Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science (sign in to use)

Tuesday 18 August

Computer Vision

Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction

X-ray imaging can be approximately modeled as the projection of an underlying volumetric attenuation field, with each measurement recording the accumulated attenuation along a corresponding ray path. Reconstructing a CT volume from only a few X-ray views is therefore severely ill-posed, as the projections collapse depth information and leave 3D locations of anatomical regions and their corresponding intensity distributions highly entangled and ambiguous. We observe that once the spatial organization of anatomical regions is established, estimating their CT intensities becomes substantially more tractable. Motivated by this, we propose LiftXR, an interleaved, geometry-guided framework that explicitly incorporates spatial layout recovery into CT reconstruction. Specifically, a layout lifter first generates a 3D anatomical layout from bi-planar X-rays, providing spatial guidance for an intensity renderer to reconstruct a CT volume. An anatomical parser then performs volumetric perception on the reconstruction, exploiting its spatially resolved boundary and intensity cues to recover a refined anatomical layout. This transition from projection-conditioned layout generation to reconstruction-conditioned anatomical perception allows the parsed layout to provide feedback for region-specific intensity calibration. Extensive experiments on two public datasets demonstrate that LiftXR consistently outperforms recent X-ray-to-CT reconstruction methods, establishing a new state of the art. Moreover, the reconstructed CT achieves superior performance in external downstream segmentation, indicating improved anatomical fidelity. Code will be released.
Read the full abstract

All authors Yifei Wu, Yicheng Wu, Qiang Ma, Qi Chen, Renyang Gu, Xinyu Liu, Yongsheng Pan, Yong Xia

Computer Vision

Heterogeneity-Aware Deep Learning for Tumour Classification from Multiparametric MRI

Intra-tumoural heterogeneity (ITH) reflects spatial variation in tumour biology and is an important determinant of tumour behaviour, prognosis, and treatment response. Radiomics and deep learning have shown promise for tumour classification from multiparametric MRI (mp-MRI), but radiomics relies on handcrafted features, while most deep learning methods use whole-tumour representations or manually defined sub-regions, limiting scalable modelling of tumour heterogeneity. We propose a Heterogeneity-Aware Deep Learning Classification (HA-DLC) framework that explicitly models imaging-derived tumour sub-regions for lesion-type diagnosis and molecular-status prediction. HA-DLC consists of: (1) a Heterogeneous Sub-region Generation (HSG) module that produces initial pseudo-labelled sub-regions via unsupervised clustering, followed by Cross-Patient Sub-region Alignment (CPSA), which maps cluster-derived regions to a shared label space using soft assignments; and (2) a Dual-Stream Feature Extraction (DSFE) module that integrates local heterogeneity-aware features with global tumour representations. Given the initial clustering masks, CPSA, segmentation, feature extraction, and classification are jointly optimized end-to-end using soft-target segmentation and classification objectives. We evaluate HA-DLC on the LLD-MMRI2023 liver lesion dataset and the RSNA-ASNR-MICCAI 2021 Radiogenomic Brain Tumour dataset. HA-DLC consistently outperforms state-of-the-art radiomics and deep learning baselines, demonstrating the value of cross-patient sub-region alignment and dual-stream heterogeneity modelling for tumour classification from mp-MRI.
Read the full abstract

All authors Yue Xia, Euijoon Ahn, Tian Xia, Yuan Yuan, Michael Fulham, Jinman Kim

Machine Learning

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Reinforcement Learning (RL) has emerged as a powerful approach for improving reasoning in language and vision-language models, yet its strongest successes still depend heavily on ground-truth supervision (e.g., verifiable reward). Such annotations are costly to obtain and become increasingly scarce as reasoning capabilities advance beyond what humans can reliably evaluate. Self-rewarding RL reduces this dependence by enabling models to derive reward signals from their own completions. However, training solely on self-generated feedback can reinforce existing biases, reduce response diversity, and ultimately lead to homogenized responses and training collapse. In this work, we show that unsupervised reasoning can emerge through cooperative multi-agent training. We introduce Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from the other agent. We further show that increasing cohort diversity, through heterogeneous model families, sizes, and rephrased training samples, reduces the correlated errors that drive self-reinforcing feedback loops. This diversity consistently improves reasoning performance and mitigates training collapse. Without any ground-truth labels, Co-RL improves the base models by 3.0-7.9% on average across seven benchmarks and by 1.6-4.4% across four multimodal benchmarks. It also outperforms the prior state-of-the-art multi-agent RL method CoMAS by 4.0% and the self-rewarding vision-language RL method MM-UPT by 2.0%. Our code is available at https://github.com/Diverse-CoRL/Co-RL and website at https://williamium3000.github.io/Co-RL.
Read the full abstract

All authors Yunhao Yang, Yuexin Bian, Yunjie Tian, Di Fu, Tianjin Huang, Yuanyuan Shi, Ziang Xiao, Nuno Vasconcelos, Yijiang Li

Cryptography and Security

ADAPTD: Adaptive Detection and Proactive Threat Defense for Autonomous APT attacks

