Machine Learning
DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum
Haoqiang Kang, Yiming Zhang, Yiyang Guo et al. (+5 more)
Executable environments enable LLM
agents to learn from the consequences of their actions. For
embodied agents, those consequences extend beyond whether the current task succeeds: completing a delivery can consume the time, energy, or money needed for later work. Learning to plan therefore requires environments that preserve these dependencies and turn them into feedback across a complete trajectory. We introduce DeliveryGym, a 3D environment for evaluating and training
agents on continuous courier shifts. It couples
multimodal tool interaction with persistent world dynamics and computes trajectory rewards from simulator events, making the costs of an
agent's decisions available for reinforcement learning (RL). The environment also adapts future training shifts to the policy's observed weaknesses while keeping evaluation fixed. Across six models and 13 city maps, evaluation exposes a gap between reliably executing assigned deliveries and choosing and sequencing work over a shift. On the unseen-city test set, RL improves Qwen3-VL-4B's net income by 54.3%, showing that learning from complete shifts improves performance under these coupled constraints. Adapting the training environment improves evaluation income by 18% over uniform sampling at 100 updates, indicating that which situations an
agent practices also matters. DeliveryGym provides an executable setting for studying how
agents learn to coordinate deliveries and preserve resources for later orders within an episode.
Read the full abstract ▾
All authors Haoqiang Kang, Yiming Zhang, Yiyang Guo, Chuying Li, Jianzhi Shen, Tianruo Rose Xu, Xiaokang Ye, Lianhui Qin
Soft Condensed Matter
Spontaneous filament formation and network self-assembly via active phase separation
Elena Lucas, Varun Venkatesh and Amin Doostmohammadi
We introduce Active Model H$^{-}$, a scalar phase-field model of non-
equilibrium phase separation in the overdamped hydrodynamic limit, and show that it produces filamentous networks with enhanced connections and arrested coarsening, a morphology not observed in existing scalar active field theories. Isolated filaments are unstable to spontaneous bending, and the resulting
curvature drives self-propulsion towards the convex side, causing them to collide and assemble into a percolating network. The networks are locally non-
equilibrium, with anomalously curved edges, disordered vertex angles and heterogeneous topological charge, yet recover Lewis's law macroscopically. Under noise they show balanced break and reform dynamics.
Read the full abstract ▾
Computation and Language
Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search
Tal Oved, Roi Pony, Oshri Naparstek et al. (+1 more)
LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run for a fixed number of iterations, and rank methods from that one point. We show this is not enough. We evaluate three evolutionary search strategies on five optimization tasks, commonly used by papers in the genre to report results. We run the analysis over a full grid of seeds and iterations. Our findings suggest that the best way to split a fixed budget between more seeds (width) and more iterations (depth) changes with the strategy, the task, and the total budget. Furthermore, we observe that the ranking of strategies also changes with the budget. On one task the strategy that looks worst at one seed is best at forty seeds. On another the best number of iterations is well below the value common in practice, so extra depth wastes budget that more seeds would turn into score. We provide a measurement protocol that reports the seeds-by-iterations frontier and practical guidance for using it.
Read the full abstract ▾
All authors Tal Oved, Roi Pony, Oshri Naparstek, Udi Barzelay
High Energy Physics (Theory)
Variational Solution of Non-Hermitian Quantum Field Theory in Two Dimensions
Paul Romatschke
This work describes a variational technique to solve non-Hermitian
quantum systems, in particular those with negative coupling quartic self-interaction. Differences of applying variational methods from standard
quantum mechanics to non-Hermitian
quantum mechanics – including potential pitfalls – are highlighted. A successful implementation of the variational approach for the non-Hermitian case is presented. The technique is used to analyze scalar
quantum field theory in d=2 with negative quartic self-interaction in the
Hamiltonian formulation in
lattice discretization.
Read the full abstract ▾
Rings and Algebras
On the trace identities of 2-dimensional tr-prime algebras over a finite field
Lucio Centrone, Rosiele Trindade Barbosa and Felipe Yasumura
We study associative
algebras endowed with a trace map. We classify the two-dimensional trace-
prime algebras over an arbitrary field. In addition, when the base field is finite, for each such
algebra, we provide a finite basis for the T-ideal of trace
polynomial identities.
