Peer Revenue Play credits. Real papers.

Papers

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

Computer Science

cs Watch Computer Science

Saturday 12 September

Software Engineering

Deterministic Temporal Reconciliation for Effective-Dated Identity Lifecycle Events

Pramod Ubbala

Identity lifecycle automation processes workforce changes that carry two distinct notions of time: when a business fact becomes effective and when an authoritative source last revised it. Corrections, cancellations, future-dated changes, duplicate delivery, and out-of-order arrival can therefore produce divergent account states when processors rely on transport order or effective time alone. This paper presents a deterministic temporal reconciliation method for effective-dated identity events. The method separates logical business facts from their physical revisions, deduplicates exact replays, selects the authoritative revision of each fact using transaction-time freshness, removes canceled facts, and then applies surviving facts in valid-time order. We establish permutation invariance, replay idempotence, revision dominance, and deterministic snapshot construction under explicit source assumptions. A reproducible synthetic fault-injection benchmark compares the method with arrival-order, effective-time, and transaction-time processing. Across 250,000 generated identity histories and 1,585,589 delivered records, the proposed method reconstructed the separately retained authoritative final state in all tested cases. At 75% delivery disorder, exact-state accuracy was 42.35% for arrival-order processing, 85.38% for effective-time sorting, 76.61% for transaction-time sorting, and 100% for the proposed method. A separate 40,000-permutation experiment produced the same final state for every tested permutation under the proposed reconciliation contract.
Read the full abstract

Information Retrieval

TF-IDF and BM25 Are Exact KL Divergences

Ivan Silajev

TF-IDF and BM25 are two of the most widely used methods for scoring query-document relevance, yet neither has a standard probabilistic derivation that justifies it as a statistical method within a unified framework. We address this gap by showing that both scoring methods admit an exact interpretation as Kullback-Leibler divergences between two probability models. We treat the BM25 variant that includes the plus 1 correction in the IDF term, which is the one used in practice, and also discuss the original BM25 formulation without that correction. The resulting framework provides a common theoretical basis for TF-IDF and BM25, clarifies what they measure, and allows them to be compared theoretically with other information retrieval methods rather than only experimentally.
Read the full abstract

Artificial Intelligence

Schizophrenia Detection from EEG Signals: A Transformer Framework with Spectrogram Representation

Abtin Shafiei, Mohsen Hooshmand and Majid Ramezani

Schizophrenia is a serious psychiatric disorder that affects millions of people worldwide, and its diagnosis remains primarily dependent on clinical assessment. Electroencephalography (EEG) provides a non-invasive approach to investigate brain activity and has shown potential to support automated Schizophrenia detection. However, existing EEG-based classification studies often suffer from limitations including small datasets, inconsistent preprocessing strategies, and evaluation protocols that may not adequately prevent subject-related data leakage. In this study, we propose an EEG-based Schizophrenia classification framework that transforms preprocessed EEG recordings into time-frequency representations using the Short-Time Fourier Transform. The generated spectrogram images are classified using both conventional Machine Learning algorithms, including Support Vector Machines, Random Forests, and XGBoost, and Deep Learning models, including convolutional architectures and CNN-Transformer hybrids. To ensure reliable evaluation, all data partitions are performed at the subject level, and image-level predictions are aggregated into subject-level decisions. On the independent test set of 18 subjects, the CNN-Transformer (CT-SZ) model achieves a subject-level AUC-ROC of 95.00%, while the CNN + Squeeze-and-Excitation + Transformer (CST-SZ) model achieves 92.50%.
Read the full abstract

Information Theory

Polarforming-Enabled Power-Splitting SWIPT: A GNN-Based Optimization Approach

Hamed Aghaei-Karkaj, Kamran Ebrahimi, Zahra Mehrzad et al. (+3 more)

Simultaneous wireless information and power transfer (SWIPT) is a critical technology for the future of the Internet of Things (IoT). However, ensuring a stable power supply in such networks remains a significant challenge. This work introduces dynamic polarization control as an additional degree of freedom (DoF) in SWIPT systems. We propose a system where both the base station (BS) and the users can adjust their antenna polarization, a technique known as polarforming. In addition, each user device is capable of splitting the incident signal to perform simultaneous information decoding (ID) and energy harvesting (EH). The resulting non-convex optimization, with many coupled variables, is solved using a graph neural network (GNN) that learns the sub-optimal beamforming, polarization, and power-splitting variables. Simulation results demonstrate that the proposed GNN-based dynamic polarforming optimization significantly outperforms fixed-polarization schemes, particularly under imperfect channel state information (CSI). Moreover, joint polarforming and GNN-based optimization maintain robust SWIPT performance under both polarization mismatch and imperfect CSI.
Read the full abstract

All authors Hamed Aghaei-Karkaj, Kamran Ebrahimi, Zahra Mehrzad, Mohammad Robat Mili, Symeon Chatzinotas, Ioannis Krikidis

Artificial Intelligence

Convergent Emergence of In-Context Learning Across Modalities

Nathan Breslow, Seungwook Han, Daniel Hyunsoo Lee et al. (+3 more)

Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples provided in its prompt and apply them to new inputs, has been extensively studied in large language models trained for next-token prediction on human text. Recently, few-shot ICL has been demonstrated in autoregressive genomic models as well. This raises a question: does ICL emerge broadly across domains, and if so, what common structure is shared? To address both, we develop a controlled cross-modality framework that instantiates the same task suite in a variety of modalities to test what we call the Convergent Emergence Hypothesis: the idea that few-shot ICL, when it emerges, shares a common cross-modality difficulty profile - i.e., tasks that benefit from ICL in one modality tend to benefit in others. We show that paired-mapping ICL emerges across six modalities (language, genome, integer sequences, time series, images, and proteins), surpasses controlled baselines, and has correlated per-task effects across five of them. Together, these results provide support for the Convergent Emergence Hypothesis in some modalities, but not all.
Read the full abstract

All authors Nathan Breslow, Seungwook Han, Daniel Hyunsoo Lee, Aayush Mishra, Anqi Liu, Daniel Khashabi

Computer Vision

CirrGuide: A Deep Cascaded Framework for Liver Cirrhosis Segmentation and Severity Classification from T2-Weighted MRI

Muntaqim Ahmed Raju and Ruizhe Ma

We present CirrGuide, a deep cascaded framework for cirrhotic liver segmentation and severity classification. Cirrhosis causes progressive structural changes in the liver and can lead to serious clinical complications, making severity assessment important for disease monitoring and treatment planning. However, severity classification is challenging because imaging patterns are often subtle, spatially variable, and similar across adjacent stages. CirrGuide addresses this by explicitly linking localization with classification. A ResNet50 encoder with an Attention U-Net decoder first predicts a soft cirrhotic liver mask, which is then used as an anatomical prior in a ResNet50-based classification branch. This branch combines global multi-scale features with mask-guided attention-pooled regional features to classify Mild, Moderate, and Severe cirrhosis. On the official CirrMRI600+ T2-weighted (T2W) 2D split, CirrGuide achieves 89.83% Dice and 84.14% mIoU for segmentation, 69.58% accuracy and 61.55% macro F1-score for severity classification. Compared with segmentation-only, classification-only, and multi-task baselines, CirrGuide improves both localization and severity classification, demonstrating the benefit of using predicted cirrhotic liver masks as anatomical priors for cirrhosis analysis.
Read the full abstract

Information Theory

Finite-Mask Gaussian-Process Reconstruction on a Periodic Sensor Ring: Mask-Geometry Dependence, Fourier-Mode Coupling, and Posterior Trace

Jun Tsuzurugi

We analyze how an arbitrary observation mask on a finite periodic ring of equally spaced sensors affects the posterior covariance, Fourier-mode coupling, and normalized posterior trace in Gaussian-process reconstruction. Under a rotationally stationary prior and homogeneous independent measurement noise, complete observation gives independent scalar posterior formulas for the Fourier modes. For an arbitrary mask, however, the matrix $Q_M=F D_MF^\ast$ is generally non-diagonal; its off-diagonal entries are finite Fourier components of the realized mask and couple modes in the posterior precision. Consequently, masks with the same unavailable-channel fraction can have different normalized posterior traces because their geometries differ. A dimensionless 64-channel synthetic benchmark illustrates this finite-matrix effect. A circumferential array of equally spaced wall-mounted microphones at a fixed axial station of a circular fan or compressor duct provides one concrete mechanical-engineering interpretation: failed, saturated, corrupted, or dropped-out channels form the observation mask. The analysis is a finite-dimensional reference calculation under the stated rotational-stationarity and common-noise assumptions, not a performance claim for a nonuniform or unequally instrumented operating duct.
Read the full abstract

Information Theory

GNN-Based Polarforming for Multi-User MISO Short-Packet URLLC under Imperfect CSI

Zahra Mehrzad, Hamed Aghaei-Karkaj, Rahman Saadat Yeganeh et al. (+4 more)

This paper investigates polarization-aware transmission for multi-user multiple-input single-output (MU-MISO) short-packet ultra-reliable low-latency communications (URLLC) under imperfect channel state information (CSI). We consider a system in which the base station (BS) and users are equipped with polarization-reconfigurable antennas that enable adaptive polarization states through controllable polarization coefficients. A multi-objective optimization problem is formulated to jointly maximize the finite-blocklength (FBL) achievable sum rate and minimize the maximum decoding error probability (DEP), subject to transmit-power, latency, reliability, and discrete polarization-control constraints. The resulting multi-objective problem is scalarized using a normalized weighted-sum utility. To enable low-complexity online decision-making, a heterogeneous graph neural network (GNN) is developed to learn the joint mapping from estimated polarized CSI to digital beamforming and transmit/receive polarforming vectors (PFVs) while accounting for the system constraints. Numerical results demonstrate that the proposed GNN-based polarforming (PF) framework substantially improves the FBL sum rate while reducing the maximum DEP compared with conventional fixed-polarization schemes, particularly under channel depolarization and imperfect CSI. This highlights the potential of adaptive polarization control for reliable low-latency transmission.
Read the full abstract

All authors Zahra Mehrzad, Hamed Aghaei-Karkaj, Rahman Saadat Yeganeh, Kamran Ebrahimi, Mohammad Robat Mili, Symeon Chatzinotas, Ioannis Krikidis

Sound

StepAudio 3 Realtime Technical Report

Bin Lin, Bo Zhao, Boyang Zhang et al. (+87 more)

Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a continuous listen-converse-think-act loop. Deep Perception captures rich acoustic cues to interpret user intent, while Seamless Duplex models synchronized audio streams to handle pauses, backchannels, and interruptions naturally. Crucially, we resolve the tension between deep deliberation and latency via Think-While-Speaking, executing private reasoning in parallel with spoken delivery. In reasoning mode, StepAudio 3 reaches a 73.0 macro average on StepAudioChat. With Think-While-Speaking, it achieves dialogue and reasoning performance comparable to dedicated reasoning models while speaking in real time. Furthermore, an integrated Voice Agent handles asynchronous tool execution without disrupting the dialogue flow. StepAudio 3 Realtime achieves top-tier performance across key dimensions: an exceptional 90.6 on the MMSU benchmark, 98.9 Overall on the Artificial Analysis Full-Duplex Bench, and a 56.0% macro task-success rate on $\tau$-Voice.
Read the full abstract

All authors Bin Lin, Bo Zhao, Boyang Zhang, Boyong Wu, Chao Yan, Chen Geng, Chen Wu, Cheng Yi, Chengli Feng, Chenglin Zhu, Chengting Feng, Chengyuan Yao, Daijiao Liu, DanNi Wan, Daxin Jiang, Dongjian Li, Dongqing Pang, Fei Tian, Feng Tian, Future Li, Gang Yu, Guanglong Yang, Haoyang Zhang, Hongyuan Wang, Jia Peng, Jiahao Song, Jialong Xue, Jiamin Fan, Jiangjie Zhen, Jianzheng Gao, Jincheng Wen, Jinghua Liang, Jinglan Gong, Jun Chen, Li Xie, Liang Zhao, Lifang Zhang, Lingli Ji, Lun Cai, Min Xu, Peilin Li, Peng Yang, Pengfei Tan, Qingjian Lin, Qinxin Du, Ruijie Xiong, Runze Li, Shenghua Hu, Shengqian Qin, Shi Qiu, Siqi Tu, Siyi Zhou, Tianjiao Deng, Wanying Lu, Weiming Niu, Wen Sun, WenWen Qu, Xiangyu Zhang, Xianwei Zhang, Xiaosu Su, Xing Chen, Xinyu Liu, Xuerui Yang, Yan Wu, Yang Li, Yang Yang, Yechang Huang, Yibo Zhu, Yifan Zhang, Yinuo Yan, Youjun Chen, Yu Fu, Yu Luo, Yu Zhou, Yujie Chen, Yumang Wang, Yunzhou Ju, Yuxiang Yang, Yuxin Li, Yuxin Zhang, Zekai Liu, Zengwei Yao, Zhaoxin Yuan, Zhenwei Mou, Zhiquan Zhang, Zhiyue Wu, Zichao Li, Zichao Zhou, Ziqi Ren, Zixuan Wang

Systems and Control · Cross-listed from math.OC

Distributed Convex Second-Order Optimization for AC/DC Hybrid Distribution Systems within PROcess Orchestration Framework

Xinliang Dai, Yuning Jiang, Junyi Zhai et al. (+5 more)

Existing operation formulations for AC/DC distribution grid often oversimplify the interplay of AC/DC interconnections and VSC characteristics. Moreover, current distributed algorithms depend on gradient-based methods, which achieve only linear convergence rates and struggle to scale efficiently for large systems. This paper proposes a convex ALADIN variant that exploits second-order derivatives of convex subproblems, achieving locally quadratic convergence for distributed nonlinear but convex optimization problems. Then, this convex ALADIN is applied to a separable AC/DC OPF model for AC/DC hybrid distribution grid, explicitly incorporating complicated AC/DC interconnections and multiple droop-controlled VSCs while retaining computational traceability. To bridge theory with practice, we implement the distributed convex second-order optimization framework using the PROcess Orchestration Framework, a co-simulation platform that automates workflow design, model integration, and distributed execution via a user-friendly graphical interface, eliminating manual coding. Numerical results illustrate effectiveness of the proposed model.
Read the full abstract

All authors Xinliang Dai, Yuning Jiang, Junyi Zhai, Jianlei Liu, Thorsten Schlachter, Colin N. Jones, Xiao-Ping Zhang, Veit Hagenmeyer

Cryptography and Security

Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula et al. (+4 more)

Personal AI agents built on large language models (LLMs) are increasingly given access to a user's private data and communications in order to provide personalized assistance. This access creates a persistent privacy risk: the agent must decide whether a given sensitive information should be disclosed to a particular party. Existing defenses address this by making the agent's backend LLM more privacy-preserving through stronger system prompts, training, or explicit consent-checking procedures, but this approach has a structural challenge: whenever enforcement is a judgment the LLM makes over the same conversational context an adversary controls, the enforcement mechanism and the attack surface coincide. We demonstrate this against existing defenses with three new attacks that require only ordinary agent interaction and no prompt injection: Collaborative Workspace Lure reframes an extraction attempt as collaborative work; Semantic Obfuscation Attack induces disclosure through omission rather than through anything the agent writes; and Channel Decoupling Attack splits the extraction request and the disclosure across independent channels. All three achieve substantially higher leak rates than the attacks these defenses were originally designed to withstand. Guided by this observation, we present FLOWSEAL, a defense that enforces confidentiality through a tool-level interceptor outside the LLM's context, grounded in data provenance and an information-flow-control lattice with controlled declassification. Evaluated across three benchmarks, five prompt-based baselines, and eight attacks, including a real agent executing live tool calls through MCP, FLOWSEAL reduces leak rates to near zero (e.g., 52.2% to 0.5% against Collaborative Workspace Lure) while preserving task utility, regardless of the underlying LLM backend.
Read the full abstract