Advanced persistent threat (APT) actors increasingly employ sophisticated techniques to propagate laterally through segmented enterprise networks. Timely detection and defense depend on cross-subnetwork coordination, yet maintaining global situational awareness generates substantial communication overhead. To manage this tradeoff, flexible monitoring and adaptable containment are imperative. This paper presents ADAPTD, a communication- and computation-efficient, decision-theoretic framework integrating: (i) compact kill chains for identifying diverse attack vectors, (ii) an immediate blocking mechanism for timely containment, and (iii) a predictive eviction strategy to restore system security. Our experiments validate ADAPTD's effectiveness across diverse threat scenarios. First, our decentralized belief update scheme outperforms state-of-the-art diffusion HMM. Second, ADAPTD substantially reduces false evictions compared to transformer-based detection. Third, under noisy environments, adaptive blocking contains attackers while minimizing unnecessary disruption. Lastly, the ablation study confirms that combining two defensive actions significantly reduces the defender's total cost.
Read the full abstract

Computational Engineering

Adaptive surrogate modeling for high-dimensional spatio-temporal output

This paper develops an adaptive surrogate modeling method for problems with very high-dimensional spatio-temporal outputs. The analysis of spatio-temporal multi-physics systems is computationally expensive and consists of a large number of inputs and outputs. Surrogate models are often constructed to replace the physics-based model to achieve computational efficiency in analyses such as uncertainty quantification and optimization that require many function calls. In order to address the challenge introduced by the high dimensionality of spatio-temporal output, a dimension reduction method is first employed to map the high-dimensional output to a low-dimensional latent space. This is followed by the construction of the surrogate model in the low-dimensional space. The prediction error in the original space, which includes both the reconstruction error and surrogate model error, is evaluated using different error metrics. Based on the prediction accuracy of the surrogate model, new training points are identified for adaptive improvement of the surrogate model. We present a novel adaptive sampling technique that combines exploration and exploitation to improve the surrogate model accuracy with the fewest possible runs of the expensive physics-based model. Thermo-mechanical analysis of a gas turbine engine blade is used to analyze the effectiveness of the proposed method.
Read the full abstract

All authors Berkcan Kapusuzoglu, Shunsaku Matsumoto, Yoshitomo Miyagi, Daigo Watanabe, Sankaran Mahadevan

Computational Engineering

Information fusion and machine learning for sensitivity analysis using physics knowledge and experimental data

When computational models (either physics-based or data-driven) are used for the sensitivity analysis of engineering systems, the sensitivity estimate is affected by the accuracy and uncertainty of the model. This paper considers global sensitivity analysis (GSA) for situations where both a physics-based model and experimental observations are available, and investigates physics-informed machine learning strategies to effectively combine the two sources of information in order to maximize the accuracy of the sensitivity estimate. Two representative machine learning (ML) techniques are considered, namely, deep neural networks (DNN) and Gaussian process (GP) modeling, and two strategies for incorporating physics knowledge within these techniques are investigated, namely: (i) incorporating loss functions in the ML models to enforce physics constraints, and (ii) pre-training and updating the ML model using simulation and experimental data respectively. Four different models are built for each type (DNN and GP), and the uncertainties in these models are included in the Sobol indices computation. The DNN-based models, with many degrees of freedom in terms of model parameters and training options, are found to result in smaller bounds on the sensitivity estimates when compared to the GP-based models. The proposed methods are illustrated for additive manufacturing and lake temperature modeling examples.
Read the full abstract

Artificial Intelligence

Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification

Personalized agents must decide whether retrieved user memory should be used, ignored, updated, or queried before it affects a current task. We use this setting to develop an empirical audit protocol for structured intermediate outputs: first audit dataset shortcuts, then isolate bundled prompt changes, check whether intermediate labels are answer-associated, test decomposed semantic evidence, and audit provider-level execution failures. A 480-example synthetic development set initially suggested large gains from a state-structured prompt bundle, but TF-IDF diagnostics showed lexical separability and no positive standalone Ignore cases. We therefore construct a frozen 160-example controlled counterfactual set with 40 matched four-way families and rule-derived reference policies. On this set, exposing the four state definitions improves accuracy, but an isolated explicit state-output field does not significantly improve policy accuracy for Llama-3.3-70B and gives only a marginal, non-significant gain for GPT-OSS-120B. Supplying benchmark-associated state labels shifts policy predictions, but because those labels deterministically map to policies, this is a label-conditioning diagnostic rather than evidence of a faithful internal mechanism. Family-level and seed-stability analyses further show that example-level accuracy overstates counterfactual consistency: complete four-way family success is rare. An exploratory follow-up that elicits decomposed semantic evidence also fails to improve routing for the cleanly evaluated endpoint; the corresponding GPT-OSS condition was unavailable because of provider-side request validation. We evaluate policy classification only, not downstream responses, tool actions, or memory-store mutation.
Read the full abstract

All authors Yihang Chen, Pin Qian, Su Wang, Chong Peng, Huan Xu, Shuaiting Li, Yiqi Sun

Machine Learning

Physics-Informed and Hybrid Machine Learning in Additive Manufacturing: Application to Fused Filament Fabrication

