Computer Vision
UniCon-Former: Unified Convolution Transformer is All You Need for Hand Gesture Recognition
Mallika Garg, Debashis Ghosh and Pyari Mohan Pradhan
Convolutional Neural Networks (CNNs) capture local features efficiently but struggle with global context due to their limited receptive field. On the other hand,
transformers effectively capture global dependencies through self-
attention but suffer from high redundancy and computational costs. Thus, to leverage the advantages of both CNNs and
transformers, we propose a unified model (UniCon-Former) that aims to provide robust and efficient performance on dynamic hand gesture recognition. The unified approach helps the model to learn both local and global features. At the beginning of each
transformer stage, the convolution projections help in decreasing the dimension of the input vectors of the
transformer block. This creates a pyramidal structure at each
transformer stage. These features enable the UniCon-Former to reduce resource usage than vanilla
transformers, making it flexible for learning multi-scale and high-resolution features, which is required in hand gesture recognition. We have performed experiments with NVGesture and Briareo
datasets and achieved state-of-the-art results with fewer parameters and MACs.
Read the full abstract ▾
Human-Computer Interaction
CogChat: Knowledge Graph-Augmented Conversational AI with Heterogeneous Graph Transformer for Cognitive Grounding in Design Generation
Jiin Choi and Kyung Hoon Hyun
LLM-based chat systems have become valuable tools for design practice, enabling rapid ideation and flexible task support. Yet these systems process designer utterances as generic sequences, maintaining context through recency rather than through any model of how the speaker organizes knowledge. In design conversation, this gap compounds as relational context decays between turns, identical words go unresolved across designers, and the conversation loops or restarts rather than deepens. We present CogChat, a real-time chat framework that grounds conversational AI in a personal heterogeneous knowledge graph constructed from each designer's input. The system extracts typed entities and relations into a heterogeneous graph, then applies a HGT (Heterogeneous Graph
Transformer) to select structurally relevant nodes for response generation and to generate both intentional and exploratory probing questions. Technical evaluation shows that HGT-based entity selection outperforms both ungrounded LLM interaction and naive KG augmentation, which introduces noise that degrades response quality. A within-subjects study with nine professional designers indicates that grounding conversation in a relationally structured, designer-specific semantic context improves context retention, personalized intent interpretation, and conversational depth while reducing cognitive load. These findings suggest that structuring a designer's expressed concepts and relations as a dynamic knowledge graph can preserve relational context that fades across turns, pointing toward a graph-grounded approach to long-term context management in LLM-based interaction.
Read the full abstract ▾
Machine Learning
History-informed Lagrangian Neural Networks
Tianshuo Zhang, Xianglei Xing, Wenzhe Zhai et al. (+2 more)
Forecasting the long-horizon
evolution of mechanical systems from position-only observations is a pivotal yet difficult task, as hidden velocities and trajectory-specific physical properties must be inferred simultaneously. Although physics-guided neural networks like Lagrangian Neural Networks (LNNs) guarantee physical plausibility, they generally require complete state inputs and lack adaptability to changing system parameters. To break these limitations, we introduce History-informed Lagrangian Neural Networks (HiLNN). Grounded in the insight that temporal position sequences implicitly encode underlying dynamics, HiLNN employs a recurrent encoder to extract a latent context from history. This context not only reconstructs the unobserved initial velocity but also adaptively modulates the mass
matrix, potential energy, and damping coefficients of a structured Lagrangian system. By leveraging a differentiable RK4 rollout scheme, the entire pipeline is optimized end-to-end under multi-step trajectory supervision and energy-consistency regularization. Empirical evaluations across conservative, dissipative, and heterogeneous variable-parameter systems show that HiLNN delivers superior long-term prediction accuracy and maintains precise energy profiles compared to state-of-the-art baselines. The source code is publicly available at https://github.com/yingtian22/History-informed-LNN.
Read the full abstract ▾
All authors Tianshuo Zhang, Xianglei Xing, Wenzhe Zhai, Jia Gao, He Cao
Machine Learning
TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures
Orkun Irsoy, Leman Akoglu and Osman Yagan
Networked systems, from power grids to traffic networks and cloud clusters, carry loads across nodes with limited capacity. A node whose load exceeds its capacity fails and sheds its load onto its neighbors, which can trigger a system-wide cascade. We study how to allocate a fixed capacity budget across nodes to resist these cascades under local load redistribution. The problem is difficult because no optimal allocation is known, and the fail-or-survive objective is non-differentiable and piecewise constant, so exact and gradient-based optimization methods do not directly apply. We introduce TANGCO (
Topology-Aware Neural Graph-Guided Capacity Optimization), which uses a graph neural network policy trained through the cascade simulator with policy-gradient learning and a heuristic anchor. We evaluate TANGCO on five synthetic graph families and five real networks spanning power, road, air, and Internet
topologies. The learned policy improves on the best of four hand-designed heuristics in all 450 synthetic instances and in 40 of 45 real-network conditions, with robustness gains ranging from 1.6% to 246%. The learned policies transfer to unseen graphs within a family and partially across related
topologies, and TANGCO$^{pre}$, pre-trained on synthetic graphs, matches per-network training on unseen real networks. Training scales near-linearly with graph size, and TANGCO$^{pre}$ allocates on a new network with no per-target training, matching the deployment cost of a hand-designed heuristic. Free-vector variants without the GNN, stay close to the heuristics, so the graph representation carries the gain beyond numerical search. Finally, analysis of the learned allocations identifies when local risk is sufficient, leads to an improved closed-form heuristic, and reveals the regimes where a
topology-aware learned policy remains necessary.
