Peer Revenue Past citations are no guarantee of future returns

Papers

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

Computer Science

cs Watch Computer Science (sign in to use)

Tuesday 18 August

Systems and Control

On the behavior assignment problem

This paper introduces the asymptotic behavior assignment problem for nonlinear systems. Given a controlled system and a reference system with an “open” input, the goal is to design a regulator such that, for every admissible input, the asymptotic input-output behavior of the closed-loop system reproduces that of the reference. This formulation captures, as special cases, classical model matching, disturbance rejection, and master-slave synchronization, but does not assume that an explicit tracking or regulation error is available for feedback. Motivated by nonlinear output regulation, we discuss how steady-state concepts for autonomous systems must be adapted when the closed-loop dynamics is not autonomous. In a SISO normal-form setting we devise sufficient conditions for the solution of the behavior assignment problem by introducing a synchrony-detection signal whose convergence to zero is equivalent to successful behavior assignment, thereby reducing the problem to a standard stabilization one. Two examples, a tunnel-diode circuit with multiple input-dependent equilibria, and a pendulum frequency-matching problem, illustrate how the proposed framework avoids artificially selecting a specific steady state.
Read the full abstract

Cryptography and Security

An Emulation Anchored Digital Twin Testbed for Cyberattack and Defense Analysis in Hospital IT OT Environments

Modern hospitals increasingly rely on integrated Information Technology (IT) and Operational Technology (OT) infrastructures to support critical healthcare services. However, this convergence expands the cybersecurity attack surface and makes safe validation of defensive mechanisms difficult on live systems. Existing testbeds often focus on isolated IT or OT environments and do not capture realistic cross-domain healthcare interactions. This work presents a hospital IT and OT cybersecurity testbed coupled with a digital twin for monitoring, experimentation, and validation of countermeasures. The testbed emulates a central server, Electronic Health Record (EHR) systems, SCADA-based infrastructure, and segmented IT, OT, and DMZ networks. It supports controlled cyberattack execution, software-patch evaluation, and training of RL-based defense agents. The testbed is further extended to a digital twin that models the real-time state of the environment using log and network statistics and enables bidirectional interaction through command execution and container lifecycle orchestration. Modbus/TCP and FHIR/HL7 support realistic communication across healthcare and industrial components. Experimental evaluation shows low computation overhead, with average normalized CPU utilization below 0.4 % per container and most lightweight services operating below 0.01%. OpenPLC Modbus TCP operations achieve a median round-trip latency of 0.901 ms. The testbed also captures a multi-stage SSH-based attack propagating from the DMZ to the IT and PLC networks. The framework provides a foundation for extending the emulated environment toward a hardware-enabled hospital digital twin.
Read the full abstract

All authors Prashant Rawat, Ravi Kumar Bairagi, Arunima, Geeta Yadav

Machine Learning

Elimination Geometry

This monograph develops elimination geometry (EG), a typed, native-loss, audit-oriented framework for studying when locally optimal objects can be realized by a shared deployment rule. Elimination and compression may erase distinctions required by prediction, inference, control, or representation. EG asks which distinctions are lost, whether the induced defect is visible to the declared task, and whether changing information, architecture, action space, or deployment domain can repair it. EG separates local solvability, global realizability, and finite-sample certifiability. It derives native defects from the original objective and distinguishes architecture obstruction from model approximation, generalization, and implementation error. The monograph synthesizes tools from geometry, optimization, information theory, statistics, and machine learning into interfaces for integrability, representation admissibility, resource constraints, observational overlap, and common deployment. Formal results address regular, coordination, singular, compositional, and resource-limited mechanisms with explicit antecedents and claim boundaries. Applications include sparse model selection, distribution-free prediction, observational treatment policies, routed expert and retrieval systems, and learned score fields. Obstruction-Aware Learning and Inference links structural diagnosis to finite-data authorization, mechanism-matched intervention, and independent validation. Reproducible synthetic and real-data studies illustrate how certificates can guide architecture repair while recording failed gates and unresolved cases. The framework requires the deployment contract, native endpoint, competing explanations, information and compute budgets, and validation rule to be fixed before a persistent performance floor is attributed to architecture.
Read the full abstract