This article investigates several physics-informed and hybrid machine learning strategies that incorporate physics knowledge in experimental data-driven deep-learning models for predicting the bond quality and porosity of fused filament fabrication (FFF) parts. Three types of strategies are explored to incorporate physics constraints and multi-physics FFF simulation results into a deep neural network (DNN), thus ensuring consistency with physical laws: (1) incorporate physics constraints within the loss function of the DNN, (2) use physics model outputs as additional inputs to the DNN model, and (3) pre-train a DNN model with physics model input-output and then update it with experimental data. These strategies help to enforce a physically consistent relationship between bond quality and tensile strength, thus making porosity predictions physically meaningful. Eight different combinations of the above strategies are investigated. The results show how the combination of multiple strategies produces accurate machine learning models even with limited experimental data.
Read the full abstract

Systems and Control

Assessing Collision Probability in Low-Thrust Deorbit

End-of-life support of satellites is necessary to improve post-mission-disposal compliance rates for maintaining space environment. Deorbit mission with low thrust, e.g. a laser, induces a low-level deceleration on the target object that gradually lowers the target altitude. Since such a low-thrust trajectory is time-consuming, the risk of collision greatly influences the mission success rate. In this context, this paper assesses the collision risk during deorbit trajectories with low thrust. Furthermore, parametric studies for the relationship between the re-entry time and the risk of collision are performed.
Read the full abstract

All authors Shuta Fukii, Daisuke Sakai, Yasuhiro Yoshimura, Yuri Matsushita, Toshiya Hanada, Yuki Itaya, Tadanori Fukushima

Artificial Intelligence · Cross-listed from math.OC

Maximum Tsallis Entropy Distributions for Robust and Efficient Sparse Learning from Correlated Data

This paper addresses the limitations of Gaussian distribution assumptions in statistical sparse learning, particularly in modeling correlated and heterogeneous data. Conventional Gaussian models often lack robustness towards outliers and underlying distribution assumptions. To overcome these limitations, we propose the use of the $q$Gaussian distribution, derived from Tsallis entropy maximization, as a robust alternative. This is notably relevant in biostatistics, where the presence of correlated observations and heterogeneity, such as in genetic and longitudinal studies, is prevalent. Our contributions include modeling of correlated data through the re-derived multivariate probability density function from Tsallis entropy maximization, thereby addressing the limitations inherent in conventional Gaussian models. Furthermore, we introduce a novel framework that adapts numerical methods designed to find equilibria in flows to tackle composite optimization problems prevalent in statistical sparse learning. Applying this framework to the Hager-Zhang conjugate gradient algorithm \cite{Hager2005}, we develop a numerically stable and efficient algorithm for sparse statistical learning. The $q$Gaussian distribution, informed by the principle of maximizing Tsallis entropy, presents a viable and flexible alternative to Gaussian-based methods. This paper not only contributes to the theoretical understanding of statistical distributions and optimization techniques, but also paves the way for practical data analysis.
Read the full abstract

Computer Vision

Training-Free Agentic Computer Vision for Structural Component Detection in 2D Structural Framing Plans

Converting structural framing plans into editable finite-element model drafts is labor-intensive and susceptible to transcription errors. Existing building-component recognition systems generally depend on task-specific neural detectors, whereas language-model agents in structural engineering typically operate on text or model data rather than on drawings. To the authors' knowledge, this work is the first to apply an agentic vision-language layer to structural-component detection and model drafting from framing-plan PDFs without task-specific detector training or fine-tuning. A deterministic stage extracts geometric primitives, estimates scale by dimension-ratio consensus, recognizes five entity classes using an explicit drafting grammar, and assembles an editable layout. The agentic stage constrains typed corrections through deterministic candidates, operation-specific admission tests, change-level review, and fail-closed transactions. Evaluation used an author-generated benchmark of 100 plans, divided equally between a development half used for all rule revisions and a seed-disjoint held-out half generated after the rules were frozen and evaluated once. All scores are end-to-end results for the complete framework on the held-out half. Scale estimates were within 0.1% of the generator reference for every drawing. Recall and precision were 0.922/0.997 for columns, 0.886/0.990 for beams, 1.000/1.000 for walls, 1.000/1.000 for braces, and 1.000/0.964 for openings. A controlled study repeated two corruptions three times on three development drawings. Calibration passed all nine trials, whereas member repair satisfied every strict end-state criterion in five of nine trials. Because both benchmark halves share a generator, the evaluation does not address independently drafted plans, raster input, analytical connectivity, or solver validation.
Read the full abstract

Systems and Control

Safe Deep Reinforcement Learning for Energy-Efficient HVAC Control in Multi-Zone Residential Buildings

HVAC systems represent a major share of building energy consumption. Traditional control strategies are limited in coordinating energy-comfort tradeoffs across multiple zones simultaneously. Reinforcement learning (RL) offers adaptive, data-driven control that optimizes performance over time. However, deploying learned neural network controllers in safety-critical building systems remains challenging due to lack of formal safety guarantees. We propose a safety-certified deep RL framework for multi-zone residential HVAC control. Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents are trained in an EnergyPlus/Sinergym simulation to minimize energy consumption while maintaining thermal comfort. Post-training safety certification is performed on the PPO policy using Lipschitz-based forward invariance analysis, building on existing tools for the computation of Lipschitz constants for neural networks, to guarantee constraint satisfaction. Both agents are evaluated over an annual simulation cycle in an eight-zone variable refrigerant flow (VRF) testbed. The PPO agent achieves 67% comfort violation reduction compared to rule-based control, while the SAC agent achieves 27.6% energy savings. The PPO policy satisfies formal safety certification with a margin of $2.003^\circ$C. These results demonstrate the feasibility of combining reinforcement learning with post-training safety verification for multi-zone building control.
Read the full abstract