Read the full abstract ▾
Programming Languages
Stream-based Online and Offline Monitoring under Measurement Noise
Bernd Finkbeiner, Martin Fränzle, Florian Kohn et al. (+1 more)
Stream-based monitoring is a runtime verification approach for cyber-physical systems that translates streams of input data, such as sensor readings, into streams of aggregate statistics and verdicts about the safety of the system. It is usually assumed that the values on the input streams represent fully accurate measurements of the physical world. In reality, however, physical sensors are prone to measurement noise and errors. These errors are further amplified by the processing and aggregation steps within the monitor. This paper introduces RLola, a robust extension of the stream-based specification
language Lola. RLola incorporates the concept of slack variables, which symbolically represent measurement noise while avoiding the aliasing problem of interval arithmetic. We present
algorithms for both online and offline monitoring of RLola specifications. Since monitoring RLola specifications may require unbounded
memory in general, we identify a rich fragment of RLola that can be automatically translated into monitors with guaranteed constant
memory usage for online monitoring. An online RLola monitor observes a live system and provides real-time feedback on the current status of specified assertions. A satisfiability-modulo-theories-based offline
algorithm analyzes complete system traces and determines whether a hypothetical ground-truth trace exists that satisfies all assertions at all time points. The offline
algorithm can therefore detect violations that the online
algorithm may miss. We implement these
algorithms in the existing RTLola framework and evaluate their precision and running time based on a comprehensive example.
Read the full abstract ▾
All authors Bernd Finkbeiner, Martin Fränzle, Florian Kohn, Paul Kröger
Computer Vision
NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
Yuheng Huang, Jianlang Chen, Jiayang Song et al. (+6 more)
Long-form
video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that may remain implicit. However, existing
benchmarks rarely evaluate these capabilities jointly, particularly in high-context, non-English media. To address this gap, we introduce NARU, a
benchmark designed to evaluate Narrative
evolution and
Reasoning on cultural Understanding in Japanese long-form
video. NARU consists of 1,481 questions grounded in 155
videos totaling 146.8 hours, spanning four narrative and five cultural dimensions. To construct the
benchmark at this scale, we propose a hierarchical
memory-based annotation pipeline that transforms raw
video into structured event, narrative, and cultural annotations, then generates questions via task-oriented synthesis and iterative shortcut removal. The construction process includes two native-speaker verification stages involving 68 annotators. Evaluations across eight model configurations reveal substantial limitations in both long-range narrative integration and culturally grounded
reasoning. By exposing these persistent gaps, NARU offers a systematic testing ground for developing MLLMs capable of reliably interpreting long-form, high-context
video.
Read the full abstract ▾
All authors Yuheng Huang, Jianlang Chen, Jiayang Song, Hua Qi, Aza Kai, Vincent Markert, Edison Marrese-Taylor, Jianjun Zhao, Lei Ma
Machine Learning · Cross-listed from stat.ME
Chance-constrained selection of sequential intervention strategies from counterfactual estimates
Minkyoung Kim and Beakcheol Jang
Many operational decisions are sequences of interventions under a cumulative resource limit, such as a maintenance schedule within a crew-hour budget. Choosing among them calls for the outcome and the cumulative cost each would produce, counterfactual quantities identified from observational data. Two strategies with the same expected cost can exceed the budget at very different rates, so constraining the mean does not bound how often an overrun occurs. Prior two-step architectures, recently extended to continuous doses, constrain the mean cost rather than its tail and allocate at a single decision point. Methods that do bound a cost tail take its distribution from a specified model rather than identifying it from data. We present a predict-then-optimize framework. In the prediction step, any
estimator returning an outcome value and a cost distribution supplies what the decision rule consumes, so the predictor is interchangeable. In the optimization step, a chance-constrained selection over a finite candidate set bounds the probability that the cumulative cost exceeds the budget. That tail does not decompose across stages, so each strategy is scored whole. Sweeping the tolerated violation probability traces a safety-utility frontier, and distribution-free finite-sample bounds cover violation and outcome shortfall. Four of five environments, spanning clinical treatment and equipment maintenance, supply exact counterfactual ground truth; the fifth carries real outcomes from a digital-health micro-randomized trial. Across them, the rule holds the budget where a point-estimate rule overruns it, at an outcome cost the frontier makes explicit. All code is available at https://github.com/mfriendly/counterfactual-chance-selection
Read the full abstract ▾
Computer Vision
Jiazi Bu, Pengyang Ling, Yujie Zhou et al. (+10 more)
Text-Image-to-
Video (TI2V) models are an emerging unified architecture, where a single model simultaneously supports text-to-
video (T2V) and image-to-
video (I2V) generation. Given a high-quality first frame or a detailed textual
prompt, TI2V models unlock substantially better visual quality than their T2V mode, raising a natural question: can the capability elicited by such privileged conditions be internalized into the model's own base generation ability? A common approach toward this goal is model self-
distillation. However, the most straightforward solution, supervised fine-tuning, follows an off-policy strategy: its supervision is confined to teacher-generated endpoints from a fixed offline distribution rather than student-visited states, lacking precise correction tailored to the evolving policy. Recent on-policy
distillation methods instead suffer from condition-state mismatch, where supervision is steered toward the given first frame instead of the student's actual content, misleading the correction. To achieve self-
distillation that absorbs the teacher's privileged prior while retaining precise policy correction, in this work, we propose Hybrid-Policy Self-
Distillation (HPSD), a novel self-
distillation framework where a single TI2V model acts as both teacher and student under different conditions: the teacher operates in TI2V mode with a high-quality first frame and an enhanced
prompt, while the student runs in the base T2V mode with only the vanilla
prompt. Specifically, the student inherits off-policy teacher trajectory points as anchors, locally refines them toward its own policy, and finally receives velocity-level supervision on these self-generated roll-outs. Extensive experiments demonstrate that HPSD significantly improves T2V performance while also delivering notable TI2V gains, effectively strengthening the model's base generation ability.
