Peer Revenue Now accepting positions

Papers

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

All of arXiv

Thursday 8 October

Materials Science

Homogeneous Charge Relaxation in Organic Mixed Ionic-Electronic Conductors

Silan Zhang, Scott T. Keene, Junfu Tian et al. (+11 more)

Organic mixed ionic-electronic conductors (OMIECs) couple ionic and electronic signals, enabling energy storage, neuromorphic computing, and bioelectronics. However, how charge relaxes in water once the bias is removed, which determines how long stored states persist, remains unclear. Using operando charge photometry, we tracked charge in OMIEC films during biasing and open-circuit relaxation. Under bias, charges moved as redox fronts. After bias removal, charge instead relaxed uniformly across the channel. Modeling and cryo-electron microscopy indicate that swelling creates connected water-rich pathways through the bulk. These pathways speed ion motion but also let stored charge leak away. Tuning the terminal side chain of a polythiophene controls water uptake and ion trapping. Bulky hydrophobic side chains enable stable programmable states, whereas hydrophilic side chains support fast electrophysiology sensing.
Read the full abstract

All authors Silan Zhang, Scott T. Keene, Junfu Tian, Georgina E. Lindop, Simon M. Fairclough, Zhengkang Qu, Xian Wei Chua, Christopher Slaughter, Christina J. Kousseff, Caterina Ducati, Iain McCulloch, Henning Sirringhaus, Akshay Rao, George G. Malliaras

Machine Learning (Statistics)

Efficient quadratic entropy with distance sketches

Steve Huntsman

We detail scalable methods for approximating the quadratic entropy $p^T d p$ for arbitrary distributions $p$ and common distances $d$ of negative type. We focus on the Euclidean and spherical geodesic cases, which both use random feature embeddings and projections to dramatically improve computational complexity within a simple framework. Amortization of a single large matrix multiplication and control variates further enable computation at large scale with low memory and runtime in situations where $d$ is held constant while $p$ varies. We demonstrate this with a comparison against direct pair sampling and bibliometric/scientometric examples on Open Graph Benchmark datasets, revealing papers, fields, and institutions with both particularly narrow and broad interdisciplinary reach from their citations and text features alone.
Read the full abstract

Robotics

Predicting Cable Dynamics with Physical Attention Bias

Avihai Giuili, Rotem Atari, Avishai Sintov et al. (+1 more)

Learned simulators for deformable linear objects (DLOs) such as cables have to predict the motion of cables they were not trained on and stay stable over long rollouts. Most of their error occurs where the cable touches itself or the floor. Attention over all pairs of cable segments can represent contact between parts of the cable that are far apart along its length, but attention has no notion of geometry. A cable has two pairwise distances, which agree only while it is straight: the arc-length distance along the cable, which governs elastic forces, and the Euclidean distance in space, which governs contact. We add a physical attention bias, an additive term on the attention logits with a learned rate, and ask which distance it should use. We compare no bias, each distance alone, and both distances on disjoint sets of heads, keeping the rest of the model and the training protocol fixed. A physical bias improves prediction on unseen cables. The gain is largest when attention is the only mechanism that connects distant segments: there, the arc-length bias reduces prediction error by 15% and more than halves the drift in segment length. The Euclidean bias alone stays close to unbiased attention, while assigning both distances across heads is best or near-best on every metric we report. Code and per-run records: https://github.com/avihaig/dlogps.
Read the full abstract

All authors Avihai Giuili, Rotem Atari, Avishai Sintov, Maya Bechler-Speicher

Number Theory

Uniform non-vanishing of prime quadratic twists of standard and symmetric square $L$-functions

Tianyu Ni

Let $S_k$ be the space of cusp forms of weight $k$ for ${\rm SL}_2(\mathbb Z)$, with $\dim S_k\geq1$, and let $\chi_p=\left(\frac{\cdot}{p}\right)$ for odd primes $p$. For fixed $s$ with ${\rm Re}(s)>(k+1)/2$, we prove that the proportion of primes $p\leq X$ satisfying $L(h,\chi_p,s)=0$ tends to zero as $X\to\infty$, uniformly over nonzero $h\in S_k$. We also prove an analogous statement for nontrivial linear combinations of twisted symmetric square $L$-values of the normalized Hecke eigenforms when ${\rm Re}(s)>k$. The main ingredient of the proof is a non-concentration theorem for random Euler products under a pairwise local separation condition. As applications, we obtain spanning and density-one basis results in $S_k$ for the kernels associated with twisted standard and symmetric square $L$-functions, with explicit basis criteria in specified right half-planes when $\dim S_k=2$ or $3$. We show that almost every tuple of $\dim S_k$ primes gives a basis of $S_k^{\ast}$ from twisted periods at every noncentral critical index. We also prove a density-one result for rational bases of $S_k$ obtained from traces of Rankin-Cohen brackets of Eisenstein series at prime levels.
Read the full abstract