All authors Oussama Ziadi, Abdelilah Rochd, Samir Idrissi Kaitouni, Mohamed Oualid Mghazli, Adnane Saoud

Cryptography and Security

COMIC: Reference-Aware Safety Gating for Multimodal Large Language Models

Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded inputs. This shift introduces a new safety risk: in many multimodal jailbreaks, neither the prompt nor the image is harmful in isolation. Unsafe behavior emerges only when the model binds an apparently benign operation, such as summarizing, translating, or following, to a localized visual target. This reveals a structural weakness in current multimodal defenses, which largely moderate the prompt-image pair as a whole even though the true security-relevant unit is the grounded operation-target pair produced during dereference. In this work, we identify and analyze this reference-dependent failure mode and show that existing defenses degrade when harmful semantics are localized, activated only after grounding, and dependent on visual reference resolution. To address this problem, we propose COMIC (Context-Operation-Modality-Image-Classifier), a reference-aware pre-generation safety gate for MLLMs. COMIC first infers the requested operation and reference type, constructs candidate targets from OCR and open-vocabulary proposals, grounds plausible referents, and evaluates safety over explicit operation-target pairs. To handle ambiguity conservatively, COMIC combines max-risk aggregation with quality-aware routing before deciding whether to forward or block a request. We evaluate COMIC across multiple open-source MLLMs, localized and broader multimodal jailbreak benchmarks, and benign reference-sensitive settings. The results show that COMIC consistently improves robustness while preserving benign utility and practical efficiency. More broadly, our findings suggest that multimodal safety cannot be enforced reliably without modeling the requested operation, the visual target to which it applies, and the confidence of that grounding.
Read the full abstract

All authors Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie, Huayue Gu, Chenyu Wang, Honghui Xu

Machine Learning

Delta2Gamma: Band-Wise Adaptive Contrastive Learning of EEG for Alzheimer's Disease Detection

Low-cost, scalable screening for dementia remains an open problem. Imaging-based diagnosis is costly and hard to deploy widely. Electroencephalography (EEG) is portable and inexpensive, but its recordings are noisy, vary widely across subjects, and carry few clinical labels. We tackle this with Delta2Gamma, a self-supervised framework that learns EEG representations from unlabeled data by contrasting augmented views of each signal. Rather than treat EEG as a single stream, Delta2Gamma decomposes every recording into the five canonical neural rhythms (delta, theta, alpha, beta, gamma). Each band gets its own encoder and projection head. Each also gets a temperature that is predicted adaptively during contrastive training, so bands with different signal statistics are balanced automatically. On the ADFTD cohort under a strict leave-one-subject-out protocol, Delta2Gamma separates Alzheimer's disease from cognitively normal controls with 92.4% accuracy. This exceeds both supervised backbones and recent dedicated EEG methods.
Read the full abstract

Discrete Mathematics · Cross-listed from math.CO

Completing the Boundary Case of the Mahmoodian-Mirzakhani Conjecture and 117 New Computational 5-Cycle Decompositions of Complete Tripartite Graphs

Let $K_{r,s,t}$, with $r\le s\le t$, denote the complete tripartite graph whose partite sets have sizes $r,s,t$. Mahmoodian and Mirzakhani gave three necessary conditions for $K_{r,s,t}$ to admit a decomposition into 5-cycles and conjectured that these conditions are sufficient. One of the conditions is $t\le 4rs/(r+s)$. We prove the conjecture for every odd triple on the extremal boundary $t = 4rs/(r+s)$. The proof is constructive. After reducing an arbitrary odd boundary triple to $(r,s,t)=(hga,hgb,hab)$, $a+b=4g$, we give an explicit cyclic decomposition of $K_{ga,gb,ab}$ and use the Mahmoodian and Mirzakhani scaling theorem to supply the common factor $h$. Together with the previously known all-even result, this settles the conjecture for every triple satisfying the boundary condition with equality. We also report explicit computer-generated $C_5$-decompositions for 117 odd triples satisfying the necessary conditions, 116 of which are strict-interior cases. To the best of our knowledge, all 117 cases were previously unresolved: no decomposition for any of them had been reported, and none of the 117 triples is covered by earlier existence results, constructions, or their recursive consequences. Moreover, these 117 certificates together with the boundary construction settle every previously unresolved triple satisfying the necessary conditions with fewer than $4400$ edges. Each computation is supplied as a machine-readable cycle-list certificate and can be checked independently by a short Python verifier. We also give a complete human-readable edge-label-matrix certificate for $K_{9,19,23}$.
Read the full abstract