Read the full abstract ▾
All authors Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Xuanlang Dai, Shengyuan Ding, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Dahua Lin, Xingang Pan
Machine Learning · Cross-listed from stat.ML
Sinkhorn Linearization and the Spectral Proxy: Unifying the Statistical and Algorithmic Theory of Feature-Parameterized Inverse Optimal Transport via a Single Spectral Sandwich
Han Dong, Jiaming Li, Yongqiang Gong et al. (+2 more)
We develop the statistical and algorithmic theory of inverse optimal transport (IOT) under the feature-parameterized cost C_theta(i,j) = -theta^T phi(i,j). The core technical contribution is the Sinkhorn linearization – the implicit-function sensitivity of the entropic OT plan to the cost – together with its spectral proxy, a formula that is spectrally exact yet geometrically transparent. The restricted Hessian on the tangent space satisfies the spectral sandwich (pi_min/epsilon) I <= H_T^{-1} <= (pi_max/epsilon) I, yielding the single core bound sigma_min >= (pi_min/(a_max epsilon)) sqrt(lambda_min(Sigma)) that drives the entire theory. On this core we establish four
theorems and one observation. T1 (identifiability): theta is globally injective on the quotient of the gauge kernel, with dimension bound F <= (K-1)^2. T2 (sparsistency): the l1-penalized
estimator recovers the true support under irrepresentability and score concentration, with exponential failure probability. T3 (well-posedness): the feature-moment map M(theta) = Phi^T x_theta is strongly monotone, and the inverse is Lipschitz with constant L <= epsilon ||Phi^T S_a||_op / (pi_min lambda_min(Sigma)). T4 (convergence): local strong convexity with mu >= pi_min^2 lambda_min(Sigma) / epsilon^2 guarantees monotone gradient descent convergence. O5 (misspecification): the
estimator converges to the OT-model projection of the truth; the Holder continuity of the projection map is assessed numerically, yielding setting-dependent empirical exponents alpha_eff in (0,1).
Read the full abstract ▾
All authors Han Dong, Jiaming Li, Yongqiang Gong, Ruixi Li, Yin Liu
Computation and Language
Zhili Shen and Craig Macdonald
Modern LLMs excel at
reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely on surface-level matching between queries and documents, resulting in a growing gap between how users express their needs and how retrievers interpret them. In this paper, we present GEM, a generative
embedding model that augments
retrieval through its own knowledge by explicitly
reasoning about user intent and relevance criteria. GEM unifies generation and
embedding within a single model: it first reasons over the query, then appends an
embedding token to encode the enriched context for
retrieval. Evaluated on
reasoning-intensive and instruction-following
retrieval tasks, GEM demonstrates the effectiveness of its
reasoning-augmented
retrieval, outperforming its non-
reasoning variant and matching baselines using substantially larger models. Furthermore, GEM's generative nature allows test-time compute scaling via prompting to further enhance
retrieval performance. Our code is available at: https://anonymous.4open.science/r/GEM.
Read the full abstract ▾
Machine Learning
Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcity
Timilehin B. Aderinola, Ilaria D'Ascanio, Luca Palmerini et al. (+5 more)
Falls are a major health concern for older adults, and wearable sensors have been widely explored for detecting falls and enabling timely intervention. However, real-world falls are extremely rare: collecting 100 of them requires an estimated 100,000 days of monitoring, resulting in severely limited labelled data for training machine learning models. Consequently, many approaches rely on simulated
datasets, often reporting high laboratory performance but limited real-world generalisation. We present a systematic evaluation of motion representations for wearable fall detection under real-world data scarcity. Using accelerometer signals, we compare interval-based, kernel-based, symbolic, and foundation model representations. As an interpretable baseline, we additionally investigate a lightweight symbolic representation that converts short motion segments into symbolic sentences augmented with physically-grounded impact descriptors. Experiments use FallAllD, a simulated falls
dataset, and FARSEEING, a clinically verified real-world falls
dataset. Through cross-validation, controlled data scarcity, and cross-
dataset transfer, we examine how representation choices affect robustness under realistic deployment. Our results reveal that highly parameterised kernel and foundation models excel on simulated data but degrade severely under both data scarcity and domain shift. Although the interval-based representation achieves the strongest absolute real-world performance, augmenting a symbolic representation with physically-grounded impact descriptors yields the smallest degradation under domain shift and retains detection sensitivity under extreme scarcity, albeit at lower precision. These findings highlight the importance of evaluating beyond simulated
benchmarks and show that representation choice is critical for deployable fall detection given the scarcity of real-world data.