Robotics
LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation
Wenbo Li, Yiteng Chen, Wenhao Li et al. (+1 more)
During manipulation,
robot and scene motion can move previously observed regions outside the camera's field of view. Geometry-aware RGB features encode visible structure, while control under partial observability requires scene
memory that integrates observation history and grounds inferred content in current evidence. We introduce \lifd{} (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene
memory. LIFD learns scene
tokens through multi-view agreement, then completes them from a single RGB view and recurrent
memory using rectified flow. Anchor-Guided Cross-
Attention anchors generation to current geometry-aware features, and compact slot features condition a visuomotor policy. Multi-view and
geometric supervision are used during representation learning; deployment requires one RGB camera, proprioception, and a task instruction. LIFD (Staged) reaches 91.6% average success on LIBERO and 79.8% on MetaWorld, improving LIBERO average success by 11.1 percentage points over Joint training. After policy-head adaptation with ten demonstrations per family, LIFD achieves 56.0% mean success across four UR5e task families, compared with 40.5% for OpenVLA-7B.
Read the full abstract ▾
All authors Wenbo Li, Yiteng Chen, Wenhao Li, Qingyao Wu
Strongly Correlated Electrons
Pressure induced structural phase transition and magneto-elastic coupling in Eu doped LaCrO$_3$
Asish Kumar Mishra, Mrinmay Sahu, Bhagyashri Giri et al. (+8 more)
In this study, we have carried out a detailed high pressure investigation on 5$\%$ Eu doped LaCrO$_3$ (ELCO) using synchrotron X-ray diffraction (XRD), micro Raman spectroscopy, and low-temperature magnetization measurements to correlate the structural and
magnetic properties under pressure. The high pressure XRD reveals the orthorhombic to rhombohedral structural phase transition around 10.6 GPa. The high pressure Raman data corroborate this result and indicate that the
lattice instabilities associated with the low-frequency soft modes play a crucial role in driving this transition. In addition, a pronounced anomaly in the Raman shift and integrated intensity of several Raman modes is observed around 4.5 GPa. By combining the low-temperature magnetization measurements with the anomalies observed in the XRD and Raman data and by comparing with the similar results in LaCrO$_3$ (LCO), a pressure-induced change in the
magnetic ground state to
antiferromagnetic ordering is predicted.
Read the full abstract ▾
All authors Asish Kumar Mishra, Mrinmay Sahu, Bhagyashri Giri, Bidisha Mukherjee, Suvashree Mukherjee, Harekrishna Bhunia, Tamalkanti Mukherjee, Sujoy Ghosh, Partha Mitra, Peter Liermann, Goutam Dev Mukherjee
Data Structures and Algorithms
Zhao Song and Song Yue
Marcus, Spielman, and Srivastava [MSS15] established the existence of Kadison–Singer partitions. We provide
polynomial-time
algorithms for the Kadison–Singer problem. For Hermitian
matrices $A_1,\ldots,A_m\in\mathbb C^{n\times n}$ of rank at most one, we give two
algorithms that find signs $\sigma\in\{\pm1\}^m$ satisfying $\|\sum_i \sigma_iA_i\|\le C\|\sum_i A_i^2\|^{1/2}$. The deterministic
algorithm achieves $C=3.3443$ using $\widetilde O(mn^2+n^{4.75})$ arithmetic operations. The randomized
algorithm achieves $C=4.8628$ using $\widetilde O(mn^2+n^{3.58})$ arithmetic operations in expectation. For vectors satisfying $\sum_i a_ia_i^*=I$ and $\|a_i\|^2\le\alpha$, the
algorithms yield partitions $[m]=I_1\cup I_2$ satisfying $\|\sum_{i\in I_j}a_ia_i^*-I/2\|\le (C/2)\sqrt\alpha$ for $j=1,2$.
Read the full abstract ▾
Computer Vision
AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization
Xu Yuan, Yi Wang, Zhuohang Jiang et al. (+8 more)
Recent advances in artificial intelligence (AI) are reshaping smart glasses from
egocentric capture and display devices into platforms for wearable intelligence. Smart glasses increasingly serve as wearable AI systems that connect first-person observation with real-time assistance under strict form-factor constraints. We frame this transition through the lens of AI smart glasses and define them as a system-level concept in which
egocentric sensing, resource-aware computing, intelligent
reasoning,
multimodal interaction, and real-world application constraints are co-designed for personalized assistance in the physical world. To systematically study this perspective, we organize the survey around four connected dimensions. First, we examine the hardware foundation that bounds sensing, computation, feedback delivery, and sustained deployment. Second, we study wearable intelligence, where
egocentric signals are transformed into perceptual, contextual, and agentic capabilities. Third, we discuss interaction design, through which users request, receive, correct, and regulate assistance during ongoing activity. Fourth, we analyze application scenarios across healthcare, accessibility, situated learning, daily life assistance, cultural tourism, and industrial support, showing how domain requirements reshape system design and evaluation. We further identify five cross-cutting research challenges for future AI smart glasses: next-generation hardware, trustworthy
egocentric intelligence, lifelong personalized
memory, proactive intelligence, and
embodied foundation models. By centering smart glasses as wearable-intelligence platforms, this survey provides a unified framework for organizing technologies, applications, and open challenges in this emerging area.