Signal Processing

Pinching-Antenna-Assisted Integrated AirComp-NOMA: Joint Transceiver and Antenna-Position Optimization

Saeid Pakravan, Wessam Ajib and Wei-Ping Zhu

Integrating over-the-air computation (AirComp) with non-orthogonal multiple access (NOMA) enables concurrent data aggregation and information transmission, but tightly couples computation accuracy with communication quality of service (QoS). This paper investigates a pinching-antenna-assisted uplink, where flexible pinching-antenna (PA) placement provides additional spatial degrees of freedom to manage this coupling. We minimize the AirComp mean-squared error (MSE) subject to NOMA QoS, transmit-power, and PA deployment constraints by jointly designing the AirComp transceiver, PA positions, and successive interference cancellation (SIC) order. Exploiting the recursive structure of uplink SIC, we establish an exact NOMA feasibility condition and derive an optimal SIC-ordering rule. These structural results eliminate the NOMA power variables and the combinatorial search over decoding orders, reducing the original problem to a continuous optimization problem. We then develop an iterative algorithm with optimal AirComp transmit-coefficient and receive-scaling updates and a feasibility-preserving majorization scheme for PA placement. The proposed algorithm preserves NOMA feasibility while generating a monotonically nonincreasing computation-MSE sequence. Numerical results demonstrate the computation-accuracy gains of jointly optimizing the AirComp transceiver and PA positions under NOMA QoS requirements.
Read the full abstract

Numerical Analysis

Mathematical foundation of symmetric fast Fourier transform

Weifeng Hou, Kai Jiang and Jingfei Tang

In this work, we study the fast Fourier transform (FFT) of discrete data with crystallographic symmetry, for which standard FFT algorithms incur substantial redundant computation. We establish a rigorous mathematical theory of the symmetric fast Fourier transform (SFFT) for $n$-dimensional crystallographic groups and propose the SFFT and symmetric inverse fast Fourier transform (SIFFT) algorithms. We derive symmetry-reduction formulas for both linear and translational symmetries and unify them into a recursive framework. We analyze the arithmetic complexity to obtain theoretical speedup factors relative to the standard FFT, and we confirm the accuracy and efficiency of the proposed methods by numerical experiments on representative three-dimensional space groups.
Read the full abstract

Robotics

CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding

Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu et al. (+6 more)

Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions are physically executed. Existing fault-recovery methods often require task-specific retraining, fault labels, explicit diagnosis, or privileged embodiment information. We introduce CAPABLE, a unified capability-aware adaptation framework for frozen VLAs that integrates self-supervised capability inference with residual reinforcement learning. CAPABLE infers capability, how much of the commanded motion each joint actually realizes and how that motion contributes to end-effector behavior, online from command-response history and kinematics using a temporal encoder shared across joints, Jacobian grounding, cross-joint attention, and self-supervised physical prediction. The resulting representation conditions a residual policy that adds bounded corrections to the VLA arm action without fault labels or faulty-joint identifiers. Across 28 LIBERO tasks, CAPABLE raises success on an actuator excluded from fault training from 24.8% to 59.3%, outperforming a parameter-matched global-history baseline by 17.4 points while preserving healthy performance. Leave-one-actuator-out experiments across six joints show that this transfer is not specific to one actuator, and additional evaluations characterize transfer to unseen fault families and demonstrate recovery on a physical Franka Panda. https://capable-vla.github.io/
Read the full abstract

All authors Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Deyuan Qu, Zhiyuan Gao, Yanxiang Zhan, Jeroen Schafer, Andrew Melnik, Qing Yang, Michael Beetz

Statistical Mechanics

Mutual Linearity of Complexes in Chemical Reaction Networks

Pedro E. Harunari, Guilherme Fiusa and Matteo Polettini

Exact statements about how a system far from equilibrium responds to changes in its rate constants are scarce beyond linear response, yet they are central to the control of biochemical networks. A notable exception is mutual linearity: in a jump process, controlling the rates of a single transition makes any two stationary probabilities obey an exact affine relation, arbitrarily far from equilibrium. With nonlinear mass-action kinetics, and conservation laws in place of a normalization, chemical reaction networks seem to defy mutual linearity since species concentrations obey no such relation. We show that it was there all along, in the complexes' activities (mass-action monomials) rather than in the concentrations of species. For zero-deficiency networks with a single linkage class, controlling one reaction makes any three stationary activities obey a linear relation whose coefficients are independent of the controlled rate constants, the conserved quantities (hence the initial state), and even of the stoichiometry of complexes. This predicts hidden activities and bounds the activity ratios the control can reach, while a violation signals nonzero deficiency or multiple linkage classes.
Read the full abstract