Read the full abstract ▾
All authors Timilehin B. Aderinola, Ilaria D'Ascanio, Luca Palmerini, Lorenzo Chiari, Jochen Klenk, Clemens Becker, Brian Caulfield, Georgiana Ifrim
Digital Libraries
Co-leading Teams Drive Scientific Novelty in Large-scale Research Infrastructures
Mingze Zhang, Yizhan Li, Hao Peng et al. (+1 more)
Large-scale research infrastructures (LSRIs) have become the engine of modern scientific discovery. While these big machines predominantly operate under a user-oriented model where external teams conduct research with support from in-house researchers, the structural integration of staff scientists into user teams and its association with scientific novelty remains unclear. By leveraging a
dataset of 273,109 publications across 76 global LSRIs and applying a hybrid machine-learning framework to classify papers into three collaboration patterns: external user only, staff participating, and staff co-leading, we find a distinct novelty premium for external teams that formally integrate staff as co-authors, especially when staff scientists play co-leading rather than participating roles. Further, the premium peaks at a relatively balanced user-staff team composition, potentially due to an "epistemic lock-in" by either party. Crucially, we find that the ideal collaboration architecture evolves with user experience: while newcomers can obtain a large novelty premium from mere staff participation, experienced users only benefit from staff co-leading teams. This result suggests a "knowledge saturation effect" for which a deeper intellectual partnership is needed to sustain novelty. By revealing how user-staff collaboration structure drives scientific creativity, our study offers practical policy implications for the strategic management and intervention of LSRIs in the era of human-machine collaboration.
Read the full abstract ▾
All authors Mingze Zhang, Yizhan Li, Hao Peng, Zexia Li
Computer Vision
Fidelity-Constrained Anchoring for Black-Box Denoisers
Masaki Satoh
We propose a fidelity-constrained framework that anchors the output of a black-box denoiser to its input without retraining and with little additional computation. The method linearly blends the denoised image with the input and selects the maximum blending factor that satisfies a prescribed local fidelity constraint using Peak Signal-to-Noise Ratio (PSNR) or Structural Similarity Index (SSIM). For PSNR control, a closed-form solution is obtained under a local constant-blending assumption. For SSIM control, we derive a tractable formulation based on inverse SSIM under the same assumption and solve it efficiently using iterative root finding. Experiments on DIV2K images with synthetic Gaussian noise and outputs from Real-ESRGAN and a non-local means denoiser show that the proposed anchoring strategy provides effective fidelity control while balancing denoising performance and statistical naturalness, as measured by the excess kurtosis of residual noise. In particular, SSIM-based anchoring yields more consistent behavior across noise levels than PSNR-based anchoring.
Read the full abstract ▾
Cryptography and Security
Smart Contract Invariants Protect Against Cybercriminals
Sofia Bobadilla, Humaira Afrin, Angela Novelli et al. (+1 more)
Blockchains are among the most
adversarial environments in computing. Billions are stolen by cybercriminals who exploit vulnerabilities. This is an open problem and no concept or technique has proven to really make a difference. In this paper, we claim that the classical notion of program invariant is perhaps the most powerful solution to the problem. We devise anoriginal experimental protocol to 1) study how invariants would have protected against past real-world attacks and 2) whether state-of-the-art automated tools can find them. The experimental toolchain is sophisticated. It is based on INVARIANTEVAL, a
benchmark of 28 real Ethereum exploits, each paired with a human-authored invariant that blocks the attack. We validate every invariant with PONDEREPLAY, a replay framework that re-executes transactions in order to prove the correctness and soundness of smart contract invariants. We demonstrate that smart contract invariants block all the cybercriminal attacks in INVARIANTEVAL, fully validated by replaying 108,637 historical transactions. Our large-scale experiments clearly demonstrate that smart contract invariants protect against cybercriminals.
Read the full abstract ▾
All authors Sofia Bobadilla, Humaira Afrin, Angela Novelli, Martin Monperrus
Machine Learning
ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning
Qianqian Wang, Yunshan Li, Dawei Huang et al. (+2 more)
Group-robust learning is crucial for maintaining accuracy on rare subpopulations when training-group labels are unavailable. However, existing methods often infer environments from a separate reference model and select representations before fitting the classifier used at deployment, leaving both decisions misaligned with the deployed predictor. In this work, we formulate group robustness without training-group labels as the endogenous environments with repair-aware selection (ERAS) problem, and propose ProME (Prototype-Margin Environments) to align both decisions with the deployed predictor. ProME splits prototype margins at their median to construct approximately balanced environments along the training trajectory, and fits a group-balanced linear head on group-annotated validation data to rank the resulting predictors by validation worst-group accuracy. We theoretically bound the worst risk across the inferred environments for a fixed predictor and partition, showing that this bound transfers to the oracle groups under an explicit
alignment condition. Extensive experiments show that prototype margins enrich shortcut-conflicting examples, classifier repair reshapes candidate evaluation, and ProME achieves the highest average worst-group accuracy among the compared methods with the same group-label access.
