated for specific sites. Methods based on machine learning and large
language models offer adaptability but require training data and substantial computation. Our main contribution is an adaptive browserless price extraction system that improves robustness to structural differences between websites. We implemented a baseline architecture combining HTML page fragmentation with syntactic, semantic, and frequency rules, and extended it in two ways: a
Bayesian approach that dynamically updates rule weights, and a genetic
algorithm that optimizes the system's global parameters. This hybrid scheme increased precision from 77.2% to 87.3% and reduced average per-page processing time by approximately 14% relative to the baseline, confirming it as a competitive alternative to manually tuned browserless solutions and to more resource-intensive browser- or LLM-based methods, offering high extraction accuracy at low computational cost.
Read the full abstract ▾
Human-Computer Interaction
Beyond Technological Solutionism: Rethinking XR in Healthcare
Md Haseen Akhtar, Cecilia Landa-Avila, Shital Desai et al. (+5 more)
The healthcare industry's enthusiastic adoption of Extended Reality (XR) technologies obscures a concerning reality: we were building increasingly sophisticated ways to perpetuate fundamentally broken healthcare systems. Through three deeply personal narratives - a rural patient cut off from care infrastructure, an urban professional navigating fragmented services, and a first-generation immigrant confronting cultural barriers - this provocation paper exposes how our obsession with technological innovation often worsens rather than resolves healthcare disparities. By applying the SEIPS 3.0 model to examine diabetes-CVD care coordination, we identify an "innovation paradox" where advanced technology creates new barriers to effective care. Our care interdependencies framework reveals that healthcare outcomes are shaped primarily by human relationships (50-60%), organizational coordination (25-30%), and sociocultural factors (15-20%), not technological sophistication. This research challenges the HCI community to confront its role in perpetuating healthcare inequities, demands a fundamental rethinking and proposes a new framework for healthcare innovation that prioritizes human relationships over technical capability, systemic change over feature sets, and actual care delivery over technological ambition. For healthcare providers, technology developers, and policymakers, our findings suggest that effective care coordination requires us to step back from our techno-solutionist mindset and engage
Read the full abstract ▾
All authors Md Haseen Akhtar, Cecilia Landa-Avila, Shital Desai, Claire Warden, Andrew Morris, Mark Anderson, Thomas Cochrane, Janakarajan Ramkumar
Computer Vision
Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set
Ruslan Rozumnyi, Matěj Suchánek, Tomáš Vojíř et al. (+2 more)
Out-of-distribution (OOD) detection predicts whether a test image belongs to none of the predefined classes. To evaluate this task,
benchmarks need images from outside the in-distribution (ID) data; typically, these are defined or collected in an ad hoc fashion. Since no ground truth is perfect, ID-labeled
datasets themselves contain a natural source of OOD images. We exploit such annotation errors and present Fi-ImageNet-1k, an OOD
dataset built from ImageNet-1k validation images that the recent ReImageNet reannotation effort assigned to no ImageNet-1k class. Each image was examined by expert human annotators supported by evidence from MLLMs, VLMs, and reverse image search, comparing it against all visually similar ID classes. We keep only images that could be assigned a specific class outside the ImageNet-1k label space. The resulting Fi-ImageNet-1k, with 655 images from 522 classes, is substantially more challenging than any commonly used OOD
dataset. No evaluated combination of classifier and OOD detector achieves a false positive rate below 51% at 95% true positive rate (FPR@95). Compared to the recent NINCO, our
dataset is 3.8x more challenging in the FPR@95 metric for state-of-the-art supervised OOD detection methods.