Formal Languages and Automata

Non-recursive trade-offs for two-way machines

Christos Kapoutsis

If the machines of some type A have enough resources to (i) solve problems that no machine of type B can solve, and (ii) simulate any unary two-way deterministic finite automaton that has access to a linearly-bounded counter, then typically no recursive function can upper bound the increase in the size of description when a machine of type A is replaced by an equivalent machine of type B.
Read the full abstract

Analysis of PDEs

Nonlinear Schrödinger equation in an exterior domain

Roberto de A. Capistrano Filho, Lionel Rosier and Bingyu Zhang

We study the exact controllability of the cubic nonlinear Schrödinger equation in the exterior $\Omega=\mathbb{R}^n\setminus\Theta$ of a non-trapping obstacle $\Theta$, with internal controls supported outside a large ball, and the corresponding boundary control problem on $\Omega_0=B_{R_0}\setminus\Theta$ with Dirichlet controls acting only on the outer sphere $\partial B_{R_0}$. Using the local smoothing effect of Burq, Gérard and Tzvetkov [9], we prove observability inequalities for the linear Schrödinger equation in the whole scale of Sobolev spaces $H^\sigma_D(\Omega)$, $\sigma\in[-2,2]$, associated with the Dirichlet Laplacian; they require only the non-trapping assumption (no star-shapedness of $\Theta$), and their proofs use no normal boundary traces. Combined with Strichartz-type estimates and a perturbation argument, this yields local exact controllability in $H^1_0(\Omega)$ and in $H^2(\Omega)\cap H^1_0(\Omega)$, in dimensions two and three, around the zero solution and, for internal controls and under a unique continuation assumption, around nontrivial trajectories. The same method applies to the quintic equation, which is energy-critical in dimension three. Several open problems are discussed.
Read the full abstract

Computer Vision

Learning Which Correspondences to Trust: Confidence-Weighted Event-Camera Localization in LiDAR Maps

Panagiotis Kiousis, Kuangyi Chen, Jun Zhang et al. (+1 more)

Localizing an event camera against a pre-built LiDAR map can be cast as dense optical-flow estimation between a rendered depth view and an event image, followed by a Perspective-n-Point (PnP) solver over the induced 3D-2D correspondences. Existing pipelines rely on geometric consensus during pose estimation, but do not explicitly model the reliability or pose informativeness, i.e., how strongly a correspondence constrains the camera pose, of individual correspondences. We show that the natural way to learn it – using the per-correspondence error to constrain the learning of confidence – suffers from a depth-dependent bias: small pixel errors reside predominantly at large depths and do not lead to high pose informativeness. Instead, in our method (CELL), we learn a per-correspondence confidence end-to-end through the pose, using a differentiable probabilistic PnP whose log-partition term encourages weight configurations that yield a better-constrained pose distribution. The learned confidence is used in three ways: (i) it reweights the flow supervision in a decoupled training scheme that keeps pose gradients out of the flow/edge backbone; (ii) it drives a probabilistic correspondence selection at test time; and (iii) together with the network's edge-probability it weights a final edge-matching refinement. We further design a partial-completion depth representation that adds signal without hallucinating across large gaps. On M3ED and DSEC our full system improves over the LEAR baseline on the majority of the evaluated sequences: it reduces the median translation error by up to 26.9% and the median rotation error by up to 15.8%.
Read the full abstract

All authors Panagiotis Kiousis, Kuangyi Chen, Jun Zhang, Friedrich Fraundorfer

Artificial Intelligence

MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation

Mengdi Liu, Wenjue Chen, Wenyue Chen et al. (+10 more)

Research idea innovation is a fundamental engine of scientific progress, yet it remains difficult to generate and evaluate in a scalable and controllable way. This challenge lies in its inherently open-ended and multi-objective nature, where ideas should balance novelty, plausibility and feasibility. While recent LLM-based approaches have made progress through carefully designed prompts or agent pipelines, they are constrained by predefined, static ideation workflows. To address this limitation, we propose MindFlow, a framework that explicitly formulates ideation as a graph-structured Flow in Mind, which is composed of modular thinking operators and modeled by a probabilistic mind supernet. Given a research topic, a controller dynamically samples thinking flows to generate candidate ideas. This open-ended problem is optimized using a tournament-based relative ranking, enabling the controller to progressively favor higher-quality thinking flows. We further introduce an evaluation protocol that jointly assesses problem finding and problem solving, going beyond title- or abstractonly judgments. Across diverse topics, MindFlow shows its superiority as an explicit, controllable and optimizable research idea innovator.
Read the full abstract

All authors Mengdi Liu, Wenjue Chen, Wenyue Chen, Cheng Yang, Fanqi Kong, Zhangyang Gao, Xiaoxue Cheng, Yiheng Li, Yujian Yuan, Keliang Li, Hong Chang, Shiguang Shan, Chenglin Wu