Read the full abstract ▾
All authors Qianqian Wang, Yunshan Li, Dawei Huang, Wenwu Gong, Lili Yang
Emerging Technologies
Enabling Ultra-Low-Power Always-On Feedforward Leakage Suppression Logic Circuits with FDSOI
Clément Choné, Leslie Xu, Filippo Quadri et al. (+5 more)
The growing deployment of real-time applications on wearable and Internet of Things (IoT) edge devices has intensified the need for energy-efficient, high-performance systems that meet stringent timing and energy constraints. Events-driven architectures leverage the sparsity of real-time to further improve system energy efficiency by employing an always-on (AO) domain to monitor inputs and activate a high-performance (HP) domain only when relevant events occur. However, for low-duty-cycle applications, the energy bottleneck shifts toward the AO domain, where leakage power dominates overall consumption. To mitigate this issue, AO
circuits are typically implemented using high voltage threshold (HVT) or ultra-high voltage threshold (UHVT) transistors, thereby avoiding sub- and near-threshold operation, which is highly sensitive to process, voltage, and temperature (PVT) variations. In this context, feedforward leakage suppression logic (FLSL) has recently emerged as a promising candidate, offering reduced leakage compared to conventional. However, previous studies report a significant degradation in FLSL leakage performance in technology nodes below 90 nm, primarily due to increased gate and junction leakage currents. FDSOI technology, with its ability to effectively suppress junction leakage, provides an opportunity to overcome this limitation and restore FLSL efficiency in advanced nodes. Therefore, we demonstrate in this work that FLSL implemented in a 22 nm FDSOI technology can significantly reduce the energy consumption of small AO
circuits with low-frequency inputs compared to state-of-the-art ultra-low-power CMOS designs. Silicon measurements on an FIR filter and an AES cryptographic core show reduced operating voltage and up to 9.8 x and 1.83 x reductions in leakage power compared to equivalent HVT and UHVT CMOS implementations, respectively.
Read the full abstract ▾
All authors Clément Choné, Leslie Xu, Filippo Quadri, Pasquale Davide Schiavone, Alexandre Levisse, Jean-Luc Naguel, David Atienza, Andreas Burg
Game Theory
Power in Liquid Democracy: A Network Centrality Approach
Davide Grossi, Andreas Nitsche, Georgios Papasotiropoulos et al. (+3 more)
This paper develops a computationally tractable framework for measuring voters' power in collective decision-making platforms that support transitive and suspendable delegations—commonly known as
liquid democracy. We employ Random Walk Decay centrality to capture how influence propagates through delegation networks, argue for its intuitive appeal in this context and its advantages over alternatives such as PageRank, and derive a natural axiomatic characterization within the class of power metrics. Moreover, we conceptualize how the framework can be extended into a practical tool for analyzing power distributions in such platforms, and propose and study, both axiomatically and algorithmically, methods for selecting representative slates of influential participants.
Read the full abstract ▾
All authors Davide Grossi, Andreas Nitsche, Georgios Papasotiropoulos, Oskar Skibski, Piotr Skowron, Tomasz Wąs
Numerical Analysis
Performance Evaluation of an Adaptive Quadrature and a Double Exponential Formula Using Arbitrary-Precision Floating-Point Arithmetic
Tomonori Kouya
Using arbitrary-precision arithmetic provided by the GNU Multiple Precision Floating-Point Reliable Library, we implement AQE11D—that is, Ninomiya's adaptive 9-point Newton–Cotes rule extended with a sequence of higher-order rules—and Takahasi and Moris' double exponential (DE) formula. We evaluate them for Kahaner's 21 test problems. For both absolute tolerances $10^{-50}$ and $10^{-100}$, AQE11D attains target accuracy on all 21 problems; however, for strong endpoint singularity such as $1/\sqrt{x}$, it requires about $5.4\times10^{7}$ function evaluations at $10^{-100}$, roughly $7\times10^{4}$ times as many as the DE formula. The formula converges on 18 problems at both tolerances, demonstrating its strength against endpoint singularities but also its failure, as it stands, on problems with a singularity inside the integration interval.
Read the full abstract ▾
Computer Vision
SketchSense: Learning to Interpret Imperfect Sketch Guidance for Image Inpainting
Zian Yang
Sketch-guided image inpainting provides intuitive structural control, yet real sketches often mix reliable global intent with locally crowded, displaced, incomplete, or deliberately unconventional strokes. Existing approaches typically either retain the input sketch as a fixed condition throughout denoising or refine it into a clean structure before RGB synthesis. The former assumes uniformly reliable strokes and can propagate local errors throughout generation; the latter must resolve ambiguous structure before emerging appearance and semantic context become available. We propose SketchSense, a framework that interprets imperfect sketch guidance by synchronously denoising interacting RGB and structure streams. Bidirectional
Attention Fusion couples appearance generation with structural recovery, producing a refined structure that exposes the model's evolving sketch interpretation. A phrase-level objective aligns the semantic grounding of the two streams. Sketch-Aware Spatial Regulation further adapts sketch use to local generation states by modulating
attention and the fusion process, while an optional signed prior injects preserve-versus-correct intent into feature representations and
attention behavior. Experiments on natural and structurally complex imagery show substantial gains over existing methods in both restoration quality and structural fidelity.