Read the full abstract ▾
All authors Xu Yuan, Yi Wang, Zhuohang Jiang, Haohao Qu, Yujuan Ding, Shanru Lin, Guoliang Xing, Hongxia Yang, Jiannong Cao, Qing Li, Wenqi Fan
Performance
Whittle index approach to multi-server scheduling with convex delay costs and impatient customers
Samuli Aalto
We consider the dynamic scheduling problem in a multi-class M/G/N + M queue with convex delay costs and impatient customers that have exponential abandonment times. We apply the Whittle index approach to find a reasonable heuristic solution for this tricky problem. By assuming exponential abandonment times, we are able to make a very straightforward use of the results of the corresponding problem with patient customers presented in Queueing Systems, Vol. 110, Article no. 2, 2026. Our main theoretical achievements are proving that the closed version of the corresponding discrete-time problem is indexable and deriving an explicit expression for the Whittle index. The discrete-time results are utilized to develop the Whittle index policy for the original continuous-time scheduling problem.
Read the full abstract ▾
Cryptography and Security
Sybil-TraceGuard: Traceability-enhanced Sybil Guardian for Connected and Autonomous Vehicles Using Dynamic Semi-supervised GNN
Qian Xu, Jiaxun Zhang, Chengyue Wang et al. (+1 more)
Connected and autonomous vehicles (CAVs) face severe Sybil attacks, where attackers exploit
privacy-preserving pseudonym-switching mechanisms to anomaly alternate identities while forging Basic Safety Messages (BSMs). Although existing schemes can flag suspicious behaviors, these temporally fragmented Sybil identities render traditional single-point and sequence-based deep learning methods ineffective. Linking these fragmented identities back to the source attacker is essential for root-cause elimination, particularly under extreme label scarcity. Therefore, the Sybil-TraceGuard is proposed as a dynamic semi-supervised spatio-temporal GNN framework for Sybil Guardian, prioritizing "who is responsible" over "whether an attack is happening". It comprises four tightly coupled modules: Incremental Stream Attack Detection (ISAD) for efficient Sybil attack pre-screening; the Dynamic
Topology-aware Constructor (DTC) for constructing spatio-temporal dynamic graphs; the Spatial GAT-Encoder with Multi-head
Attention (SGEM) to capture multi-identity logical conflicts in spatial interactions; and the Multi-scale Spatio-Temporal Audit (MSTA) to audit short-term and long-term temporal inconsistencies. These modules are optimized within a semi-supervised Mean-Teacher framework via feature-edge shuffling perturbations, regularizing the latent feature space using minimal labels. Experiments across four Sybil attack scenarios demonstrate that Sybil-TraceGuard effectively links fragmented pseudonyms to source attackers. It outperforms state-of-the-art baselines across unlabeled ratios of 0.70-0.95, maintaining high stability and sensitivity despite extreme class imbalance and varying hyperparameter settings.
Read the full abstract ▾
All authors Qian Xu, Jiaxun Zhang, Chengyue Wang, Zhenning Li
Analysis of PDEs
Nonexistence of solutions to $\Delta_pu+\Delta_qu+u^s|\nabla u|^t\leq 0$ on geodesically complete noncompact Riemannian manifolds
Biqiang Zhao
In this paper, we consider the inequality $\Delta_pu+\Delta_qu+u^s|\nabla u|^t\leq 0$ on geodesically complete noncompact Riemannian
manifolds. By a test function argument, we establish Liouville-type
theorems under the upper bound of volume of geodesic ball. In the Euclidean space $\mathbb{R}^n$, we obtain new nonexistence results which extend the result of Bhakta-Biswas-Filippucci \cite{BBF}. In particular, we have addressed the influence of the higher order term for $s<0$. At last, we present some examples to illustrate sharpness in some cases.