Computer Vision

Probing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking

Training query-propagation end-to-end multi-object tracking (MOT) models requires dense bounding-box and identity annotations across video sequences, making dataset construction expensive. Clip-level active learning reduces this cost by selecting video clips for annotation, but prior acquisition criteria based on output-level temporal uncertainty may miss clips whose informativeness comes from association instability in propagated track states. We propose QPID (Query-Propagation Instability and Diversity), a clip acquisition method for query-propagation MOT that targets association instability in propagated track states. QPID estimates this instability by applying two-sided perturbations to internal track states and measuring prediction differences from a clean reference branch. The key idea is that, in stable clips, each propagated track should continue to follow the same target under small perturbations, whereas in ambiguous clips, small changes in the track state can alter which target the track follows, leading to changes in localization or confidence. QPID measures these perturbation-induced prediction differences with two metrics: Localization Drift and Entropy-Weighted Confidence Discrepancy. These metrics are aggregated into a clip-level association-instability score. To avoid redundant uncertainty-only selection, QPID selects a representative annotation batch from high-instability clips using Uncertainty-Weighted Visual Coverage with track-level visual prototypes. Experiments on DanceTrack and SportsMOT with MeMOTR and SambaMOTR show that QPID achieves strong performance compared with active learning baselines under the same annotation budget.
Read the full abstract

All authors Riku Inoue, Shogo Sato, Kazuhiko Murasaki, Tomoyasu Shimada, Toshihiko Nishimura, Ryuichi Tanida

Computation and Language

Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal

Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random, i.e., on temporal leakage. We audit this dependence on a 49,799-article corpus across 16 feature-model combinations spanning TF-IDF, MiniLM, FinBERT, and fine-tuned RoBERTa-large / DeBERTa-v3-large, plus separate zero/few-shot and LoRA probes of Llama-3 and Qwen2.5 LLMs: random splits inflate MCC by $1.1\times$ to $6.5\times$, tracking model capacity and feature richness, and end-to-end FinBERT fine-tuning re-amplifies rather than closes the gap (size-matched ratio $1.75\times$). Conditioning on event type, mergers and acquisitions (M&A) is the only audited category with a positive locked-test signal under near-temporal chronological evaluation (TF-IDF MCC $= 0.138$ train-only, $0.068$ under train$\cup$val refit; 10,000-permutation $p < 10^{-3}$); the signal does not transfer to FNSPID's 2009-2020 U.S. corpus, localising the headline to our 2024-2025 European-tilted M&A semantics rather than a universal predictor. Three independent role labellers converge on acquirer-tagged articles as the signal locus, a power-limited qualitative convergence rather than a hypothesis-tested asymmetry. Chronological splitting plays for financial NLP the role characteristics-purging plays for asset pricing: it strips the predictable, stale component of news and leaves a residual that is small, event-localized, and lexically shallow. We advocate leakage audits as a required disclosure for financial-NLP benchmarks.
Read the full abstract

All authors Chenhao Xue, Raslen Guesmi, Siwei Feng, Yucheng Gong, Jacob Xavier Sundram, Jordan Pang, Lan Wang, Julian Kaljuvee

Cryptography and Security

PACE: Policy-Attested Contract Execution for Safe AI Agents in Decentralized Finance

Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management. Because these agents rely on large language models (LLMs) to plan transactions, they inherit the LLM's susceptibility to prompt injection and lack of mechanisms to bind a verifier's approval to the exact transaction ultimately submitted on-chain. We present PACE (Policy-Attested Contract Execution), a transaction-level authorization framework that interposes between an LLM-based agent and on-chain execution. PACE introduces typed transaction intents, a deterministic policy verifier, and signed Policy Decision Records (PDRs) that cryptographically bind the approved intent, policy, and simulation report to the exact execution bytes, with replay and expiration protection. A Solidity smart account enforces PDR signatures on-chain with a measured overhead of 29,826-31,822 gas. We evaluate PACE against six baselines on 40 tasks spanning four attack categories plus benign utility (2,800 trials, 10 seeds). In our deterministic sandbox, PACE achieves a 0.00 unsafe execution rate and 0.00 false-positive rate on benign tasks, compared to 0.80 for the unguarded baseline. Ablation studies identify permissive policy settings (+57.5 pp) and the touched-contract allowlist (+12.5 pp) as the dominant safety components. To test whether the same deterministic floor holds for real model outputs, the artifact additionally provides a three-model live-LLM evaluation over the full task suite with repeated runs. A mainnet-fork harness is included for archive-RPC deployments, but fork results are reported only when the corresponding artifacts are generated. These auxiliary studies are separate from, and never substitute for, the deterministic benchmark. We frame our claims as logic-level safety within a reproducible benchmark rather than deployment-ready DeFi security.
Read the full abstract

All authors Rabimba Karanjai, Yang Lu, Richard Williamson, Hemanth Hm, Prakhar Mehrotra, Lei Xu, Weidong Shi

Computation and Language

The Plot Thins: Uniformity and Linearity in Literary Summaries

Works of literature are complicated; they balance plot, suspense, surprise, and artistic expression. Summaries of literature prioritize plot, and therefore may deviate from their sources. Using a combination of manual and LLM-based annotation, we construct a dataset mapping sentences from 150 novel summaries to their respective source chapters. We find the task unexpectedly difficult for both human and model annotators. Using the sentence-to-chapter mappings, we then measure summary linearity, the degree to which it maintains the source's order of events, and uniformity, the degree to which a summary spreads attention equally across a source. By examining when and how summaries break linearity and uniformity, we identify differences in how literary works and summaries express plot, particularly with regard to the clarity and prominence with which narrative details are described.
Read the full abstract

All authors Rebecca M. M. Hicke, Sil Hamilton, David Mimno, Ross Deans Kristensen-McLachlan