Number Theory

Pythagorean pairs in boxes of prime powers

Rongzhong Xiao

Let $p_i$ be the $i$th prime, and let $f(N)$ be the largest cardinality of a subset of \[ \left\{\prod_{i=1}^N p_i^{a_i}:0\le a_i<N,\ a_i\in\mathbb{Z}\right\} \] containing no two distinct legs of an integer right triangle. We prove \[ f(N) \ll N^N (\log\log N)^{-1/1296}. \]

Systems and Control

From Asymptotic to Designer-Assigned-Time Control: A Review of Stability Notions, Design Mechanisms, and Controller Architectures

Özhan Bingöl

Many control tasks require a target to be reached not only eventually but on time. Finite-, fixed-, predefined-, and prescribed-time control address this need, yet the labels are used loosely: a settling time that grows with the initial condition, a bound that holds for all initial conditions, a deadline chosen by the designer, and a limit attained only at the terminal instant often share one name. This review aims to make such claims comparable. It separates three questions that are often conflated: what temporal property is promised, which feature of the Lyapunov analysis produces it, and which controller architecture carries it into the closed loop. A recurring question is whether a guarantee proven for an idealized loop survives once observers, adaptation, disturbances, actuator limits, and digital implementation are included. The examined studies are therefore audited one by one, recording what each claims, which variable is actually certified, and how the result is validated. The audit shows that estimation and approximation errors often reduce an exact guarantee to a practical one, and that experimental evidence comes mostly from fast electromechanical systems. A scalar benchmark with two complementary tunings shows how much of the apparent difference between methods stems from conservative bounds, initial-condition dependence, and numerical tolerance, and how saturation and sampling can delay or remove a deadline. The review closes with open problems, among them deciding which deadlines a given plant can meet, combining certificates across interconnected subsystems, and preserving a guarantee through implementation.
Read the full abstract

Software Engineering

Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes

Utku Boran Torun, Veli Karakaya and Eray Tüzün

A no-code fix resolves an invalid bug report by directing the user to change a setting, update to a version where the problem is already fixed, or adjust their workflow. Manually verifying whether a proposed no-code fix resolves the reported bug takes considerable developer time. This study proposes an automated, execution-based pipeline for evaluating the capability of large language models (LLMs) to generate no-code fixes in a real browser environment. We evaluate 322 no-code fixes generated by the 12 configurations released with the benchmark of a previous study, covering bug reports categorized as Faulty Configuration, Wrong Version, or External System & Dependency. An executor agent applies each fix by following its natural-language instructions, and an issue-specific checker determines whether the reported bug persists. We repeat the pipeline with three executors: two Computer-Use Agents, OpenCUA-72B and Claude Sonnet 5, and one multimodal agentic LLM, Meta's Muse Glimmer. Only 17.6% of the candidate issues could be set up and passed both sanity gates. Across the 322 fixes, 14.6% to 49.7% resolved the bug depending on the executor, and the strongest configuration, Claude Opus 4.6 in the Vanilla pipeline, resolved up to 74.1% of its fixes under Claude Sonnet 5. Changing only the executor shifted a configuration's resolution rate by 38.8% on average, and the three executors reached the same verdict on only 46.9% of the fixes. Compared with human execution, the executors matched the human consensus for 66.1% to 88.1% of the sampled fixes. Even under the best executor, fewer than half of the LLM-generated no-code fixes resolve the reported bug, so such fixes need verification before they reach users. Execution-based verification can provide this, but the measured capability depends strongly on the executor, which evaluations must report and control.
Read the full abstract

Geophysics

Escaping Geological Generative Prior Distributions in Bayesian Travel Time Tomography

Pratyay Roy, Xuebin Zhao and Andrew Curtis

Solutions to geophysical inverse problems are generally non-unique, and greatly benefit from additional geological prior information. Generative Neural Networks (GNNs) are commonly used to parametrise such information, typically restricting solutions to a lower-dimensional latent space. The final inversion result is obtained by mapping the latent space parameters to the original higher-dimensional model space using the GNNs. However, solutions then remain confined to a low-dimensional geological generative manifold; if the true Earth model lies outside of this manifold, standard latent space inversion fails. We propose a Bayesian model space inversion method that uses the generative manifold as a guide to find the solutions that lie outside this manifold. We validate our approach in non-linear travel-time tomography experiments on both simple and more geological structures. By comparing our method with model space inversion using uniform prior probabilities and standard latent-space inversion, we demonstrate that the less informative uniform prior fails to constrain the solution, while the latent space approach fails when the true Earth model lies outside of the generative manifold. Conversely, our new model-space inversion method successfully recovers complex off-manifold geological features while maintaining low solution uncertainty.
Read the full abstract

Optimization and Control

A Bregman proximal linearized ADMM for fractional programming with nonlinear coupling constraints

Pengjie Liu, Jinhu Chen, Minh N. Dao et al. (+2 more)