Read the full abstract ▾
Social and Information Networks · Cross-listed from physics.soc-ph
Beyond persuasion: Mobile electoral interfaces in polarized societies
Nuno Crokidakis and Celia Anteneodo
Many traditional models of electoral dynamics emphasize opinion change, social influence and persuasion mechanisms. In contrast, contemporary polarized societies often exhibit relatively stable partisan blocs coexisting with an electorally relevant mobile population. We propose a minimal dynamical model in which electoral competition is governed not by direct persuasion between opposing blocs, but by the dynamics and allocation of a mobile electoral interface. The electorate is partitioned into two stable partisan blocs and a mobile fraction, while direct transitions between the polarized blocs are strongly suppressed. Mobile voters are allocated between the competing blocs through a
Fermi-like probabilistic rule governed by rejection asymmetries. Analytical calculations show that the electoral susceptibility to political shocks is proportional to the stationary size of the mobile electoral interface, identifying electoral mobility as the key quantity controlling the macroscopic response of polarized systems to external perturbations. The model naturally predicts a continuum of mobility regimes, ranging from frozen polarization to highly responsive electoral states characterized by a broad mobile interface. These results suggest that, in strongly polarized elections, aggregate electoral changes may be governed primarily by fluctuations at the mobile electoral interface rather than by large-scale ideological conversion.
Read the full abstract ▾
Computer Vision
A Controlled Study of Self-Supervised Image and Video Pretraining under Limited Resources
Brunó B. Englert and Gijs Dubbelman
Visual foundation models are a cornerstone of image and
video understanding but typically require large amounts of data and computation. The current scale required for pretraining visual foundation models may be unsustainable or unnecessary, and significant benefits arise when effective models can be obtained with fewer resources. To better understand how self-supervised learning (SSL) objectives behave under resource constraints, we conduct a controlled study of image and
video SSL objectives under matched data, architecture, and compute budgets. We compare contrastive, reconstruction, feature-prediction, and
diffusion objectives and evaluate both standalone and jointly trained image-
video SSL formulations across a diverse set of image and
video understanding tasks. Our results show that DINOv2-style pretraining consistently provides the strongest overall performance under limited resources. Furthermore, combining DINOv2 with
video SSL objectives such as VideoMAE substantially improves image classification and
segmentation performance, but degrades
video tracking and camera-pose estimation performance, revealing an important tradeoff between semantic and
geometric representation learning. These findings suggest that combining image and
video SSL objectives can be beneficial in resource-limited settings, while highlighting the need for improved methods that better balance semantic, temporal, and
geometric supervision.
Read the full abstract ▾
Artificial Intelligence
Teach the Magnitude, Not the Direction: Verifier-Anchored Credit Assignment for Multi-Turn Multi-Step LLM Agents
Zechuan Wang, Siyuan Lu, Hongxuan Zhang et al. (+3 more)
Reinforcement learning with verifiable rewards (RLVR) directly optimizes verifier-defined outcomes for multi-turn tool-use
agents, yet its trajectory-level credit assignment conflates heterogeneous per-turn outcomes into a single reward signal. On-policy
distillation provides dense per-
token supervision but uses a teacher-defined
token-level objective and can be prone to gradient concentration collapse. We introduce $\textbf{CrEST}$, a hierarchical credit assignment framework that anchors each sampled
token's scalar advantage sign to verified rewards while incorporating dense magnitude signals from a privileged self-teacher. $\textbf{CrEST}$ resolves credit at two levels: turn-segmented verified advantages address inter-turn dilution, while
entropy-gated self-teacher modulation refines intra-turn
token contributions. Experiments on BFCL V3 and WildToolBench show that $\textbf{CrEST}$ consistently outperforms both RL and
distillation baselines across two model scales, with the largest gains on long-trajectory and strict session-level metrics. Our work demonstrates that the teacher's role in policy optimization can be reduced from determining
token-level reinforcement or suppression to modulating update magnitudes, enabling dense credit assignment while keeping verifier rewards as the training objective.