Artificial Intelligence

LLM-Derived Preference Judgments Are Not Self-Consistent

Agents increasingly interpret a person's natural-language preferences by querying an LLM for numerical preference judgments, e.g., by asking how much the person would be willing to pay for an item. A growing body of work estimates a utility function from these judgments and then chooses actions based on their estimated utility. This pipeline assumes the judgments are approximately self-consistent: that a single utility function can reproduce them. But are they? To study this question, we measure the self-consistency of cardinal LLM preference judgments. For example, the difference in stated willingness-to-pay between two items should match the stated payment that makes a person indifferent to exchanging them. We develop statistical tests and interpretable measures of how far observed responses depart from the best-fitting self-consistent utility function. Experiments with flight, apartment, and hotel examples across six LLMs reveal large persistent inconsistencies. This suggests that LLM-derived preference judgments cannot be faithfully summarized by a single utility function.
Read the full abstract

All authors Matthew T. Ford, Francis Bahk, Jingjing Wang, Adam S. Jovine, Tinghan Ye, David B. Shmoys, Peter I. Frazier

Software Engineering

Unified Message Model for Heterogeneous Serial Data Exchange Protocols

Modern embedded systems are becoming increasingly complex and typically integrate numerous heterogeneous devices, such as controllers, sensors, actuators, and supporting subsystems. As a result, their development and integration involve a wide variety of serial communication protocols, ranging from standardized solutions to partially standardized and fully project-defined formats. Efficient development of such systems increasingly depends on automation toolchains, which in turn require a clear, unified, and machine-processable formal basis. This paper proposes a unified, protocol-agnostic message model for explicit and deterministic description of serial messages. The model is based on formal definition of data types, atomic message elements (containers), and complete message structure. In addition to the model itself, the paper introduces methods for practical work with it, including configurable message types for expressing structural constraints and supporting deterministic automation, as well as configurable user representations for engineering-oriented reading and editing. The proposed model and methods are demonstrated through implementation in an industrial tool environment. The results show that the approach can support machine-readable interface control document development, automated generation of transport-layer software, and practical engineering work with both standardized and weakly formalized serial protocols. Taken together, the proposed model, methods, and tool implementation provide a practical foundation for automation toolchains in heterogeneous serial communication development.
Read the full abstract

Machine Learning

rl-triton: High-Performance Triton GPU Kernels for Reinforcement Learning Credit Assignment

We present rl-triton, an open-source library of high-performance GPU kernels for reinforcement learning credit assignment, implemented in Triton. The core contribution is a unified associative scan framework that recasts seven distinct RL estimation algorithms - Generalized Advantage Estimation (GAE), V-Trace, Retrace($\lambda$), TD($\lambda$) returns, discounted returns, eligibility traces, and episodic prefix sums - as instances of a single first-order linear recurrence solved in $O(\log T)$ parallel steps. All algorithms share the same associative scan operator, with algorithm-specific fused Triton kernels constructing their recurrence coefficients on-chip. We verify the associative operator algebraically and define the treatment of terminated and truncated episodes explicitly. Benchmarks show a 1.6-5.70$\times$ full-call speedup over a vectorized torch-compile baseline in the massively parallel simulation regime (thousands of environments, short rollouts). The reported range covers all seven algorithms on both GPUs, both with and without per-step truncation handling. For most algorithms, speedups increase at longer sequence lengths, as the baseline requires more scan stages as $\log T$ grows, each adding an intermediate HBM round-trip. The library is available at https://github.com/simonsays1980/rl-triton.
Read the full abstract

Artificial Intelligence

Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing

What a reasoning model writes is only a partial record of the process that produces it. We introduce a two-level internal readout for mixture-of-experts reasoning. We first distill vocabulary-scale J-space into J64, a 64-axis semantic frame learned from the model's own reasoning states. J64 reveals readable process state that the emitted trace does not show: it separates inference effort from problem-induced strain. It also adds 0.096 to 0.135 held-out AUC over a baseline that reads the same rollout as token occupancy and aggregates it in exactly the same way. We then reconstruct J64 from native expert-routing statistics. The result is R64, a low-overhead proxy: its median per-axis correlation with J64 is 0.69 to 0.86 across three models and two families, and on gpt-oss-20b it preserves 95 to 100% of J64's predictive gain. The readout supports test-time decisions at two temporal resolutions. Over completed candidate sets, J64 and R64 improve single-branch selection, and R64-weighted voting improves plain majority voting in seven of eight settings. During generation, rolling readout windows drive a cumulative stop-and-resample policy whose operating point is fixed on training questions alone. J64 improves accuracy by 1.1 to 5.9 points over a sibling-permuted control, and the routing-only R64 proxy retains 0.9 to 3.2 of those points. Finally, router edits aimed at the mechanism J64 names induce the predicted reasoning behaviors and shift a diagnosed stall from numerical guessing toward exact symbolic execution. Together, J64 makes latent process state readable, while routing makes it deployable and actionable.
Read the full abstract