All authors Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula, Kaiwen Zhou, Xin Liu, Xin Eric Wang, Zhou Li

Computation and Language

Unlocking the Unsolvable: Teacher-Guided Curriculum for Data-Efficient RLVR

Yukang Zhu and Zhen Han

Reinforcement Learning with Verifiable Rewards (RLVR) has shown remarkable success in improving the mathematical reasoning of large language models. Yet problems beyond the model's current capability, where rollouts uniformly fail and no learning signal is produced, are structurally wasted despite marking the most informative training frontier. We show that these otherwise-inert problems can be unlocked via teacher-guided curriculum learning: partial reasoning traces from a stronger model create a graded difficulty landscape, and a backward-chaining curriculum progressively withdraws guidance until the model solves problems unaided. Training on only 128 unsolvable problems matches or exceeds GRPO trained on a full 2,000-problem corpus (~16x data efficiency) on the nine-benchmark average for both base models, while substantially expanding the reasoning boundary measured by pass@k at large k. Furthermore, we identify a distribution-shift cost that is particularly acute in the unsolvable-only regime and propose Monotone Frontier Curriculum (MFC), a method that monotonically drives training toward unguided solving, consistently outperforming existing curriculum methods.
Read the full abstract

Artificial Intelligence

Synthetic Data in Marketing Research: How to Evaluate and When to Trust

Oded Netzer and Rajan Sambandam

Debate over synthetic data in marketing research has polarized between claims that large language models (LLMs) make human respondents obsolete and calls to avoid them entirely. We argue that both positions obscure the more useful question: not whether synthetic respondents work, but when. Building on Brand, Israeli, and Ngwe (2026), we make three contributions. First, we distinguish three types of synthetic data (ungrounded LLM responses, segment-level personas, and individual-level digital twins) and map each to the decisions it can support. Second, we develop a taxonomy of four families of accuracy measures and suggest that the wide range of reported twin accuracy, from near-perfect to near-chance, largely reflects differences in what is being measured rather than in method quality. Aggregate measures often perform well even when little information is supplied to the LLM, and can mask a complete absence of respondent-level differentiation. Third, we introduce the forgotten question problem, in which a question is omitted from a fielded study, as a setting for twin-based augmentation of existing data. We propose an ex-ante answerability diagnostic that requires no ground truth: the R^2 of a random forest predicting twin outputs from the data used to construct the twins. Across 108 attitude questions from a nationally representative survey (N = 3,063), screening at R^2 above 0.7 raises the mean twin-human individual-level correlation by 15% and reduces the share of poorly answered questions from 25.9% to 4.3%. Embedding similarity and experienced-researcher judgment provide correlated but weaker screens.
Read the full abstract

Information Retrieval

P$^3$Rec: Distilling Prior–Posterior Preference Reasoning for LLM-based Recommendation

Jinfei Chen, Weihai Lu and Jiawei Cheng

Large language models (LLMs) exhibit strong semantic understanding and preference reasoning capabilities, offering new opportunities for user modeling in recommender systems. Existing LLM-as-Enhancer methods typically distill LLM-derived preference knowledge into lightweight recommenders to avoid costly online LLM inference. However, they often construct distillation knowledge from only one perspective. Prior preference captures users' stable and consistent interests but provides limited guidance for the current decision, whereas posterior preference reveals target-relevant fine-grained interests but may rely excessively on target clues. To address these limitations, we propose P$^3$Rec, a framework that jointly extracts and internalizes complementary prior and posterior preference reasoning knowledge. Specifically, P$^3$Rec first derives target-agnostic prior preferences and target-conditioned posterior preferences from the user side, while further extracting item-centric preference representations from item semantics and predecessor interactions. It then progressively internalizes prior and posterior knowledge into behavioral representations through prior preference absorption and posterior-guided preference distillation. Since the resulting comprehensive preference representation may not always provide an equally decisive retrieval direction, P$^3$Rec further characterizes historical interest dispersion with interest entropy and adaptively calibrates the user representation before contrastive retrieval optimization. In this way, P$^3$Rec achieves more complete preference reasoning while preserving efficient recommendation. Extensive experiments on multiple public datasets demonstrate its effectiveness.
Read the full abstract

Computer Vision

Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion Decoding

Yongyi Lu, Xiongfeng Huang and Zhijing Yang

Reconstructing 3D objects from brain signals offers a promising avenue for understanding human visual cognition. While prior work has shown initial success using EEG signals for 3D reconstruction, existing methods typically employ a uniform diffusion decoder, overlooking the evolving semantic granularity of both EEG representations and the diffusion denoising process. In this paper, we propose Mind2Cloud, a novel EEG-to-point-cloud generation framework based on two-granularity diffusion decoding. The core of Mind2Cloud is a time-aware decoder that integrates a global Transformer branch and a local Point-Voxel CNN (PVCNN) branch across diffusion timesteps through a learnable fusion mask. Specifically, Transformer layers are incorporated into the early upsampling stages to capture global object structure under high uncertainty, while PVCNN modules are used in later stages to refine local geometric details. Inspired by the hierarchical nature of EEG-based visual representations, this design dynamically adapts its spatial granularity in accordance with the coarse-to-fine trajectory of diffusion denoising. We further introduce an adversarial refinement module to enhance geometric realism and semantic consistency. Extensive experiments on the EEG-3D dataset across all 12 subjects demonstrate that Mind2Cloud outperforms prior work in both geometric accuracy and semantic alignment, setting a new benchmark for EEG-to-point-cloud generation. Our source code is available at https://github.com/duasoi/Mind2Cloud.
Read the full abstract