Read the full abstract ▾
Artificial Intelligence
Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
Qi Rong Sua, Junhao Dong, Nguyen Duc Thai et al. (+3 more)
Multi-
agent trading systems built on large
language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to
adversarial inputs is largely unknown. We study the vulnerability of LLM trading stacks to black-box, input-only attacks that enter solely via admissible social-media feeds. We introduce the Generic Multi-
Agent Trading System (GMATS), a framework that captures modern multiagent trading architectures and instantiate a class of black-box poisoning attackers that treat an LLM as a post generator and inject budget-constrained, plausibly benign social-media content into the analyst's evidence stream. We define contagion metrics that trace how
adversarial content propagates through the stack, including belief-shift scores at analyst and coordinator layers and attack-clean deltas on standard backtest metrics. Experiments on a safe offline
benchmark with historical
market and social data show that even simple input-only attackers can materially degrade risk-return profiles, sharply reducing Sharpe ratios. At the same time, we find that suitably designed multi-
agent topologies and coordinator
prompts can dampen
adversarial shocks and improve average robustness under identical poisoning budgets.
Read the full abstract ▾
All authors Qi Rong Sua, Junhao Dong, Nguyen Duc Thai, Yuqing Wen, Cheston Tan, Yew-Soon Ong
Earth and Planetary Astrophysics
Widespread plasma jets in the Martian magnetosheath revealed by dual-spacecraft observations
Abigail Tadlock, Chuanfei Dong, Chi Zhang et al. (+4 more)
Plasma jets in planetary magnetosheaths are transient, high dynamic pressure structures capable of strongly perturbing downstream magnetospheres and modulating
solar wind energy transfer. Although recently identified at Mars, their formation mechanisms and global occurrence remain poorly constrained. Using dual-spacecraft observations from Mars Atmosphere and Volatile
EvolutioN (MAVEN) and Tianwen-1, we show that magnetosheath jets occur throughout the Martian magnetosheath, in striking contrast to Earth where jet occurrence is strongly controlled by interplanetary
magnetic field orientation and largely confined to quasi-parallel shock regions. We propose that this widespread distribution is linked to Mars' extended hydrogen corona, which generates pickup ions that drive
proton-cyclotron waves upstream of the bow shock. Because this mechanism is generic to any body with an extended corona (or exosphere) embedded in a
stellar wind, this finding bears on
solar-wind interactions at comets and other small bodies, and on the space environments of unmagnetized terrestrial
exoplanets. These results indicate that magnetosheath jet formation can be governed not only by external
solar wind forcing but also by intrinsic planetary properties, pointing to a previously unrecognized pathway for
solar wind-
planet coupling at unmagnetized worlds.
Read the full abstract ▾
All authors Abigail Tadlock, Chuanfei Dong, Chi Zhang, Savvas Raptis, Hongyang Zhou, Xinmin Li, Jiawei Gao
Information Retrieval
Dense Feature Representation over Sequence Modeling: A Solution to the KDD Cup 2026 UniRec Challenge
Yi Zhang and Weiliang Ji
We describe our 10th-place solution to the KDD Cup 2026 Tencent UniRec Challenge, industrial click-to-conversion (CVR) prediction over 34.82M records, and we ask which mechanisms actually move held-out AUC. Starting from the official PCVRHyFormer baseline, a 15-step single-variable chain raises test AUC from 0.813237 to 0.827816, and our final submission reaches 0.828535. A leave-one-out ablation from the full model attributes the gain: removing the dense-feature representation stack costs 0.0095 AUC and removing the orthogonalized optimizer costs 0.0028, while no sequence-modeling component (merged single-stream backbone, polarity channel, auxiliary head, per-
token FFN) costs more than 0.0005, within or adjacent to a $\pm$0.0004 seed band. We also report a generalization hazard: the row-group train/validation split shares one time window, so validation AUC overstates the leaderboard by about 0.014; anti-memorization and high-cardinality-ID changes even invert sign against it, a divergence that traces to dump-to-dump distribution shift and survives a time-ordered re-split. Dense representation and optimization, not finer sequence modeling, drive CVR AUC at this scale, and verdicts must come from the held-out leaderboard.