Read the full abstract ▾
All authors Ruslan Rozumnyi, Matěj Suchánek, Tomáš Vojíř, Klára Janoušková, Jiří Matas
Distributed Computing
MakoXC: Rearchitecting DFT Exchange-Correlation with Matrix-Aligned and Knowledge-Organized Sparsity
Haozhi Han, Fusong Ju, Jing Bai et al. (+8 more)
Density Functional Theory (DFT) is indispensable for materials science and drug discovery, yet the exchange–correlation (XC) evaluation remains a major bottleneck due to its cubic scaling. Although linear-scaling methods exploit electronic nearsightedness to reduce asymptotic complexity, they produce irregular sparse workloads that hide implicit sparsity and prevent efficient use of modern AI accelerators. We present MakoXC, a modular
matrix-aligned XC evaluation engine that rearchitects nearsightedness-induced sparsity into regular, accelerator-friendly computations. MakoXC co-designs three key techniques: (1)
Matrix-Aligned
Cells reorganize nearsightedness-induced interactions into dense, accelerator-aligned data clusters; (2) Sparsity-Guided Activation translates deeper implicit sparsity into numerically correct structured execution for practical linear scaling; and (3) Kernel-Fused Pipeline consolidates fragmented workloads into a unified, compute-intensive execution path that fully unleashes accelerator throughput. Extensive evaluations show that MakoXC achieves average speedups of 67.8$\times$ speedup over standard XC evaluation and 4.7$\times$ over state-of-the-art linear-scaling methods. When integrated into a production-grade commercial DFT package, MakoXC scales XC evaluation to ubiquitin (1,231 atoms, def2-SVP) on 64 GPUs, enabling the end-to-end DFT calculation to complete in under five minutes. By restructuring XC evaluation into a unified, structured computation, MakoXC demonstrates how scientific workloads can achieve genuine low complexity while maximizing parallel efficiency on AI accelerators.
Read the full abstract ▾
All authors Haozhi Han, Fusong Ju, Jing Bai, Ruge Zhang, Xiang Zhao, Liang Yuan, Yunquan Zhang, Ting Cao, Liu Yunxin, Yifeng Chen, Kun Li
Computation and Language
PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition
Ziyan Gan, Fangxin Liu, Chenyang Guan et al. (+10 more)
Mixture-of-Experts (MoE) architectures scale Large
Language Model (LLM) capacity efficiently by activating a sparse subset of experts per
token. However, modern MoE inference remains heavily constrained by the rigid, whole-expert abstraction. Existing frameworks manage, schedule, or prune experts as atomic execution units, which fixes the optimization boundary too early and leaves fine-grained intra-expert computational redundancy underexplored. In this work, we present PCoMoE, a path-compositional execution framework that shifts MoE inference from coarse-grained expert selection to fine-grained path composition. PCoMoE incorporates a path-level formulation of expert computation, a compatibility-aware layer-wise
pruning strategy to suppress low-value path combinations, and a hardware-friendly execution engine to exploit reusable sub-expert structures under strictly bounded overheads. Experimental results demonstrate that PCoMoE achieves up to a 1.31x end-to-end inference speedup while enhancing model accuracy by 10%. The code is available at https://github.com/gzyyy0/PCoMoE
Read the full abstract ▾
All authors Ziyan Gan, Fangxin Liu, Chenyang Guan, Junjie Wang, Ning Yang, Haomin Li, Xiang Li, Siran Yang, Jiamang Wang, Lin Qu, Zongwu Wang, Li Jiang, Haibing Guan
Cryptography and Security
AKRASIA: Stealthy Backdoor Attack on Reasoning-based Code LLMs
Chua Jin Chou, Sarang Nambiar, Murali Srinivasan et al. (+1 more)
We present AKRASIA, a stealthy, inference-time
backdoor attack against
reasoning-based Code LLMs. AKRASIA aims to achieve a
backdoor target (e.g., malicious code execution) in
reasoning LLMs while evading automated defenses and human inspection. To achieve this, AKRASIA probes the victim LLM to construct a code-level
backdoor trigger. It then employs in-context learning for
backdoor learning, and model unfaithfulness to conceal the
backdoor trigger, and generate plausible
reasoning. We evaluate AKRASIA using four
backdoor targets six (6)
reasoning LLMs, three coding tasks/
datasets and three defense methods. AKRASIA has up to 99.34% average attack success rate on SOTA LLMs and mantains up to 97.23% average accuracy. AKRASIA evades the SOTA defense, retaining up to 98.82% average ASR in most (14/18) defense settings. It evades human inspection, successfully hiding the
backdoor trigger and
reasoning steps in up to 80% of settings. Our findings motivate the need to defend LLMs against
reasoning backdoors.