Systems and Control

Diffusion-Based Multiple-Shooting Indirect Optimal Control for Fuel-Optimal Spacecraft Trajectory Generation

Saeid Tafazzol, Ehsan Taheri and Ryne Beeson

Diffusion-based generative models (DMs) have found applications in control problems, and in particular robotics, where the DMs enable exploration of possible control solutions. A critical shortcoming of these applications is that they have lacked optimality guarantees. This is a problem for their potential use in fuel-optimal spacecraft trajectories that are characterized with long time-horizons and bang-bang profiles. Alternatively, indirect optimal control methods ensure explicit satisfaction of necessary conditions, but are highly sensitive to the initial costate estimation needed to solve the resulting Hamiltonian boundary-value problems (HBVPs). To alleviate this sensitivity and enlarge the convergence domain of HBVPs, advanced indirect methods have been developed that use smoothing approaches and continuation. We propose a diffusion-based multiple shooting indirect control method that combines the exploration capability of DMs with indirect method to generate fuel-optimal spacecraft trajectories. We benchmark our method against an advanced indirect method on a fuel-optimal Earth-Mars low-thrust transfer problem, showing higher convergence robustness than the advanced indirect method that is based on random costate initialization. Code and visualizations are available at https://saeidtafazzol.github.io/Diffusion_Indirect_Control/.
Read the full abstract

Multimedia

A Low-Latency Interactive System for Real-Time Video Understanding Based on VLMs

Punan Dai, Jun Xu, Bingcong Lu et al. (+4 more)

Vision-language models are extending video understanding from offline clip analysis to continuous interactive streaming, but most research still emphasizes model capability rather than deployable low-latency interaction. This paper presents a unified edge-cloud system for real-time video VLM applications. Lightweight phone, smart glasses, PC, and pseudo-replay clients publish video and speech to a server runtime that provides shared ASR/TTS, session orchestration, backend adaptation, response delivery, and archive-backed measurement. The system integrates six representative video VLM backends with streaming or interaction-oriented capabilities and evaluates them across backend runtime, media transport, client-observed latency, and interaction behavior. With suitable backend selection and the WebRTC path, the tested system reaches approximately 0.9 to 1.0 s to first VLM text and 1.3 to 1.5 s to first non-silent TTS audio, while exposing backend adaptation costs and differences in real-time interaction behavior.
Read the full abstract

All authors Punan Dai, Jun Xu, Bingcong Lu, Zhengxue Cheng, Hongwei Hu, Ronghua Wu, Li Song

Robotics

What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency

Luoyang Sun, Guoyang Xia, Fengfa Li et al. (+9 more)

Vision-Language-Action (VLA) models combine a pretrained vision encoder, a language backbone, and an action head, but their relative contribution has not been established under controlled, latency-paired conditions. We fix the backbone families (SigLIP2 and Qwen2.5) and the training pipeline, sweep action-head design and module scale, and pair each configuration with measured on-device latency. The study yields three findings. First, action-head performance is governed primarily by initialization rather than decoder architecture, loss, or inference budget: copying the last transformer layers of the language backbone into the head is the single largest lever, at no latency cost, and the only axis that helps at every module scale. Alignment also explains the other axes: flow matching and a heavier decoder pay off only while the head is misaligned and reverse once it is aligned, and extra inference passes give no measurable benefit; expressiveness appears to substitute for missing alignment. We read this as representation transfer: the aligned head keeps attending to the instruction's object nouns and stays close to the backbone in weight space rather than relearning to act from scratch. Because we reach alignment only through initialization, we offer this as the account that best organizes the measurements, not a demonstrated cause, and name the control that would settle it. Second, capacity pays only after alignment: the aligned action head is the highest-return module to scale. Third, those returns diminish sharply near the size today's $\pi$-series VLAs already use, so further growth buys little in-domain accuracy for its latency. These specify EffVLA, a compact model matching the strongest open-source VLAs on standard LIBERO, leading on most LIBERO-Plus perturbation axes at lower latency, and transferring to a real SO-ARM101 arm with the recipe unchanged.
Read the full abstract

All authors Luoyang Sun, Guoyang Xia, Fengfa Li, Lei Ren, Xinyu Cui, Haifeng Zhang, Fangxiang Feng, Kaike Zhang, Kun Zhan, Yan Xie, Jun Wang, Cheng Deng

Robotics

Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Collaboration

Qiping Zhang, Kate Candon, Debasmita Ghose et al. (+1 more)