Read the full abstract ▾
Machine Learning
Learning-Based Reconstruction of Optical Properties in Bilayered Media from Single-distance Time-Resolved Reflectance Measurements
Caterina Amendola, Giulia Maffeis, Lorenzo Buffoni et al. (+8 more)
The inverse problem of reconstructing optical properties, specifically absorption and scattering coefficients, in layered biological media from time-domain reflectance measurements remains a significant challenge for traditional analytical models. Inverse solvers based on the
diffusion equation often struggle with structural heterogeneity, frequently yielding poor accuracy for superficial absorption and deep-layers scattering. In this work, we propose a machine learning framework as an alternative approach to reconstruct the optical properties of a bilayered medium, benchmarking its efficiency and accuracy against model-based
algorithms. To overcome the intrinsic approximations of
diffusion theory and inverse reconstruction, we generated a robust synthetic
dataset of forward DTOF using exact Monte Carlo simulations at multiple source-detector distances. A machine learning pipeline was then trained on this
dataset and validated against state-of-the-art model-based reconstruction methods. Besides the significant reconstruction speed-up, the machine learning approach achieves higher accuracy than model-based inverse solvers, further providing an estimate of the parameter space dimensionality without requiring any a priori information about the number of layers in the investigated geometry. Further enhancements in the reconstruction accuracy can be expected in future extensions of this work, by training the pipeline over multiple DTOF curves from the same medium, in a joint multi-distance reconstruction approach.
Read the full abstract ▾
All authors Caterina Amendola, Giulia Maffeis, Lorenzo Buffoni, Lorenzo Chicchi, Francesco Coghi, Duccio Fanelli, Raffaele Marino, Fabrizio Martelli, Riccardo Paoli, Lorenzo Pattelli, Lorenzo Spinelli
Mathematical Physics
Classification of pairs of second-order Hamiltonian operators and hydrodynamic type systems in six components
Giorgio Gubbiotti, Lambertus Van Geemen and Pierandrea Vergallo
Following a recent characterisation of hydrodynamic systems with second-order
Hamiltonian structure in terms of alternating three-forms on the projective space, we present a complete classification of systems in 6 components. We use non-trivial group action techniques to obtain 5 canonical forms. A general result for every dimension is also obtained for one of these cases, whose
geometric structure is strictly related to the
symplectic canonical form.
Read the full abstract ▾
Quantum Physics
Transduction-Enabled Superconducting Quantum Repeater: Toward Deterministic Entanglement Distribution with High-Fidelity Gates
Francesco Fiorini, Jing Wu, Andrew Cameron et al. (+5 more)
Long-distance
entanglement distribution is hindered by
photon loss in optical fibers and the nocloning
theorem. Optical
quantum repeater (QR) protocols rely on Bell state measurements (BSMs), they are intrinsically limited to probabilistic
photon operations and fail 50% of the time. We propose a hybrid approach to building
quantum repeaters that combines the high transmission speed of photonic
qubits in optical fiber with the high-fidelity
quantum processing capabilities enabled by superconducting
circuits. The transduction-enabled superconducting QR (TESQR) architecture eliminates the need for probabilistic BSMs and allows deterministic processing operations. The TESQR framework always yields a final state at the remote nodes rather than aborting on
photon loss, manifesting deterministic
entanglement distribution within certain parameter regimes. We evaluate the performance by assessing output-state fidelities and success probabilities of
entanglement distribution using realistic noise models. Additionally, we integrate an
entanglement purification scheme and evaluate the performance through numerical simulations in QuTiP environment. Our results show that, for
entanglement swapping, the proposed scheme improves the
entanglement distribution rate by an average of 63% and by up to 159% compared with photonic-only architectures. Moreover, after purification, the end-to-end fidelities exceed 0.8 over distances up to 20 km.
Read the full abstract ▾
All authors Francesco Fiorini, Jing Wu, Andrew Cameron, Changqing Wang, Doga M. Kurkcuoglu, Rosario G. Garroppo, Michele Pagano, Silvia Zorzetti
Quantum Physics
Scalable entanglement distribution using encoded hybrid repeater chains
Stav Haldar, Saikat Guha, Don Towsley et al. (+1 more)
Long-distance
entanglement distribution requires error correction protocols to compensate for
qubit decoherence in
quantum memories and noise introduced during
entanglement swapping. We argue that repeater chains with error-correction capabilities should exploit more than one physical platform, combining the complementary strengths of different
quantum memory technologies into a single hybrid repeater architecture. An important constituent of such an architecture is a hybrid repeater which combines type-1
memories, characterized by fast
entanglement generation rates and suitability for multiplexing, and type-2
memories that offer long coherence times and low two-
qubit gate error rates. Taking the resource-intensive nature of hybrid nodes into account, we propose and analyze repeater chains in which only a subset of nodes need to be hybrid, while the remaining nodes are simpler first-generation repeaters with no error-correction capability. Through detailed Monte Carlo simulations of fault-tolerant encoded repeater chain protocols based on the three-
qubit phase-flip repetition code, the $[[7,1,3]]$ Steane code, and the $[[9,1,3]]$ Shor code, we demonstrate that these hybrid architectures outperform pure architectures based on a single
memory platform in terms of end-to-end
entanglement distribution rate. In our study we develop a full
circuit-level noise model of our architectures and examine the impact of an imperfect interface between the two platforms on our hybrid architecture. We also develop a modified version of the swap-as-soon-as-possible policy with multiplexing, more suited to our architecture where some nodes perform error-correction while others do not. This modified policy significantly reduces the information storage time in
memory qubits relative to the previously considered swap policies in encoded repeater chains.