Read the full abstract ▾
All authors Chua Jin Chou, Sarang Nambiar, Murali Srinivasan, Ezekiel Soremekun
Data Structures and Algorithms
Kernelization of 2-Club Cluster Edge Deletion on Interval Graphs
Ajinkya Gaikwad
The \emph{$s$-Club Cluster Edge Deletion} problem asks whether, given a graph $G$ and an integer $k$, one can delete at most $k$ edges so that every remaining connected component has diameter at most~$s$. This generalizes the classical Cluster Edge Deletion problem by permitting components of bounded diameter instead of requiring cliques. On general graphs, $2$-Club Cluster Edge Deletion is known to be fixed-parameter tractable when parameterized by $k$, but it remains open whether it admits a
polynomial kernel, as posed in~\cite{ABUKHZAM2023113864}. Motivated by this question, we study the problem on interval graphs and obtain a
polynomial vertex kernel of size $\mathcal{O}(k^{5})$. As a complementary result, we also show that the \emph{$s$-Club Cluster Edge Deletion} problem is
polynomial time solvable on unit interval graphs. We also show that $2$-Club Cluster Edge Deletion is NP-hard even on split graphs.
Read the full abstract ▾
Computer Vision · Cross-listed from physics.med-ph
PyDoseRT Proton: A GPU Pencil-Beam Engine with a Convolutional Residual-Correction Network for Fast Proton Dose Calculation
Lukas Zimmermann, Hermann Fuchs, Attila Simkó et al. (+1 more)
Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction network (RepVGG-U-Net). We addressed the DoseRAD2026
proton dose-prediction task with PyDoseRT
Proton, a GPU-accelerated engine implemented in PyTorch and augmented by a learned residual toward Monte Carlo (MC) accuracy. A double-Gaussian PB kernel was calibrated to GATE/Geant4 integrated depth doses in water in two stages: a classical per-energy curve fit, then a gradient-based fit of the full 3-D dose through the PyTorch physics engine as it retains a differentiable execution path for gradient-based optimization of dose-dependent objectives. The engine computes each beamlet on a beam's-eye-view (BEV)
lattice with variance-preserving Gaussian splitting, an analytic
nuclear halo, and a
Fermi-Eyges heterogeneity term, then rotates the result into the patient frame. Additionally, a compact residual U-Net predicts an additive correction in BEV space. It is conditioned on voxelwise material-label
embeddings, a discrete energy
embedding and spot size. The same model was used for all anatomical sites (thoracic and abdominal). It was trained with a patient-space L1 objective emphasizing the scored high-dose region and multi-scale BEV deep supervision. The submitted CT configuration obtained preliminary-test beamlet MAE 0.0066, image-z IDD distance 0.0025, plan MAE 0.0049, 98.30% gamma pass rate (1%/1 mm), and DVH error 0.460.
Read the full abstract ▾
All authors Lukas Zimmermann, Hermann Fuchs, Attila Simkó, Gerd Heilemann
Computation and Language
Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech
Che Hyun Lee, Sangkwon Park, Donghun Kang et al. (+4 more)
Current
speech synthesis struggles with code-switching, which mixes a foreign
language phrase into a primary
language utterance, causing the phrase to be spoken with the primary
language's accent rather than its native one. We propose Phrase-Localized
Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-
speech. LCG replaces the single
language guidance applied across the whole utterance with a separate guidance for each region, so each part is guided by its own
language. To choose where to apply this localized guidance, we propose a self-
attention probing technique that finds the phrase boundaries without external
alignments. Together, these components generate
speech in which each region carries the accent of its own
language, requiring no fine-tuning or auxiliary models. Across diverse
language pairs, LCG robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and naturalness.