Read the full abstract ▾
All authors Zechuan Wang, Siyuan Lu, Hongxuan Zhang, Linjian Mo, Chenyi Zhuang, Leilei Gan
Computational Geometry · Cross-listed from math.CO
New Quantitative Bounds for the $(p,q)$-Theorem for Unions of Convex Sets
Chaya Keller and Shakhar Smorodinsky
A set in $\mathbb{R}^d$ is $s$-convex if it is the union of at most $s$ convex sets. A family $F$ satisfies the $(p,q)$ property if among any $p$ sets in $F$, some $q$ intersect. Let $\mathrm{HD}_d^{(s)}(p,q)$ be the minimum number of points needed to pierce a finite family of $s$-convex sets that satisfies the $(p,q)$-property. Alon and Kalai (1995) proved that $\mathrm{HD}_d^{(s)}(p,q)$ exists for any $p \geq q \geq d+1$ and any $s \geq 1$, but the quantitative bounds they obtained are very loose. We present several improved upper and lower bounds, for a general $d$ and for $s$-intervals of the line (i.e., $\mathrm{HD}_1^{(s)}(p,q)$). In particular, we prove the following: (i) For every $d\ge2$, $s \geq 1$ and $\delta>0$, if $p>q$ and $q\ge C_d\log(e sp)$, then $\mathrm{HD}_d^{(s)}(p,q) \le p-q+1 + O_{d,\delta}((s \cdot \tfrac{p}{q} \cdot \log \tfrac{esp}{q})^{\rho_d+\delta}),$ where $\rho_d<d$ is the exponent in the weak epsilon-net
theorem of Rubin (2022). (ii) For $s \geq 1$, $p \geq q \geq 2$ and $q\ge C_0s\log(2s)\log(ep)$, $p-q+s \leq \mathrm{HD}_1^{(s)}(p,q) \leq p-q+2s+1$. This result provides the first near-tight estimate for $\mathrm{HD}_1^{(s)}(p,q)$ for $q>2$. (iii) For any fixed $s$, there are an integer $\kappa_s\in\{s,\ldots,2s\}$ and constants $C_s,p_s>0$ such that, whenever $p\ge p_s$ and $q\ge C_s\log(ep)$, $ \mathrm{HD}_1^{(s)}(p,q)\in\{p-q+\kappa_s,\;p-q+\kappa_s+1\}. $ Interestingly, this two-value concentration result holds, although the exact value of the threshold remains unknown. (iv) For any $s \geq 1$, $\mathrm{HD}_3^{(s)}(p,4) \geq sp^{2-o(1)}$. Already for families of convex sets, this significantly improves the best known lower bound on $\mathrm{HD}_d^{(1)}(p,d+1)$, for all $d \geq 3$.
Read the full abstract ▾
Artificial Intelligence
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
Chang Liu, Yuqi Zhang, Yiman Zhong et al. (+3 more)
Agent skills are crucial external instructions that enable
language agents to execute long procedural tasks such as coding or document processing. Existing
agent skills are primarily created through human manual crafting or
agent execution traces, with limited understanding of how each step contributes to overall skill performance on specific tasks; i.e., there remains an open problem in quantifying the contribution of individual steps within an
agent skill. To address this issue, we first model skill-step attribution as a Shapley value-based contribution estimation problem, and then propose SkillShapley, a step-level attribution framework for
agent skills. Notably, SkillShapley operates in two phases, motivated by key empirical insights, i.e., discretized
benchmark rewards that create sharp performance cliffs, and step interactions that are largely additive rather than synergistic. Specifically, it first identifies informative coalitional regions, and then adaptively samples new coalitions that can yield reusable marginal evidence. Experiments on skills from the widely adopted SkillsBench demonstrate that our SkillShapley can effectively and efficiently identify high- or low-value skill steps, providing several key takeaways for
agent skill creation.
Read the full abstract ▾
All authors Chang Liu, Yuqi Zhang, Yiman Zhong, Boyi Liu, Hengjun Wang, Shuyue Wei
Machine Learning · Cross-listed from stat.ML
High-dimensional networks and mean squared error for possibly misspecified models
Lourens Waldorp
To avoid missing important variables and their connections in networks, more and more variables are included in network analysis. Here we show that in a setting with many more parameters than observations (high-dimensional) it is possible to get a conservative (i.e., low false positive rate) estimate of the neighbourhood for each node (which connections are in the network). A neighbourhood is often estimated with a linear model, and this leads to two interesting cases: (i) If the true model is linear, then neighbourhood selection work reasonably well, and (ii) if the true model is nonlinear, then neighbourhood selection requires a penalty for the high dimensions. Here we show the impact of the ridge parameter on the mean squared error, and how this leads to low test variance and hence to neighbourhoods with large numbers of edges. We connect these insights with results from machine learning, where the so-called double descent (when more parameters are included than observations, the mean squared error goes down a second time) has put the traditional view on model selection upside down. Essentially, for adequate neighbourhood selection in models with a large number of parameters, the volume of the model space needs to be included in the penalty. Most neighbourhood selection methods (e.g., Lasso, AIC, BIC) lead to spurious edges (high false positive rate), but we prove that in the high-dimensional setting, minimum description length leads to correct neighbourhood selection or smaller (low false positive rates) in both cases when either the model is correctly or incorrectly assumed linear
Read the full abstract ▾
Information Theory
Counterexamples to the Markovity Conjecture for the Two-Receiver Broadcast Channel
Yanxiao Liu and Mian Huang
We present two counterexamples to the Markovity
Conjecture of Gohari, Liu and Nair (ISIT 2025), which is a structural
conjecture concerning the optimizers of the dual functional associated with Marton's inner bound and, if true, would greatly simplify the evaluation of Marton's inner bound. Both counterexamples are ternary-input broadcast channels with strictly positive transition probabilities and use the same nonrectangular $2\times2$ auxiliary structure. In each case, we exhibit an explicit non-Markov construction whose objective value is rigorously larger than that achievable by any construction satisfying the conjectured Markov structure. Both examples are obtained with the assistance of GPT-5.6 Sol and disprove the Markovity
Conjecture.