Read the full abstract ▾
All authors Stav Haldar, Saikat Guha, Don Towsley, Filip Rozpędek
Graphics
Printing the Underdetermined: Materializing Multi-solutionness in Figurative Paintings
Yutao Ming, Teng Xu, Youjia Wang et al. (+6 more)
Figurative paintings are often approached as if they depict a single recoverable 3D scene: viewers infer depth and occlusion, and reconstruction pipelines attempt to converge to one stable model. We instead foreground multi-solutionness, the non-uniqueness of 3D configurations compatible with a single painted image, and propose a workflow that keeps this non-uniqueness visible and material. Multi-solutionness arises from two sources: unobserved content, where backsides and occluded volumes admit multiple plausible completions, and observed cues, where perspective, shading, and occlusion still underconstrain geometry. When additional views are synthesized by a
video generative model without explicit 3D constraints, small frame-level drifts become inevitable rather than exceptional. Our pipeline samples multiple camera-orbit multi-view
video sequences from one painting, reconstructs each sequence with 3D Gaussian Splatting into a point-based Gaussian scene representation where density
halos and ghosting expose unresolved degrees of freedom, and fabricates these representations as physical artifacts using DreamPrinting. By treating multiple compatible interpretations as explicit outputs rather than residual error, we provide a computational framework for spatial readings of figurative painting that can be inspected, compared, and discussed in both digital and physical form.
Read the full abstract ▾
All authors Yutao Ming, Teng Xu, Youjia Wang, Yunyang Liu, Fengmin Yang, Fuqiang Zhao, Jingyi Yu, Hua Yang, Yanjun Zhou
Statistical Methodology
Mutual Information as a Tool for Optimal Classification: Application to Identifying Rapid-Responding Behaviour
Santeri Holopainen, Jari Metsämuuronen, Mikko-Jussi Laakso et al. (+1 more)
Existing methods for identifying rapid-responding behaviour in large-scale assessments require parametric assumptions about the population. In this study, we propose a novel, non-parametric, mutual information-based framework of methods as an alternative. The methods within this framework compute the mutual information of the observed responses and discretised response times and maximise the information gain to determine a threshold that differentiates rapid responses from engaged responses. The only difference between the methods is the number of categories in the relevant variables. We present three methods explicitly. The first method uses response correctness and binarised response times. The second method uses correctness and categorises time into three groups. The third method uses raw responses and binarised times. We applied these methods to mathematics achievement data collected through the Programme for International Student Assessment in 2022. Furthermore, we examined the behaviour and usability of the first method in certain realistic conditions at the population and realised levels. The results indicated that the proposed framework is a viable alternative for identifying rapid responses. The framework's novelty lies in its non-parametric nature and its ability to utilise raw responses instead of correctness. Finally, we discuss some possible future research directions on this topic.
Read the full abstract ▾
All authors Santeri Holopainen, Jari Metsämuuronen, Mikko-Jussi Laakso, Janne V. Kujala
Computational Complexity
A Separation Between Distribution-Free SQ Learning and Dimension Complexity
Shyamal Patel
We show that there exists a class of boolean functions C such that $(i)$ there is a distribution-independent statistical query
algorithm for learning C that makes a
polynomial number of queries of inverse
polynomial tolerance and $(ii)$ for any set of functions $\Phi_1, \dots, \Phi_r$ such that for all $f \in$ C we can write $f(x) = \text{sign} \left( \sum_{i = 1}^r w_i \Phi_i(x) \right)$ for some set of weights $w_i \in \mathbb{R}$, we must have that $r \geq n^{\omega(1)}$. This gives a superpolynomial separation between dimension complexity and the query complexity of distribution-free learning in the statistical query model, negatively answering a question of Feldman, Kamath, and Srebro [FKS26]. Our construction C is a subclass of DNFs, and the proof is a simple consequence of recent progress on agnostically learning conjunctions [DKR25,CPS26] and the work of Razborov and Sherstov on the sign rank of DNFs [RS10].