Monday 17 August

Human-Computer Interaction

Human-AI Collaboration at Scale: Task Criticality, Agency, and Friction across 250,000 Conversations

AI is increasingly embedded in professional work, yet how people actually collaborate with it at scale remains poorly understood. Drawing on a corpus of 249,834 real-world conversations, we conduct privacy-preserving analysis by asking three questions: what work people bring to AI, what roles humans retain in completing that work, and where human-AI collaboration breaks down. We find that users bring to AI not only trivial tasks but also consequential, hard-to-reverse work, with high criticality delegation concentrating in advisory and professional domains. As stakes rise, users engage more actively with AI output, and conversation length nearly doubles from ephemeral to high-stake tasks. We then examine human agency, the degree of control and responsibility users retain in completing the task. Human-led collaboration dominates overall, but users construct their level of agency through how they prompt and iterate. Across different levels of agency lies a common tension: does working with AI build human capability, or substitute for human effort? We examine this tension through AI-supported learning and upskilling, finding that active teaching is common (67% of conversations) but its benefits are unevenly realized. We further show that friction arises in roughly half of all conversations but it is often productive, and users often employ active strategies to recover from friction when it does occur. Together, these results map how humans and AI work together at scale and when that collaboration makes people more capable, and when it doesn't.
Read the full abstract

All authors Yijia Shao, Dora Zhao, Vishakh Padmakumar, Jennifer Wang, Diyi Yang

Social and Information Networks

Measuring the Influence of Modality-Specific Node Representations on Graphs

Multimodal attributed graphs combine graph structure with node text and image representations in recommendation and multimedia analysis. Graph predictors propagate these representations across connected nodes, so one input can change predictions at its own and nearby nodes. Measuring this distributed response reveals which modality-specific inputs a trained model relies on and how predictor design changes that reliance. We study influence measurement for modality-specific node representations. Given an encoded graph, a trained predictor, a training split, and fixed candidate representations, the task outputs one influence score per candidate and separate text and image rankings. We score a candidate by replacing it with its modality's training-node mean and comparing the original and changed predictions. Existing feature attribution and data valuation generally target one output, training examples, whole nodes, or graph elements rather than prediction changes across graph nodes. Our empirical study shows that nearby-node responses contain information missed by source-only scores and simple proxies, while response magnitude alone does not identify which class changes support the task. Guided by these observations, we propose MoGI (Modality-specific Graph Influence). It propagates training labels to define task direction, reads the same replacement response for the favored class and full class distribution, and averages the resulting ranks. MoGI requires no predictor retraining or learned scoring parameters. Under a shared five-dataset, eight-predictor benchmark, it achieves the largest aggregate held-out loss increase against all five external methods at every tested ranking cutoff.
Read the full abstract

All authors Xu Wang, Xunkai Li, Yinlin Zhu, Rong-Hua Li

Cryptography and Security

The hidden life of signals: Time-domain inferences and other privacy attacks on everyday devices

In privacy research on radiofrequency-based protocols, the dominant focus has remained on Bluetooth, WiFi, and Zigbee, while a broader and arguably more consequential attack surface has gone largely unnoticed: the privacy risks created by the composition of everyday wireless protocols. Widely deployed systems such as KeeLoq remotes, vehicle TPMS sensors, and other sub-GHz devices continuously emit metadata and timing structure that, when analyzed jointly rather than in isolation, enable powerful behavioral inference. This work-in-progress paper argues that privacy leakage in these environments is not merely a property of individual protocols, but an emergent property of their interaction, correlation, and composition across devices, spaces, and routines. The resulting attack surface arises both from protocol metadata that directly degrades privacy and from the latent relationships between devices and the ways users move among and interact with them over time. We present preliminary evidence that these composed signals expose underappreciated opportunities for inference and tracking, and we outline a research agenda for characterizing and mitigating this broader class of privacy failures.
Read the full abstract

Cryptography and Security

Trouble at the top: can Python extend the chains of trust in infrastructure firmware?

Compiled Python bytecode (PYC) has become an essential part of network switches, routers, and other network infrastructure devices. Our analysis shows that its integrity is implicitly trusted in multiple designs that make use of Python code at the top of the operational software, such as the management and control pane of enterprise network switches. At the same time, the integrity of PYC files is not covered under the traditional chain-of-trust models, due to complex interactions with the CPython loader, byte compiler, and other Python runtime components. We explore the risks inherent in including PYC and Python runtimes in the de facto trusted code basis of commercial enterprise equipment and offer a comprehensive framework for understanding emergent behaviors in these designs.
Read the full abstract