Read the full abstract ▾
All authors Che Hyun Lee, Sangkwon Park, Donghun Kang, Dongwook Lee, Youngho Cho, Heeseung Kim, Sungroh Yoon
Social and Information Networks
A Network Science Perspective on Evaluating Deep Graph Generative Models
Tianrui Mao, Abele Malan, Megha Khosla et al. (+2 more)
Traditional network models from network science, such as the Erdos-Renyi and configuration models, generate random networks that reproduce few selected topological properties observed in real-world networks. Deep graph generative models emerge as a data-driven approach, leveraging deep neural network architectures to learn complex structural distributions directly from real-world networks to generate more realistic synthetic networks. Because real social contact networks cannot be shared due to
privacy risks, synthetic networks serve as an alternative for developing and evaluating epidemic mitigation strategies. In this work, we evaluate deep graph generative models as well as the configuration from a network science perspective by assessing both the topological similarity between generated and real-world networks and their utility in identifying effective node immunization strategies to sup- press epidemic/misinformation spreading. It is found that two deep graph generative models produce synthetic networks that closely resemble the structural properties of real-world networks, enabling them to identify effective immunization strategies.
Read the full abstract ▾
All authors Tianrui Mao, Abele Malan, Megha Khosla, Lydia Chen, Huijuan Wang
Computer Vision
Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints
Vedat Can Dilaver and Benjamin S. Riggan
Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment (gallery) imagery and the scarcity of training data for large-scale models. While recent face recognition (FR) models perform well on high-quality (HQ) imagery, their accuracy drops significantly on LQ images with extremely low signal-to-noise ratio (SNR). Moreover, fine-tuning HQ-pretrained models on LQ data often improves LQ recognition at the expense of HQ generalization. This trade-off becomes more pronounced in modern evaluation settings spanning multiple
datasets with varying image quality levels. To address these limitations, we propose a unified framework that combines three main components: (1) Local Probability Margin (LPM), which estimates per-sample difficulty directly from the model's discriminative landscape; (2) Nested
Attention Module (NAM), a new low-rank adapter module that embeds a self-
attention mechanism within selected
transformer layers; and (3) Quality Gating Protocol (QGP), where an off-the-shelf image quality
estimator modulates the adapter contribution at test time, enabling a single model to handle the full quality spectrum without sacrificing HQ performance. Experiments on surveillance (TinyFace, SurvFace) and standard (IJB-B, IJB-C) face recognition
benchmarks demonstrate consistent gains in both identification and verification. Code and models will be released at github.com/candllq/nam.
Read the full abstract ▾
Numerical Analysis
OptiXDE: A fast optical-inspired solver for differential equations
Yang Yang, Mingjiao Yan and Zongliang Zhang
OptiXDE is a
matrix-free spectral operator framework for differential equations on uniform grids and embedded domains. Inspired by angular-spectrum propagation in
Fourier optics, it maps transform-diagonal spatial operators to analytical modal multipliers and composes them with physical-space operators for nonlinearities, geometry and boundary enforcement. A common transform–operator–inverse-transform backbone is demonstrated across transient
diffusion, periodic and embedded-domain Poisson problems, the cubic nonlinear Schr"odinger equation, viscous Burgers dynamics, the two-dimensional Allen–Cahn equation and incompressible flows from the Taylor–Green
vortex to embedded-cylinder
vortex shedding. Transform-compatible linear problems are recovered near the floating-point limit, whereas errors on the singular L-shaped domain remain localized near the re-entrant corner and regularized interface. Nonlinear
benchmarks recover second-order temporal convergence and the expected conservative or dissipative behavior, while incompressibility remains near round-off level during long-time
vortex shedding. The
matrix-free updates require \(\mathcal{O}(N\log N)\) work and \(\mathcal{O}(N)\)
memory. Device-resident transform workloads reach \(94.9\times\) GPU acceleration, and the complete embedded-cylinder solver achieves a \(42.1\times\) CPU–GPU speedup under matched numerical settings. These results establish OptiXDE as a deterministic and extensible operator-centric framework for structured and embedded-domain differential equations.