Read the full abstract ▾
Optimization and Control
Extended MF-AFBSDDEswCN and stochastic optimal controls of linear system
Hao Wu
The research studies the extended mean-field anticipated forward-backward
stochastic delayed differential equations with common noise (extended MF-AFBSDDEswCN) by expanding the domination-monotonicity conditions. We generalize the conditions from a linear setting to a nonlinear one by including nonlinear adjoint functions which are key to guaranteeing the well-posedness of extended MF-AFBSDDEswCN. Utilizing this broader well-posedness framework for extended MF-AFBSDDEswCN, combined with other refined analytical tools, we examine two classes of
stochastic optimal control problems. These include a linear-convex problem and a linear-quadratic problem with input constraints that can be both time-dependent and random. Moreover, the control elements regarding the initial values are path-dependent, which will cause some essential difficulties. For each problem, we establish the existence and uniqueness of optimal controls and provide their explicit, closed-form representations.
Read the full abstract ▾
Computation and Language
Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection
Bo Xu, Chenyuan Wang, Xinyu Chen et al. (+5 more)
Hateful memes spread abusive content through implicit interactions between images and text, posing serious threats to the safety of online communities. In recent years,
multimodal large
language models have been widely used for hateful meme detection and are increasingly adopted to generate explainable detection results. However, we find that existing explain-then-detect methods often couple explanation generation and label prediction within the same training process. This coupling causes interference between task objectives, leading to limited detection performance and even worse results than simple SFT baselines. To address these challenges, we propose ProKDA, a progressive knowledge-to-decision
alignment method for explainable hateful meme detection. Inspired by the human annotation training process, ProKDA first uses an agentic background knowledge construction pipeline to obtain external knowledge related to meme understanding. It then adopts a three-stage training strategy that sequentially performs background knowledge learning, hatefulness detection learning, and hatefulness boundary
alignment. Unlike prior explain-then-detect methods that jointly optimize both tasks, ProKDA focuses on a single training objective at each stage. This design reduces interference between the two tasks and progressively transforms background knowledge into robust detection decisions. Experiments on three public hateful meme
benchmarks show that ProKDA achieves state-of-the-art detection performance and provides accurate, explainable, and evidence-supported decisions for hateful meme moderation. Project page: https://meizhiyuan88666.github.io/prokda.
Read the full abstract ▾
All authors Bo Xu, Chenyuan Wang, Xinyu Chen, Quanhao Zhu, Rui Lin, Liang Zhao, Hongfei Lin, Feng Xia
Combinatorics
Nearly Spanning Regular Subgraphs
Varun Sivashankar
Alon and Mubayi asked whether, for every integer $k\ge1$ and every $\varepsilon>0$, there exists $r_0=r_0(k,\varepsilon)$ such that every $r$-regular graph on $n$ vertices with $r\ge r_0$ contains a $k$-regular subgraph covering at least $(1-\varepsilon)n$ vertices. Previously, the
conjecture was known for $k\in\{1,2\}$ and for $k$ and $r$ both even. We answer this question affirmatively for general $k$ and $r$ with $\varepsilon=O_k(r^{-1/2})$. For $k=2$ and every odd $r\ge3$, we show that $\varepsilon=1/(r^2-3)$ suffices which is best possible.
Read the full abstract ▾
Machine Learning
PhyRestore: Physics-Structured Latent-Factor Restoration
Ahmed Shafee and Chayan Lahiri
Estimating temporal soil-loss change is challenging when physically meaningful input factors are noisy or corrupted, particularly because substantial changes are rare relative to the large number of locations exhibiting little change. We study this problem through the Revised Universal Soil Loss Equation (RUSLE) and introduce PhyRestore, a physics-structured latent-factor restoration framework. Rather than directly predicting soil-loss change or correcting a degraded physical estimate, PhyRestore restores corrupted physical factors and reconstructs temporal change through the known physical relationship. We evaluate PhyRestore in a watershed-scale bitemporal raster setting under isolated and simultaneous corruption of rainfall erosivity and cover management, comparing it with the degraded RUSLE estimate and Direct RF, XGBoost, MLP, and CNN models. Factor restoration improves high-magnitude recovery when the corrupted factors remain identifiable, but its advantage weakens under joint corruption, sparse positive extremes, and factor values outside the training support.