This paper considers a nonconvex fractional optimization problem with composite structure and nonlinear equality constraints. We reformulate the problem as a non-fractional min-max problem with corresponding optimal solutions. By linearizing the nonlinear constraint terms in the augmented Lagrangian and incorporating Bregman proximal linearization and a relaxation factor in $(0, 2)$ into the alternating direction method of multipliers (ADMM), we develop a Bregman proximal linearized ADMM with guaranteed subsequential convergence to a lifted critical point. Convergence of the entire sequence is established under the Kurdyka–Łojasiewicz (KL) property. We further derive convergence rates under either a Hölderian value proximity error bound condition or the KL property, with the corresponding exponent in $[0, 1)$. In particular, we establish superlinear convergence for exponents in $(0, 1/2)$, together with finite, linear, and sublinear convergence in the remaining cases. Numerical experiments demonstrate the effectiveness of the proposed algorithm.
Read the full abstract

All authors Pengjie Liu, Jinhu Chen, Minh N. Dao, Hu Shao, Jinbao Jian

Information Theory

Estimation with Quantized Parameter Side-Information

Mathis Wetterwald, Ofer Shayevitz and Michèle Wigger

This paper presents upper and lower bounds on the minimax risk of a parameter estimation problem where the estimator not only observes independent and identically distributed observations but also a quantized version of the parameter, where the quantization has a limitation on the number of levels, but can be optimized otherwise. Our upper and lower bounds have similar decay rates for large number of observation samples and quantization levels.
Read the full abstract

Computation and Language

MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement

Xiaomi LLM-Core Team: Zongming Qiao, Ziyue Hua, Zirui Ou et al. (+145 more)

Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute. Prior to RL, we conduct mid-training on a broad multimodal corpus to provide ample exploration space, and build a solid infrastructure on the pretrained hybrid-SWA architecture to support subsequent scale-up. We scale RL compute along three dimensions: (1) larger batches and higher throughput, with an asynchronous training that consumes 1,568 samples and 2.7-3.7B tokens per step at context lengths of up to 1M; (2) more diverse and complex environments, spanning code, general, visual, and cyber domains under a mixture of agent harnesses; and (3) more grader compute, via groupwise agentic grading that yields more accurate reward signals for long-horizon tasks and steers the model towards shorter, more token-efficient solutions. To keep training stable at scale, we freeze the MoE router and establish a multi-layer defense against reward hacking. We further build infrastructure for mixed-task agentic RL, including a unified trajectory representation, high-concurrency multi-framework rollout, decoupled control and data planes, and training-inference consistency. We open-source the training dynamics, RL environments, and RL framework to facilitate reproduction and further research on scaled RL and model self-improvement.
Read the full abstract

All authors Xiaomi LLM-Core Team: Zongming Qiao, Ziyue Hua, Zirui Ou, Zihao Yue, Zihan Jiang, Zhuo Huang, Zhiyang Chen, Zhixian Zheng, Zhipeng Xu, Zhengrui Ma, Yuyang Hu, Yuhang Dong, Yuechen Zhang, Yudong Wang, Yuanxin Liu, Yixin Yang, Yishuo Cai, Yikai Zhao, Yihan Yan, Yifan Zhang, Yifan Song, Xiyu Wei, Xing Zhang, Xin Zhang, Xiaoqian Liu, Xiaodong Ji, Xiangwei Deng, Xueyu Guo, Wenhan Ma, Weimin Xiong, Weikun Wang, Weiji Zhuang, Shuo Liu, Shuhuai Ren, Shuhao Gu, Shimao Chen, Shijie Cao, Shihua Yu, Shicheng Li, Shengjie Zhou, Shaolei Zhang, Rang Li, Qiying Wang, Qingkai Fang, Qianli Chen, Minzheng Wang, Liwen Wang, Linli Yao, Linghao Zhang, Liangyu Cheng, Liang Zhao, Lei Li, Jinhao Dong, Jinyu Xiang, Jianyu Wei, Jiangshan Duo, Huaqiu Liu, Huanjie Fan, Hongyi Guan, Hongshen Xu, Hao Tian, Hanyu Li, Hailin Zhang, Gang Wang, Fuli Luo, Feng Wei, Dong Zhang, Dawei Zhu, Chiheng Lou, Chenhong He, Chenhao He, Chenghua Liu, Bowen Ye, Bowen Shen, Boshen Xu, Bo Yang, Bingquan Xia, Bangjun Xiao, Baixuan Xu, Zhouxiang Mao, Zhiyang Zhang, Zhixiang Xu, Zhenru Lin, Zhengju Tang, Zhaojun Huang, Yuzhe Weng, Yuxing Xiang, Yuxiao Li, Yuheng Yang, Yuhang Wang, Yuchen Liu, Yuanyuan Tian, Yuanliang Dong, Yu Cheng, Yongzhe He, Yongshun Liang, Yong Wang, Yiyan Wang, Yitian Gong, Yijie Zhang, Yanshu Xin, Xun Zhang, Xingjian Zhao, Wenyu Yang, Wenshan Huang, Wenhao Li, Tingwei Huang, Tianyu Yu, Tianyang Lu, Taoyu Yang, Sinan Du, Shutong Tian, Shulin Du, Shengfan Wang, Shanchuan Fang, Qihao Zhang, Qibin Yang, Qian Yu, Qian Tu, Pengrong Xie, Peipei Wang, Peidian Li, Minkun Guo, Mingchen Shao, Luohan Gao, Lijie Wang, Liang Shi, Kaiqi Chen, Kaiming Liu, Kaifei Wang, Kai Yang, Jinlong Xue, Jiechen Zhang, Jiaxuan Liu, Hongxu An, Hao Peng, Hanglong Lü, Guonan Wang, Feiyu Yang, Fanyu Cao, Fangyue Liu, Fan Cui, Cong Wang, Chun Chen, Chenxu Bai, Chengxuan Zhu, Chenghua Wang, Boyi Zeng