Read the full abstract ▾
Computation and Language
Who Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory
Junkai Zhou, Shiting Guan and Zhaoyi Zhang
As large
language models (LLMs) are increasingly applied for emotional companionship, evaluating their behavior and capabilities in intimate relationships has become a pressing issue. However, existing assessments primarily characterize general personality traits, providing limited insight into model behavior within intimate and emotionally sensitive contexts. Therefore, we introduce adult attachment theory into LLM evaluation and use the Experiences in Close Relationships-Revised (ECR-R) scale to characterize attachment anxiety and avoidance. To evaluate emotional companionship capabilities of LLMs in realistic interaction scenarios, we present an emotional companionship
benchmark, ECBench, spanning four scenarios including emotional support, collaborative tasks, conflict resolution, and social guidance, across friendship and romantic relationships. ECBench is utilized to assess model behavior using 11 dialogue-quality metrics and three evaluation methods. We evaluate the attachment tendencies of 32 LLMs and select representative models to investigate how these tendencies manifest in contextualized multi-turn interactions and whether they can be shaped through prompting. Our study provides a theoretical lens from psychology, along with practical tools to understand and select LLMs for emotional companionship.
Read the full abstract ▾
Computer Vision
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
Fnu Pramono, John Cai and Sourabh Kulkarni
When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that
Vision-
Language Models (VLMs) can internally distinguish when abstention is required, but fail to express it anyway. We introduce TRAPSBench, a procedurally generated
video benchmark of 1,404 matched physics pairs in which a single targeted change renders the outcome undeterminable from the visual evidence. Furthermore, we introduce Penalized Epistemic Calibration Score (PECS), a new robust metric that requires models to both answer correctly when the outcome is knowable, and abstain when the outcome is not. Across 16 VLMs spanning five families, spontaneous restraint is poor: the best PECS is 0.292. The bottleneck is expression, not perception: linear probes decode answerability from hidden states at up to 0.91 AUROC across physics domains; steering a single-layer void direction causally induces or suppresses abstention. Our results replicate across three open-weight families (Qwen, Gemma, LLaVA). The failure is also more pronounced in visual than textual uncertainty: models detect textual impossibility about 4x more readily than missing visual evidence. Closing this representation–output gap likely requires output-stage interventions.
Read the full abstract ▾
Computation and Language
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
Yilin Wang, Yuchun Fan, Weidong Bao et al. (+5 more)
Multilingual retrieval-augmented generation (mRAG) equips large
language models with access to globally distributed external knowledge for complex
multilingual question answering. Recent approaches either translate retrieved documents into English or the query
language to bridge the cross-lingual semantic gap, or decompose a complex query into sub-questions and aggregate the intermediate
reasoning process. However, both lines of work suffer from two limitations. First, one-size-fits-all translation
alignment, blanket translation discards culturally and linguistically native information unique to the target
language, introduces translation noise, and inflates system cost. Second, greedy decomposition and aggregation, uncontrolled decomposition produces redundant sub-questions that compound errors during step-wise
reasoning, and the final aggregation over
reasoning paths further amplifies these errors. We address both with our method Syfer, a synthesizer-folding framework for
multilingual multi-hop question answering that defers translation rather than applying it by default. Syfer first invokes a format-constrained decomposer to produce a sub-question graph in the original
language, followed by a decomposition-quality check; when the check passes, sub-questions are answered sequentially under a retrieve-then-answer policy in the target
language, and the English translation pathway with bilingual sub-question graph
alignment is activated only when the check fails. Experiments across multiple
languages show that Syfer attains competitive accuracy while striking a favourable balance between performance and computational cost.
Read the full abstract ▾
All authors Yilin Wang, Yuchun Fan, Weidong Bao, Zili Wei, Shi Feng, Tong Xiao, Zhengtao Yu, Jingbo Zhu
Computer Vision
Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling
Kiseok Choi, Inchul Kim, Jaemin Cho et al. (+2 more)
Cone-beam computed
tomography (CBCT) enables volumetric reconstruction from X-ray projections, but suffers from severe artifacts–especially beam hardening–when imaging materials with high attenuation such as metals. These artifacts arise from the polychromatic nature of X-rays and are not properly addressed by conventional monochromatic reconstruction
algorithms. While recent neural representation-based methods offer improved reconstruction quality, they are computationally expensive and often impractical for deployment. We propose a novel physics-inspired, self-calibrating metal artifact reduction method that efficiently reconstructs 3D CBCT volumes while correcting beam hardening artifacts. Our method integrates a polychromatic X-ray projection model, material-dependent attenuation profiles, and system response modeling into a Gaussian Splatting framework. Unlike prior work, we eliminate the need for manual metal masks or strong prior assumptions, and we optimize both reconstruction parameters and X-ray spectral characteristics jointly during training. We further introduce a high-fidelity synthetic CBCT
dataset generation pipeline validated on Monte-Carlo x-ray simulation toolbox and release new
datasets with severe metal-induced artifacts to support the community. This is the first splat-based method for reducing beam hardening in CBCT. Extensive experiments on both synthetic and real-world
datasets demonstrate that our method outperforms state-of-the-art approaches in artifact suppression and reconstruction accuracy.
Read the full abstract ▾
All authors Kiseok Choi, Inchul Kim, Jaemin Cho, Hyeongjun Cho, Min H. Kim