Information Theory · Cross-listed from quant-ph

Improved Transversal Non-Clifford Gates from Cup Products

It is a major challenge in quantum fault-tolerance to obtain low-overhead protocols for performing non-Clifford gates. In this vein, we construct quantum codes with low-weight stabilizers that support transversal (i.e. low-depth) implementations of the non-Clifford $C^{r-1}Z$ gate, for every constant $r\geq 3$. In particular, we obtain length-$n$ quantum LDPC codes (with constant-weight stabilizers) of polynomial distance $d\geq n^{(1-\epsilon)/r}$ supporting transversal $C^{r-1}Z$ gates on a close-to-linear number $k\geq n^{1-\epsilon}$ of disjoint tuples of logical qubits, for arbitrarily small $\epsilon>0$. Our construction is the first with constant-weight stabilizers that obtains $dk\gg n$, and as a consequence achieves arbitrarily small magic state overhead exponent $\gamma=\log(n/k)/\log(d)>0$. Comparable prior constructions instead required at least polylogarithmic stabilizer weight. We also show how to obtain linearly many $k=\Omega(n)$ logical $C^{r-1}Z$ gates, though with stabilizer weight and physical circuit depth $n^\epsilon$. We show that our transversal gates also support addressing (i.e. targeting) of specific logical qubits. To obtain our codes, we develop a general transformation based on cup products that maps classical codes satisfying a multiplication property to quantum codes with transversal $C^{r-1}Z$. We apply this transformation to a new family of classical Tanner codes that we construct from punctured tensor products of algebraic codes.
Read the full abstract

Data Structures and Algorithms

Faster Minimum k-Cut II: Improved Randomized and Deterministic Algorithms for Weighted Graphs

The Minimum $k$-Cut problem asks for a minimum-weight set of edges whose removal leaves an undirected weighted graph with at least $k$ connected components. We consider only $k\ge3$. The fastest previous algorithm for weighted graphs ran in $n^{k-2}(m+n)(\log n)^{O(k^2)}$ randomized time~\cite{LV26}; on dense graphs this is $\widetilde O_k(n^k)$, and for $k=3$ it gives an $\widetilde O(nm)$-time algorithm. We improve the dense-graph exponent from $k$ to $k-1$ and obtain the same exponent deterministically. After aggregating parallel edges in $O(m)$ time, our randomized algorithm runs with high probability in \begin{equation*} k^{O(k^2)}n^{k-1}\log^2n \end{equation*} time, while our deterministic algorithm runs in \begin{equation*} k^{O(k^2)}n^{k-1}\log^{O(1)}n \end{equation*} time. In particular, weighted Minimum $3$-Cut can be solved in $O(n^2\log^2 n)$ randomized time and in $\widetilde O(n^2)$ deterministic time. The algorithms have two main components. First, we give a faster algorithm for weighted Minimum $3$-Cut. After handling optima with a very small side and optima with two light sides, the remaining optimum has a unique structured side. Tree packing reduces its completion to a batched collection of $2$-respecting cut problems. Second, we reduce Minimum $k$-Cut to Minimum $3$-Cut by enumerating a bounded family of light-cut candidates and recursively completing either side of each candidate. If the enumeration produces too many cuts, then we can instead produce an optimum $k$-cut directly. We derandomize the $3$-cut algorithm using a deterministic near-minimum-cut skeleton, and derandomize the reduction using a specialized $4$-cut algorithm using the skeleton, the constructive light-cut bounds, and the deterministic spectral sparsifier of \cite{BSS12}.
Read the full abstract

Computer Vision

DMM-Align: Closed-Loop Optimization for 2D-3D Registration with Dual-Role Diffusion

2D-3D registration remains brittle in challenging scenarios such as low overlap, occlusion, repetitive structures, and severe cross-modal ambiguity. A key reason is that existing methods improve representation learning, correspondence estimation, or pose computation in isolation, while the dominant failure mode is inherently cross-level, where errors propagate between features, correspondences, and pose. To address this limitation, we propose DMM-Align: Diffusion-based Matching Matrix Alignment, a closed-loop framework that couples correspondence refinement, pose estimation, and representation learning through a shared differentiable geometric state. Our method leverages diffusion in two coordinated roles: a geometry-aware diffusion process refines the soft matching matrix for robust correspondence estimation, while a geometry-conditioned diffusion teacher injects pose-induced supervision back into feature learning. These processes are connected via a differentiable geometric hinge that converts correspondences into a global pose and exposes geometric inconsistency to upstream modules. Extensive experiments on 7-Scenes and RGB-D Scenes V2 demonstrate that DMM-Align consistently outperforms strong baselines, especially under low-overlap and heavy-occlusion conditions, highlighting the effectiveness of closed-loop geometric feedback for robust 2D-3D registration.
Read the full abstract

Computer Vision

DualStabSleepNet: A Dual-Domain Diffusion Stabilization Network for Robust Sleep Staging

Existing deep learning approaches for automatic sleep staging suffer from limited robustness under heterogeneous recording conditions, where non-stationary noise, inter-subject differences and cross-dataset distribution shifts cause unstable features and poor generalization. This work proposes DualStabSleepNet (DSSNet), a dual-domain diffusion stabilization network for robust sleep staging, which improves robustness in both data and feature domains. After preprocessing multi-channel polysomnography (PSG), a continuous-scale diffusion-based stabilization module suppresses noise while preserving physiological signal structures. Stabilized signals are converted to time-frequency representations and fed into a Vision Transformer backbone. A teacher-student guided diffusion feature stabilization module further mitigates feature drift and enforces multi-level feature consistency. Evaluated on four public PSG datasets SleepEDF-20, SleepEDF-78, SHHS and ISRUC-S3, DSSNet achieves state-of-the-art accuracy of 89.2%, 88.0%, 89.7%, 86.7% with improved macro-F1 and Cohen's kappa. It obtains notable improvements on hard transitional stages (e.g., 12.5% gain for N1 on SHHS) and boosts N2/REM recognition. Under cross-dataset settings, DSSNet is robust to distribution shift and performs on par with or superior to target-dataset trained baselines, demonstrating its practical potential for real-world sleep staging across heterogeneous cohorts.
Read the full abstract