Formal Languages and Automata

From k+1 to k heads the descriptive trade-off is non-recursive

Christos Kapoutsis

We prove that no recursive function can upper bound the increase in the size of description when a two-way deterministic finite automaton with k+1 heads is replaced by an equivalent two-way deterministic finite automaton with k heads. This is true for all k, and remains true if the automata are unary and/or nondeterministic.
Read the full abstract

Machine Learning

Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability

Meihui Zhong, Wenxin Tai, Ting Zhong et al. (+1 more)

Conformal prediction offers a distribution-free coverage guarantee, making it especially attractive for clinical applications. Standard conformal prediction, however, provides such guarantees only at the population level, and its prediction sets can exhibit coverage disparities across clinically important subgroups. A natural remedy is to calibrate within predefined groups. However, this can require access to sensitive subgroup attributes and is prone to a worst-group bottleneck: protecting the most difficult subgroup can inflate prediction sets for all, increasing cognitive burden on decision makers. To this end, we propose Stochastic Grouping Conformal Prediction (SGCP), a conformal framework for subgroup-reliable uncertainty quantification. It learns a stochastic grouping map that allows each sample to draw calibration information from others with similar calibration behavior, yielding a local score law that boosts reliability across subpopulations. We prove that SGCP retains the standard coverage guarantee. Experiments on synthetic and real-world benchmarks show that it consistently reduces subgroup coverage gaps while achieving smaller or comparable prediction set sizes relative to existing baselines.
Read the full abstract

All authors Meihui Zhong, Wenxin Tai, Ting Zhong, Fan Zhou

Robotics

Reliability-Aware Future Conditioning for Temporally Robust Robot Manipulation

Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Zhiyuan Gao et al. (+8 more)

A generated video of a task the robot is about to perform is useful guidance only if it depicts the phase the robot is actually in. We show that temporal misalignment can turn a task-consistent generated future into actively harmful guidance. On CALVIN, a five-frame early shift nearly erases the benefit of generated futures, reducing success from 81.3% to 54.8% against 54.0% without futures; imposed timing shifts reduce it even further to 34.2%, 19.8 points below the future-free policy. We introduce Reliability-Aware Future Conditioning (RAFC), which treats this as a control problem rather than a generation problem. At every step, RAFC estimates how far to trust the received clip and which nearby temporal hypothesis to prefer, falling back toward a static branch when neither fits, and it learns both from task reward alone without shift labels or alignment supervision. RAFC sits on top of Future-Experience Conditioning (FEC), which builds the clip once from task grounding, a robot-free digital-twin rollout, and mask-free video diffusion. Under deliberately off-grid phase shifts and rate mismatch, RAFC substantially improves success under temporal mismatch. Candidate ensembling accounts for most of the recovery near alignment, while learned reliability adds a further 7.0 percentage points over uniform averaging of the identical candidate bank under off-grid shifts. The gain holds on the evaluated task sets and survives on a Franka under natural timing mismatch nobody imposed, where aggregate success rises from 26.7% to 56.7%. All resources will be made publicly available. https://future-condition.github.io/.
Read the full abstract

All authors Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Zhiyuan Gao, Deyuan Qu, Max Gandyra, Yanxiang Zhan, Mehreen Naeem, Andrew Melnik, Jeroen Schafer, Qing Yang, Michael Beetz

Distributed Computing

Capturing a Moving Target on Star Graphs by Two Communicating Mobile Agents

Khaled Jawhar and Evangelos Kranakis

We study a problem of searching for a mobile target in an $m$-ray star graph, a natural generalization of linear search to multiple directions. The target is placed adversarially on one of the rays and may move with constant speed. We investigate a two-robot setting, where cooperation and communication play a central role. We study two communication models: the Face-to-Face (F2F) model, where robots communicate only upon meeting, and the Sender-Receiver (S/R) model, where communication is asymmetric. We focus on the away model, in which the target moves away from the origin with speed $v<1$. We design search strategies that minimize the competitive ratio and analyze the problem under three knowledge assumptions: NoDistance, NoSpeed, and NoKnowledge. For each setting, we derive upper bounds on the competitive ratio and for some cases, we derive the lower bound. Our results highlight how the number of rays and the communication model influence the competitive ratio.
Read the full abstract