Read the full abstract ▾
Artificial Intelligence
Integrating knowledge from case reports: a medical ontology based multimodal information system with structured summary
Shuyu Guo, Lan Huang, Yichen Liu et al. (+2 more)
Published medical case reports serve as a crucial medical information carrier, documenting discoveries in rare diseases, diagnostic methods, and innovative treatments. Despite the wealth of clinical knowledge in millions of case reports in the public medicine literature database (PubMed), accessing relevant information efficiently is hindered by the limitations of traditional keyword-based
retrieval tools on unstructured and diverse case reports. To address the above issues, we introduce a comprehensive
multimodal information system for case reports integrating structured clinical summaries of patients including medical images and biomedical named entities from 52949 open-access case reports published from 2000 to 2021. The
multimodal essential information is organized in a well-structured medical ontology. Also, a powerful interface for searching and browsing case reports is designed to assist junior clinicians in retrieving cases effectively and improving the identification and diagnosis of rare diseases.
Read the full abstract ▾
All authors Shuyu Guo, Lan Huang, Yichen Liu, Hanbin Ma, Tian Bai
Human-Computer Interaction
Treadstone: A Social-Media-Inspired Platform for Multi-Agent Collaborative Data Analysis
Hyunwook Lee, Sungbeom Cho, William Benjamin et al. (+6 more)
Coordinating human analysts with autonomous AI
agents faces the same challenges as human-to-human collaboration: sharing intermediate results, avoiding conflicts, and maintaining group awareness. Current tools rely on unstructured messaging or single-threaded chatbot interaction, which lack the structure to track evolving hypotheses or link claims to evidence. We propose agentic social data analysis, a collaboration paradigm extending social data analysis with a shared coordination feed modeled on the content timeline in social media services. We instantiate this concept in TREADSTONE, a platform where human and AI
agents asynchronously post, link, and contest analytical claims via threaded messages within a shared feed. By allowing
agents to proactively broadcast hypotheses and enabling users to steer the analysis through lightweight curation, Treadstone seeks to balance machine autonomy with human analytical control. A qualitative user study shows that Treadstone fosters collaboration while preserving human analytical agency, in contrast to the solitary experience of conventional chatbot interaction.
Read the full abstract ▾
All authors Hyunwook Lee, Sungbeom Cho, William Benjamin, Changhee Lee, Hyotaek Jeon, Daeun Jeong, Sungbok Shin, Sungahn Ko, Niklas Elmqvist
Metric Geometry
Algebraically independent distances and rigid metrics
Yoshito Ishiki
We study metrics whose distances on distinct two-point subsets are algebraically independent over the rationals. We prove that every compatible metric on a strongly zero-dimensional metrizable space of cardinality at most continuum can be uniformly approximated by compatible metrics with this property. If the space is completely metrizable, the approximating metrics can also be chosen complete. For every $\sigma$-compact metrizable space, the metrics with algebraically independent distances form a $G_\delta$ set in the uniform
topology. We also study rigid metrics, whose only bijective self-isometry is the identity. On every locally compact Polish space, rigid proper metrics form a $G_\delta$ set among proper compatible metrics. Using a
theorem of Niemiec, we obtain uniform density of rigid metrics on compact metrizable spaces with at least three points. Passing to compact completions then yields rigid approximations of every totally bounded compatible metric on any space with at least three points.
Read the full abstract ▾
Image and Video Processing
Video Based Assessment of Surgical Skills Using Frozen Pretrained Video Foundation Models
Sangrock Lee, FNU Rahul and Suvranu De
Automated
video-based
surgical skill assessment has advanced rapidly, yet rigorous evaluation of continuous standardized score prediction under participant-level generalization to unseen trainees remains limited. We introduce VBA-Net+, a
video-only framework for Fundamentals of Laparoscopic Surgery (FLS) score regression and pass-fail classification using pretrained
video foundation models as frozen feature extractors. We evaluate two FLS
datasets, suturing and pattern cutting, using VideoPrism, V-JEPA2, and VideoMAE v2, with a frame-level SimCLR baseline. A lightweight fully convolutional head is trained on
embeddings offline and evaluated using participant-level leave-one-user-out (LOUO) cross-validation within the standardized assessment protocol. For continuous score prediction, the best representation achieves $R^2$=0.6367 for suturing and 0.9261 for pattern cutting. For pass-fail classification at official FLS thresholds, area under the receiver operating characteristic curve (AUC) reaches 0.9073 and 0.9906, respectively. Frozen
video-encoder pipelines generally outperformed the frame-level SimCLR pipeline, particularly for suturing, providing a
benchmark for
video-only FLS assessment.
Read the full abstract ▾