All authors Chongjian Wang, Chen Liu, Junjie Gao, Xiaofang Zhong, Shiyuan Han, Tong Zhang

Artificial Intelligence

Ask Which, Not How Good: Sizing Benchmarks Scored by an LLM

Benchmarks scored by an LLM judge routinely adjudicate differences of a tenth of a point, but the resolution of those benchmarks has never been measured. Existing sample-complexity work covers accuracy benchmarks and leaves the judged case open. Treating the system as the object of measurement, we decompose 373,019 judgments into system, item, judge and interaction components using generalizability theory. The central result is structural: under a single judge, generalizability asymptotes to sigma2_s/(sigma2_s+sigma2_sj) regardless of item count, because the system-by-judge term carries no n_i. Items saturate; judges do not. The item cost of a target diverges as the target nears that ceiling. The ceiling is a property of pointwise rubric scoring, not of LLM judging. Run as a pairwise preference in both presentation orders, sigma2_sj falls two orders of magnitude below sigma2_s and the ceiling rises to 0.986 (bootstrap [0.934, 1.000] on 11 systems), so one judge suffices. Pairwise buys a different problem: a system presented first wins 8.6 percentage points more often than the same system presented second, a bias 1.23x the median improvement claimed in the 53 published win-rate comparisons we recovered. Protocol design dominates panel size. Measured floors are 0.41-1.24 points on a 0-5 scale at native item counts, against a median reported improvement of 0.28 points; on the one benchmark recurring often enough for an exactly matched comparison, all 17 recovered MT-Bench improvements fall below MT-Bench's own floor, and 70% of the win-rate claims fall below the pairwise floor. An audit of 628 arXiv papers, double-coded by two independent models and validated against blind human coding (kappa=0.73), finds fewer than one paper in four states whether its evaluation was run more than once, and only 46-67% report uncertainty of any kind.
Read the full abstract

Computational Engineering · Cross-listed from q-fin.RM

Financial Tail Risk Beyond Lipschitz Continuity via Semi-Discrete Optimal Transport

Financial returns are heavy-tailed, and accurate tail risk estimation is central to portfolio risk management. Modern neural generators sample by pushing a simple base distribution through a learned map, and for training stability that map is built from Lipschitz components. This is the binding constraint: a Lipschitz map of a Gaussian is sub-Gaussian, so heavier-tailed targets admit no exact match at any finite Lipschitz constant. The Monge–Ampère equation ties the Brenier map's local distortion to the density ratio $f/(g\circ T)$, so a deeper trough in the target density requires a higher-gain map and yields a higher-variance estimator. The argument needs only bounded distortion, so it covers normalizing flows, flow matching, GANs, and diffusion samplers alike. Semi-Discrete Optimal Transport (SDOT) relaxes the map's regularity rather than the source's tail class. Its power diagram gives every training observation a cell holding exactly $1/N$ of the source measure, and tail observations are reached by crossing a cell boundary rather than by stretching. Our primary experiment sweeps severity over a calibrated Merton jump-diffusion spanning kurtosis 94 to 1,679. SDOT holds tail ratios at $0.85$–$0.94$ with cross-seed standard deviations below $0.025$, while every learned generator either compresses the tails or inflates them with a variance that grows alongside. Further experiments carry the result to real S&P~500 returns and to a 21-year backtest, where SDOT gives the best risk-adjusted market-neutral strategy under CVaR optimization (Sharpe $0.70$, max drawdown $-2.60\%$, against $0.40$ for the next-best generator).
Read the full abstract

Information Retrieval

EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QA

Semi-structured documents are ubiquitous in scientific reports, financial statements, and technical manuals. Question answering over such documents requires simultaneous understanding of text, tables, charts, and complex hierarchical layouts. Existing methods either rely on repeatedly calling large language models for structure parsing and retrieval, leading to high cost and large latency, or they flatten the document and lose layout and hierarchy information, sacrificing answer accuracy. To address this, we propose EidosDoc, a novel system that achieves state-of-the-art accuracy with minimal computational expense. Our approach introduces three core innovations. (1) An Implicit Structure Encoder trained via contrastive learning and a structure consistency loss. This module jointly embeds hierarchical relationships, spatial positions, and textual content into a dense vector space, capturing document structure holistically without the need for manually defined and error-prone constructions. (2) A Hybrid Retrieval Pipeline that leverages BM25, layout fingerprints, and a lightweight cross-encoder to perform high-precision retrieval entirely without invoking an LLM, drastically reducing cost and latency. (3) A Dynamic Evidence Expansion mechanism that adaptively retrieves spatially adjacent and structurally related evidence, overcoming the evidence omission common in fixed-path retrieval methods. We evaluate EidosDoc on four benchmarks, and comprehensive evaluations show that EidosDoc achieves a new state-of-the-art accuracy on the four benchmarks. Crucially, it does so with a 50 times reduction in cost and 4 times lower latency compared to the previous state-of-the-art Method. These results demonstrate that EidosDoc establishes a new optimal trade-off among accuracy, cost, and speed, offering a practical and scalable path for accurate semi-structured document analysis.
Read the full abstract