Computer Vision

Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion

Kartik Bali, Mahish Guru, Yiderigun Borjigin et al. (+3 more)

CAD reconstruction methods assume a luxury reality rarely grants: unrestricted visual access to the object, photographed from any desired angle. Real objects, however, are scene-embedded, bolted against walls, wedged into corners, resting on floors, where the scene renders much of the view sphere unreachable and the remaining views unequally informative. We introduce SightCAD, a framework for parametric CAD reconstruction that treats view feasibility as a first-class constraint. In this work we consider objects from standard CAD benchmarks embedded in realistic indoor scenes with physically derived visibility constraints over a discrete view sphere. A learned view selector must choose $K$ feasible views for a vision–language model (VLM) that generates executable CadQuery code, scored by geometric fidelity of the executed solid. Because reward arrives only after discrete view selection, autoregressive generation, and CAD-kernel execution, we propose a joint training paradigm in which the view selector and the CAD-generation VLM are trained together against this reward. The learned selection policy departs sharply from random, uniform, and coverage-greedy alternatives, outperforming surface-area maximization (SA-max) by up to $6.4$ Intersection-over-Union (IoU) points across budgets $K\in\{1,\dots,5\}$. The full system surpasses strong external baselines on scene-embedded, occluded multi-view renders of DeepCAD and Fusion360 objects ($+21$ and $+17$ effective-mIoU points over the best baseline, respectively), as well as on test-time domain-canonicalized real images from the industrial T-LESS benchmark and on both synthetic and real images from the MP6D industrial metal-parts benchmark, while producing the highest rate of executable programs of any method compared (invalid-code rate ${\leq}1.5\%$).
Read the full abstract

All authors Kartik Bali, Mahish Guru, Yiderigun Borjigin, Alexandra Starostina, Christian J. Cyron, Roland Aydin

Machine Learning

Interval-valued SHAP in Tree-Based Models

Chenrui Zhu, Vu-Linh Nguyen, Marie-Hélène Masson et al. (+1 more)

Shapley values are among the most popular feature-attribution explanations. Efficient approaches for computing/estimating Shapley values for tree-based models, which are state-of-the-art for tabular data sets, have been developed. However, it is known that Shapley values can be (highly) unrobust due to small and realistic changes. In this paper, we propose an imprecise Dirichlet model (IDM) based method to analyze the robustness of Shapley values in decision trees and random forests. Technically, it is done by quantifying and analyzing the interval-valued Shapley values when a few unannotated instances are randomly introduced to the leaves of the trees. The interval-valued Shapley values can be defined following common principles in handling incomplete data: the pessimistic and averaging principles. We derive various theoretical results that lead to efficient computation of the interval-valued Shapley values. We also show that the proposed method can be straightforwardly generalized to the case of Banzhaf values. We then present various case studies and experiments to illustrate the behaviour of the proposed interval-valued Shapley values and their applications in debiasing uninformative features.
Read the full abstract

All authors Chenrui Zhu, Vu-Linh Nguyen, Marie-Hélène Masson, Sébastien Destercke

Robotics

Tell Robot What Not to Do: A Negation Understanding Perspective

Fazeng Li, Gan Sun, Hao Cheng et al. (+2 more)

Instruction following enables robots to perform diverse tasks specified in natural language, making it a fundamental capability for human-robot interaction. Beyond communicating desired outcomes, users also need to specify constraints on what not to do. We investigate how to enable vision-language-action models (VLAs) to follow negated instructions, where robots must accomplish task goals while respecting explicit exclusions. To this end, we propose NegaAlign, a parameter-efficient, plug-and-play framework that extends pretrained VLAs to follow negated instructions through image-language supervision alone. Specifically, we introduce Negation Transformation Layers into selected layers of the vision-language backbone to reshape intermediate instruction representations. Meanwhile, a teacher-guided alignment mechanism is designed to align instruction-relevant visual tokens, transferring action-relevant grounding from instructions that satisfy the negated constraint. The training phase uses supervision constructed from existing demonstrations and updates only the inserted layers, keeping all pretrained parameters frozen, including the action generator. We further introduce NegaBench, a simulation benchmark spanning 10 scenarios across five domains for systematically evaluating manipulation under negated constraints. Experiments across GR00T, $\pi_0$, and $\pi_{0.5}$ demonstrate consistent improvements in negated instruction following. With 11.6M trainable parameters, NegaAlign increases the negated-instruction success rate of $\pi_{0.5}$ from 2.60% to 88.45% on NegaBench and from 12.4% to 88.8% on real-world tasks, while retaining performance on affirmative instructions.
Read the full abstract