In Human-Robot Interaction, the standard approach to learn a reward model that represents human preferences for robot behavior consists of three steps. First, the robot collects limited direct evidence from human feedback (e.g., positive or negative binary feedback). Then, the robot utilizes the direct evidence to derive accepted or rejected labels to feasible but unchosen actions using fixed implication rules. Finally, the robot updates the reward model with both the direct and derived evidence. Unfortunately, the fixed rule can hinder preference learning: in a user study with two collaborative simulation environments, human-provided implication labels often differed from the standard fixed rule, and using the human labels substantially improved reward learning with the Preference Learning from Implicit and Explicit Feedback (PIE) algorithm. Consequently, we propose IMPLIED, an implication modeling method that treats fixed-rule implications as an initial guide while learning to infer and revise accepted and rejected action labels over time. Across evaluations on recorded human-robot interaction trajectories and a physical robot pizza-making study, IMPLIED predicts human implications more accurately than the fixed rule approach and LLM baselines, approaching the performance of a human-label oracle. In turn, IMPLIED reduces preference-estimation error and leads to robot actions that are more often rational with respect to a combined reward (which includes the true preference reward and a task-specific reward) compared to baselines. By learning to reason about the implications of human feedback, this work enables more faithful and efficient robot behavior adaptation during human-robot collaboration.
Read the full abstract

All authors Qiping Zhang, Kate Candon, Debasmita Ghose, Marynel Vázquez

Numerical Analysis

Chronological stability for nonstationary matrix refinement

Yuwen Li and Yupeng Wang

A matrix cascade is an iterative refinement process in which vector-valued data are repeatedly filtered by matrix-valued masks across successively finer scales. Such cascades arise in multichannel subdivision, Hermite refinement, multiresolution synthesis, and exponential-spline constructions, and in nonstationary schemes the masks may vary with scale. We develop a chronological stability framework for this setting, allowing both the transition operators and the associated matching spaces to change from level to level. If the chronological radius satisfies $\rho_{\rm ch}<1$ and the matching defects are summable, then the cascade converges uniformly and, for every $q\in(\rho_{\rm ch},1)$, \[ \|F_n-\Phi\|_\infty \lesssim q^n+\sum_{j=1}^n\delta_j q^{\,n-j} +\sum_{j>n}\delta_j . \] The time-weighted defect term records the level at which each perturbation is inserted, and the matching spaces need not converge; they may even alternate indefinitely. For compact piecewise-linear seeds, every finite ordered matrix cascade admits an exact fixed-width ReLU realization with $O(n)$ depth and parameters, and this linear depth order is worst-case optimal at fixed width. Consequently, exponentially decaying defects yield certified approximants of size $O(\log\varepsilon^{-1})$. We further construct stable two-channel classes in which the chronological radius and the leading metric-entropy coefficient are independent invariants, showing that stability does not determine finite-accuracy description complexity. The framework therefore provides tolerance-controlled finite representations for nonstationary multiresolution and exponential-spline refinement.
Read the full abstract

Computation and Language

Mizan: A National Benchmark for Evaluating Large Language Models on Iraqi Arabic and the Iraqi Civic Context

Nawar S. Alseelawi and Mustafa S. Aljumaily

Arabic large-language-model (LLM) evaluation has matured around Modern Standard Arabic (MSA): aggregated leaderboards such as the Open Arabic LLM Leaderboard (OALL), HELM Arabic, and BALSAM rank models across dozens of MSA tasks, and frontier systems increasingly saturate them. Dialectal Arabic, the language Iraqis actually speak, remains nearly invisible to this infrastructure. We introduce Mizan ("the balance"), Iraq's national benchmark for evaluating LLMs on Iraqi Arabic and the Iraqi civic context: an MSA baseline track paired with an Iraqi track across six axes (dialect comprehension, dialect generation, bidirectional MSA-Iraqi translation, Iraq-specific knowledge, official-document field extraction, and safety), built from 340 originally authored, dually reviewed items with statistically audited answer positions and Wilson intervals on every published score. A pilot evaluation of 27 systems, spanning closed frontier models three days after release, open weights across size tiers, and an Arabic trio of commercial, open-specialized, and sovereign systems, yields four findings. The MSA track saturates while the Iraqi track discriminates, with a consistent 14-18-point per-model gap and statistically tied leaders. Official-document extraction confines every system to 32-56. Arabic-focused specialization behaves as MSA specialization: two dedicated Arabic models score below a size-matched generalist on the Iraqi track. And the safety-hardened tier of the newest model family deterministically refuses innocuous dialect-comprehension items as policy violations, an over-refusal mode invisible to MSA benchmarks. The platform enforces an integrity protocol of immutable snapshots, verification certificates, a human publication gate, and public retraction, all exercised during this study. Code and the public development set accompany the paper.
Read the full abstract