Read the full abstract ▾
Artificial Intelligence
Figures as Programs: Recursive Generation of Editable Scientific Figures
Yepeng Liu, Dasen Dai, Chengzhi Liu et al. (+7 more)
Scientific methodology figures are essential for communicating complex methods clearly, yet creating them remains labor-intensive and typically requires multiple rounds of refinement. Recent image-generation models can synthesize visually appealing raster figures, but producing a human-satisfactory result in a single generation step remains difficult. Moreover, precise edits to raster figures are challenging for both humans and models. We formulate scientific figure generation as recursive SVG program construction and propose FigTree, a multi-
agent system that automatically transforms a scientific paper into a structured vector figure. FigTree grounds figure content in the source paper, decomposes a figure into a hierarchy of local regions, generates each region as a short SVG program, and assembles the resulting fragments. A render-critic refinement loop jointly inspects the rendered figure and its underlying program, enabling visual defects to be traced to specific statements and accurately repaired. We conduct extensive evaluations of FigTree on figure quality and editability, showing that FigTree produces high-quality figures, while also enabling more effective editing than existing raster-based methods.
Read the full abstract ▾
All authors Yepeng Liu, Dasen Dai, Chengzhi Liu, Yiren Song, Hai Ci, Yu Zhang, Qi Zhang, Mike Zheng Shou, Xin Eric Wang, Yuheng Bu
Computer Vision
Shiyu Li, Zi-Yuan Hu, Shijia Huang et al. (+3 more)
Despite their strong
multimodal understanding ability,
multimodal large
language models (MLLMs) incur substantial computational overhead when processing long visual
token sequences. To reduce inference costs, recent studies have explored visual
token pruning through
vision-centric or text-guided strategies. However, these methods often overlook high-norm outlier
tokens, i.e.,
tokens with abnormally large feature norms, leading to suboptimal
pruning decisions. In this work, we show that such high-norm outlier
tokens are highly redundant in both feature and spatial dimensions, yet are often mistakenly preserved as informative cues by existing methods. Motivated by this observation, we propose SinkPruner, a training-free visual
token pruning framework for efficient MLLM inference. SinkPruner follows a coarse-to-fine design with two key modules: a visual sanitizer that filters high-norm redundancies and alleviates
attention sink and
attention dispersion, and a text-guided pruner that further retains
tokens semantically aligned with the text query. Extensive experiments on twelve image-
language and four
video-
language benchmarks demonstrate the effectiveness, efficiency, and generalizability of our framework. Notably, SinkPruner preserves 96.5% (91.8%) of the original performance of LLaVA-1.5 (Qwen2.5-VL) under an 89%
token reduction. Experiments further indicate that our visual sanitizer exhibits promising transferability in enhancing the performance of existing
pruning methods. Our code is available at https://github.com/LaVi-Lab/SinkPruner.
Read the full abstract ▾
All authors Shiyu Li, Zi-Yuan Hu, Shijia Huang, Yanyang Li, Yiwu Zhong, Liwei Wang
Computation and Language
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close
Rania Elbadry, Ahmed Heakl, Saeed Almheiri et al. (+12 more)
When a question has valid answers under different normative frameworks, a
language model must decide which framework to use and whether it can answer correctly within it. We call this setting normative pluralism and study it in Islamic finance using a four-choice taxonomy that separates framework selection from within-framework correctness. This separation reveals the stereotype trap: a cultural cue steers a model toward one framework, but the model selects an incorrect answer within that framework. Across twelve models, two
languages, and fifty demographic signals, cultural cues change framework selection and reveal substantial differences in accuracy, especially among non-frontier models. Under the strongest signal, large open-weight models select the Islamic framework 97% of the time. A two-choice evaluation would report near-perfect
alignment, although 57–66% of those selections are incorrect. These findings motivate, but do not directly test, the competence-conditioned routing hypothesis: models may favor frameworks where they are more accurate, while cultural cues may expose framework-specific competence gaps.