All authors Fazeng Li, Gan Sun, Hao Cheng, Weihong Ren, Yang Cong

Human-Computer Interaction

"Hot-Blooded" vs "Cold-Blooded": Simulating the Behavioral Phenotypes of Childhood Aggression via Generative Agents

Liping Fu

This study examines the construct validity of LLM-based generative agents in simulating reactive, proactive, and co-occurring aggression in children. Four distinct agents were instantiated using a theory-driven parameterization grounded in the social information processing model. A total of 1,920 simulation runs were conducted across eight social scenarios, employing a hybrid blind-coding pipeline to extract 32 quantitative behavioral indicators. Results demonstrate robust discriminant validity relative to a non-aggressive baseline, with large effect sizes. High cross-seed reliability confirms that behavioral differentiation is driven by underlying psychological parameters rather than model stochasticity. Qualitative narrative analyses further converged with established empirical literature. Overall, these findings indicate that theory-parameterized LLM agents can accurately reproduce distinct aggression subtypes, offering a scalable, highly controllable framework for hypothesis generation, intervention piloting, and the refinement of psychological measurement tools.
Read the full abstract

Optimization and Control

Computing Lower Bounds on the Non-negative Rank via SAT Solvers

Tilman Engel, Thomas Kalinowski and Matthias Schymura

Finding the extension complexity (xc) of a polytope is equivalent to finding the non-negative rank of its slack matrix. We provide a formulation for the rectangle and refined rectangle covering, bounding the non-negative rank of diverse non-negative matrices. While the bounds are known, our formulation enables us to use boolean satisfiability (SAT) solvers, which proves to be a strong tool. We obtain improved values for lower bounds on the non-negative rank of multiple matrices. In particular, we determined the xc of some regular polygons.
Read the full abstract

General Relativity and Quantum Cosmology

Testing General Relativity with Binary Lens Microlensing Events

Xinyang Jin, Shuo Cao, Xuanni Chen et al. (+3 more)

Einstein's General Relativity (GR), which has been precisely tested on galaxy and solar system scales, is still poorly constrained in extremely weak gravitational fields (with dimensionless Newtonian potentials of $\Phi \sim 10^{-8}$). In this Letter, we propose a new method to probe such a weak-field regime of gravity and measure the spatial curvature generated per unit mass. Specifically, binary microlensing events provide a laboratory to measure the parameterized post-Newtonian (PPN) parameter ($\gamma$), by combining the lensing mass ($M_{\rm lens}^{\rm GR}$) inferred from microlensing with the dynamical mass ($M_{\rm dyn}$) determined from interferometric astrometry. Astrometric tracking of binary lenses was previously hindered by their faintness and minuscule angular separations (typically a few milliarcseconds). This limitation has been alleviated by the deployment of GRAVITY+, which pushes the instrument's sensitivity and astrometric precision to unprecedented heights. Based on astrometric simulations of the binary microlensing event ASASSN-22av, we directly estimate $\gamma$ at the precision of ~23%. Such test of GR in the extremely weak-field regime can be further improved to much higher precision (~3%), based on more binary microlensing events with precise determination of the dynamical/lens mass.
Read the full abstract

All authors Xinyang Jin, Shuo Cao, Xuanni Chen, Yalong Nan, Xuchen Tai, Shuxun Tian

Computation and Language

When History Helps and Hurts: Selective History Use across Multimodal Turns

Shuoyang Sun, Kerui Gu, Hao Fang et al. (+2 more)

Reliable multimodal interaction depends on selective use of conversational history: an earlier question may remain relevant while its previous answer is outdated, whereas a current request may depend on historical evidence despite conflicting new observations. Existing multi-turn evaluations rarely separate these history-use demands from underlying question difficulty. To address this gap, we introduce ReTurn, a benchmark of 7,000 base tasks spanning visual and audio evidence for evaluating selective history use. For task-carrying history, Reconfirm/Reground require applying a historical question to current media while varying historical agreement; for evidence-carrying history, Retrieve/Rebind require answering a current question using historical media while varying current-media competition. Each pair preserves the target question, media, and answer. Tasks support open-ended and multiple-choice evaluation, with matched single-turn counterparts serving as answerability references. Across 13 omni-modal, vision-language, and audio-language models, median model-level open-ended accuracy falls from 93.7% with direct input to 72.3% in conversation. Behavioral probes show that high question recall can coexist with weaker task application, while competing media can redirect answers away from historical targets. Supervised adaptation yields only partial gains. ReTurn provides a controlled framework for assessing whether multimodal models select and use the historical information required by each request.
Read the full abstract

All authors Shuoyang Sun, Kerui Gu, Hao Fang, Shaoli Huang, Bin Chen