Software Engineering

Introspective Uncertainty Estimation for LLM-Based Code Generation

Thomas Klassert

Large Language Models (LLMs) are increasingly used for code generation but can produce fluent yet functionally incorrect outputs, which limits trust in their usage for practical software engineering workflows. This thesis investigates whether Introspective Uncertainty Estimation (IUE), based on internal hidden-state representations of LLMs, can reliably indicate correctness at the response and line levels for code generation tasks. The objective is to determine the extent to which hidden states encode information about functional code correctness and how this can be leveraged for practical risk assessment and fault localization. Methodologically, this thesis combines response-level evaluation on LiveCodeBench (LCB) and BigCodeBench (BCB) with an augmentation pipeline that derives token- and line-level labels from incorrect programs. In this setup, it compares static and dynamic response-level features, evaluates generalization across tasks, programming domains, and token positions, and studies line-level fault localization. The results show that hidden states contain a strong response-level correctness signal. Static single-token probes perform best, while more elaborate dynamic strategies yield no consistent gains. While generalization across tasks, domains, and token positions is feasible, setting-dependent degradation largely remains for real-world software projects. At a fine granularity, line-level prediction is substantially harder than response-level estimation. However, in a conditional localization setup with known-incorrect programs, Top-K point-of-failure ranking remains effective. Overall, the findings suggest that hidden states are a robust and informative resource for estimating functional code correctness, supporting a two-stage workflow that combines response-level risk screening with targeted line-level prioritization.
Read the full abstract

Software Engineering

Towards a faithful stochastic model for brain digital twins

Abdelhamid Rouatbi, Alexandre Muzy and Eugene Syriani

Twinning the brain means reproducing its electrical activity with fidelity. This activity arises from many neuronal mechanisms across several scales, from a single neuron to whole brain regions. Current large initiatives rely on models that each capture only a few of these mechanisms. Some act at the scale of a single neuron, others at the scale of neuronal populations. No single model captures both scales with fidelity. We propose a new stochastic model, based on a combination of Random Neural Networks and Markov-Modulated Poisson Processes, that would improve the fidelity of a brain digital twin. We map the model to the Discrete Event System Specification. This yields an initial executable simulation model suitable for incorporation into a brain digital twin.
Read the full abstract

Game Theory

Revisiting EFX and fPO Allocations for Binary Chores

Zehan Lin, Xiaowei Wu and Shengwei Zhou

We study fair and efficient allocations of indivisible chores under binary additive costs, with a focus on unequal entitlements and best-of-both-worlds guarantees. While binary valuations have been extensively studied for goods, their chore counterpart remains much less understood. A notable exception is due to Tao et al. (TCS 2025), who established that EFX and fPO are compatible for binary chores with equal entitlements. We revisit binary chores under unequal entitlements and establish the computation of allocations that satisfy WEFX and fPO. Our key technical contribution is a new lexicographic potential function tailored to chores: any allocation minimizing this potential ensures both WEFX and fPO. This potential further guides a polynomial-time local-search algorithm for computing allocations with such fairness and efficiency guarantees. For best-of-both-worlds guarantees, we show that unequal entitlements create a sharp obstruction: even with two agents and identical binary additive costs, no lottery can simultaneously satisfy ex-ante WEF and ex-post WEF1. In contrast, for equal entitlements, we construct in polynomial time a lottery that is ex-ante EF and fPO, while every realization is both EFX and fPO.
Read the full abstract

Computer Vision

Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning

Wen-Chun Lin, Kuan-Peng Chen, Nan-Yow Chen et al. (+2 more)

Ptychographic phase reconstruction is commonly formulated as an iterative inverse problem, requiring repeated object-probe updates and resulting in substantial computational cost for large-scale 4D-STEM data. We present a direct local-to-global learning framework that reconstructs full-field phase maps from diffraction measurements without iterative refinement during inference. The proposed network predicts local wrapped-phase patches from individual diffraction patterns using a sine-cosine representation, and the predictions are assembled into a full-field reconstruction using calibrated scan positions and Gaussian-weighted stitching. To evaluate generalization beyond the training domain, the model is trained on one material and directly applied to another in a zero-shot setting without target-domain fine-tuning. Experiments on AuPd and MoS$_2$ demonstrate consistent cross-material transfer in both directions, with the proposed method achieving the best full-field MSE, PSNR, and MS-SSIM among the evaluated learning-based methods. Compared with the iterative ePIE approach, the proposed direct local-to-global pipeline reduces end-to-end reconstruction time by approximately 10$\times$, demonstrating its potential for efficient and transferable ptychographic reconstruction.
Read the full abstract

All authors Wen-Chun Lin, Kuan-Peng Chen, Nan-Yow Chen, Yu-Chee Tseng, Jen-Jee Chen

Information Theory

A Novel Approach to Counterexamples of the Polujan-Pott Conjecture via Set-Partition Permutations

Yansheng Wu, Jiaxin Wang and Jong Yoon Hyun

In this paper, we settle a conjecture of Polujan and Pott by constructing an explicit, infinite family of Maiorana–McFarland bent functions $f_t$ in $2(2^t-1)$ variables with algebraic degree $\deg(f_t) = t + 1$ for any integer $t \ge 2$. Our construction builds upon a minimal commutative algebra $I_t$, which naturally induces a triangular set-partition polynomial permutation $P_t$. By identifying an elementary abelian subgroup within the direct sum $ I_t \oplus I_t^*$, we establish an explicit nonlinear coordinate transformation that pulls $f_t$ back to a canonical quadratic form. This linearizes the translation development $\operatorname{Dev}(D_{f_t})$ under an exotic group structure and proves that it is isomorphic to the classical symplectic design $S^\pm(2(2^t-1))$, thereby fully resolving the conjecture.
Read the full abstract