Read the full abstract ▾
All authors Rania Elbadry, Ahmed Heakl, Saeed Almheiri, Fan Zhang, Muhra AlMahri, Xueqing Peng, Mohsinul Kabir, Shuyao Wang, Yi Han, Saadeldine Eletter, Duzhen Zhang, Preslav Nakov, Yuxia Wang, Fajri Koto, Zhuohan Xie
Computation and Language
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
Michele Ciletti
Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern
languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source
language (Navigli, 2026). These assumptions break down for most historical and low-resource
languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary
retrieval pipeline that links
tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-
language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid
retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-
embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE
dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings.
Read the full abstract ▾
Computer Vision
Does This Moment Justify the Recommendation? Counterfactual Behavior-Grounded Evidence Retrieval for Personalized Video Recommendation
Xin Liu
Personalized
video recommendation predicts user preference at the
video level, while temporal
video grounding localizes query-relevant moments. However, strong localization does not establish whether the retrieved moment constitutes valid evidence for recommending the
video to a particular user. We study counterfactual behavior-grounded evidence
retrieval, which separates where personalized evidence occurs from whether such evidence exists and evaluates whether model predictions respond consistently when that evidence is replaced. We introduce CBGER-10K, containing 5,000 controlled factual–counterfactual pairs for 3,026 users, where each pair replaces only the focal behavior-supported segment while preserving the user, temporal position, and hard distractors. We further propose CBGER, a compact framework that decouples segment-level localization from
video-level evidence estimation and learns both through structured counterfactual supervision. CBGER achieves $0.4432$ MRR, $0.6977$ Pair Accuracy, and $0.6987$ Intervention Consistency across five adapted personalized-highlight and temporal-grounding baselines. Notably, compared with QD-DETR, its MRR improvement is not statistically significant, while Pair Accuracy improves by $11.03$ points. These results show that accurate temporal localization does not necessarily imply reliable personalized evidence existence, motivating explicit evaluation of Whether alongside Where.
Read the full abstract ▾
Computer Vision
CQF-HMR: Continuous Quaternion Flows for Probabilistic 3D Human Mesh Recovery from a Single Image
Cuong Le, Bao-Long Tran, Pavlo Melnyk et al. (+3 more)
Recovering 3D digital humans from a single 2D image is an ill-posed computer
vision problem due to the loss of depth information. Probabilistic 3D human pose estimation compensates for this by estimating a set of 3D hypotheses from a prior distribution via generative models. However, most prior work focuses only on 3D keypoints, which often leads to implausible poses that are difficult to apply to downstream tasks, e.g. animation or digital humans. SMPL-based methods are more scalable thanks to the explicit body priors, but it requires more complex modeling of the generation process due to the non-additive nature of the joint rotations. In this work, we propose a novel approach for probabilistic 3D humans using quaternion-constrained continuous normalizing flows conditioned on 2D pose estimations. Our proposed quaternion flows show significant advantages over approaches using other rotation representations. Experiments demonstrate state-of-the-art results of our method on Human3.6M, particularly in ambiguous settings, and comparable pose estimation accuracy on challenging 3DPW and EMDB
benchmarks.
Read the full abstract ▾
All authors Cuong Le, Bao-Long Tran, Pavlo Melnyk, Tahereh Dehdarirad, Bastian Wandt, Mårten Wadenbäck