Computer Vision

SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight Detection

Hanjuan Huang, Yung-Chieh Yeh and Hsing-Kuo Pao

Video highlight detection aims to identify temporally important segments that capture the most informative or engaging events in a video. Reliable prediction therefore requires not only discriminative segment representations but also preservation of the temporal relationships among neighboring and distant segments. The information bottleneck principle has proven effective for learning compact and task-relevant representations, yet it has not been explored for video highlight detection, and applying conventional formulations directly would overlook inter-segment relational structure and distort highlight relevant temporal organization during compression. We therefore introduce the Sliced Gromov-Monge Gap (SGMG), a structure aware regularizer that measures the excess relational distortion induced by a prescribed source-to-bottleneck mapping relative to an optimal sliced structural correspondence. Building on SGMG, we develop SGWIB, an information-bottleneck framework for single-modal video highlight detection that learns compact bottleneck representations while preserving inter-segment temporal structure. We further introduce Home-Away-Related Contextual Pseudo-Labels and a contextual disentanglement module that reduce sports-specific contextual bias by separating highlight oriented information from contextual patterns. Experiments on MrHiSum and MoSu show that SGWIB attains the best Kendall's tau, Spearman's rho, mAP@50, and mAP@30 among the compared single-modal methods on both datasets. On MrHiSum, the visual model improves the strongest previous results by 0.031, 0.031, 0.87, and 0.75 on these four metrics, respectively. These results show that structure-aware information-bottleneck regularization combined with contextual disentanglement improves segment-level highlight prediction.
Read the full abstract

Machine Learning

Tabby: An Open Pretraining Recipe for Time Series Foundation Models

Shifeng Xie, Bahaeddine Abdessalem, Zehao Xiao et al. (+9 more)

In this report, we release Tabby, a long context probabilistic time series foundation model, together with a complete and open recipe of how it was built. Tabby adopts an encoder-only patch Transformer architecture and concentrates the contributions on the data and the training procedure. The pretraining corpus combines an extended real-world collection, GIFT-Eval-Pretrain+ and BLAST, with synthetic data from KernelSynth and CauKerV2, an online generator that composes temporal dynamics through randomly sampled structural causal models. Training couples a progressive convergence schedule, which yields reusable intermediate checkpoints, with a deep quantile supervision objective for intermediate layers. The resulting 145M parameter backbone supports contexts of up to 8,192 observations and serves forecasting, classification, and anomaly detection, while a prompt-tuning module further improves in-distribution forecasting performance with the pretrained weights frozen. Tabby achieves competitive zero-shot forecasting performance on GIFT-Eval and the out-of-distribution TIME benchmark, while the same pretrained backbone also supports classification on the UCR Archive and zero-shot anomaly detection on TSB-AD-U. We release training pipeline and model as open source at huawei-noah/trustworthyAI.
Read the full abstract

All authors Shifeng Xie, Bahaeddine Abdessalem, Zehao Xiao, Youssef Attia El Hili, Ambroise Odonnat, Zhiwei Dong, Lei Zan, Themis Palpanas, Jianfeng Zhang, Lujia Pan, Keli Zhang, Malik Tiomoko

Machine Learning

Linear Ensemble Sampling with Smaller Ensembles

Taehyun Hwang and Min-hwan Oh

Ensemble sampling offers a practical approach to randomized exploration by maintaining a collection of models, but how small an ensemble can be while retaining strong regret guarantees remains unresolved. In particular, the existing guarantees use an ensemble size of $\Theta(d\log T)$, leaving a logarithmic gap in the horizon $T$ relative to the intrinsic $\Omega(d)$ ensemble-size barrier. We aim to narrow this gap by proposing an ensemble sampling algorithm that refreshes the ensemble only when the regularized Gram matrix changes substantially. This mechanism localizes the perturbation analysis to epochs with controlled Gram-matrix drift and reduces the sufficient ensemble size to $\Theta(d\log d+d\log\log T)$, while preserving the state-of-the-art $\tilde O(d^{3/2}\sqrt T)$ regret for ensemble sampling with arbitrary bounded arm sets. We further show that, when the arm set is finite of cardinality $K$, the proposed algorithm achieves the sharper regret bound $\tilde O(d\sqrt{T\log K})$. To the best of our knowledge, this is the first ensemble-sampling guarantee that simultaneously recovers both canonical regret scalings known for randomized linear bandit algorithms: the $\tilde O(d^{3/2}\sqrt{T})$ rate for arbitrary bounded arm sets and the $\tilde O (d\sqrt{T\log K})$ rate for finite arm sets. The algorithm also admits an anytime implementation without resetting past data, and experiments show that it remains competitive with baselines while using substantially smaller ensembles.
Read the full abstract

Computation and Language

Thought without systematicity? Evaluating reasoning models on rule induction tasks

Simon Schug and Brenden M. Lake

A central tenet of human cognition is systematicity, the principle that understanding one concept is inherently tied to understanding close variations of that concept. Do reasoning models robustly exhibit such systematicity? If so, we would expect consistent performance on structurally equivalent variants of the same task. Here, we extend established rule induction tasks from cognitive science to assess the systematicity of thought in current reasoning models. Each task family has compositional structure that we use to create structurally equivalent task variations through task isomorphisms such as recombination and substitution. We find that despite being able to correctly solve a task, models often fail on structurally equivalent variants of the same task. These findings suggest that many model behaviors lack systematicity, rendering it difficult to robustly establish the cognitive abilities of reasoning models beyond the particular contexts they were evaluated in.
Read the full abstract