All authors Kang Chen, Sihan Zhao, Yixin Cao, Yu-Gang Jiang

Discrete Mathematics · Cross-listed from math.MG

Non-rectifiable Delone sets under pointwise co-Lipschitz bijections

For each $d\in\N_{\geq 2}$ we construct a Delone set $Y$ in $\R^{d}$ for which every Lipschitz bijection from $Y$ to $\Z^{d}$ has a very irregular inverse. For example, the inverse fails to be Lipschitz, even at just a single point. Further, we clarify the relationship between several notions of regularity for bijections between Delone sets, studied in the literature.
Read the full abstract

Numerical Analysis · Cross-listed from q-fin.CP

COS-TT-CHF: A Tensor-Train Characteristic-Function COS Method for Multi-Asset Option Pricing

This paper considers European multi-asset option pricing under Lévy and affine characteristic-function models. The main obstruction is the curse of dimensionality: direct multidimensional COS pricing forms tensor-product coefficient arrays whose size grows exponentially with the number of assets. We study and extend COS-TT-CHF, a low-rank construction that uses TT-cross to compress sampled characteristic-function tensors into tensor-train COS coefficients for arithmetic basket and min/max option pricing. Once built, the compressed representation gives fast post-setup strike-grid and selected component Delta/Vega calculations. The numerical study compares with adaptive-quadrature Fourier benchmarks, direct COS, a tensor-Fourier min-option benchmark, and quasi-Monte Carlo (QMC) references based on randomized Sobol points. The reported timings show a low-dimensional crossover against direct COS as the benchmark moves from $d=2$ to $d=4$, favorable timings against the tensor-Fourier min-option benchmark from $d=3$ onward, and favorable timings against the QMC common-Heston reference already at $d=2$. The reported tests reach $d=30$ for GBM and $d=20$ for VG, NIG, and common-Heston benchmark families, with accuracy, rank, runtime, control-sensitivity, and component Delta/Vega diagnostics reported throughout.
Read the full abstract

Computer Vision

MaLViL: Multi-axis Low-rank Vision-LSTM for Medical Image Segmentation

Vision-LSTM (ViL) enables efficient global modeling, but its cost still scales with the number of spatial tokens, so existing segmenters confine ViL to a coarse bottleneck and lose fine anatomical detail. Rasterizing 2D features into a 1D sequence further breaks adjacency across the orthogonal scan axis. We propose MaLViL, a Multi-axis Low-rank Vision-LSTM network that extends ViL across decoder resolutions. Bidirectional low-rank ViL (Bi-LRViL) reasons on a compact orthonormal subspace and preserves detail through an orthogonal residual; scale-aware SaLViL restores cross-axis neighbors before serialization; and a Cross-Directional Mixer (CDM) fuses orthogonal horizontal and vertical traversal paths. Statistics-Guided Skip Modulation (SGSM) further retains boundary cues in encoder skips. On skin-lesion, ultrasound, and multi-organ CT benchmarks, MaLViL achieves competitive or state-of-the-art segmentation accuracy, while reducing ViL operator memory by up to $83\times$ at fine decoder resolutions. Code is available at: https://github.com/xmindflow/malvil.
Read the full abstract

All authors Afshin Bozorgpour, Sina Ghorbani Kolahi, Moein Heidari, Ilker Hacihaliloglu, Dorit Merhof

Artificial Intelligence

Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models

The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and functionally by replacing their mechanisms with constants. To call these operations equivalent is not yet a mathematical statement: one returns a graph and remembers only the targets, whereas the other returns mechanisms and also remembers the imposed values. We make a dependency-level comparison precise for deterministic acyclic structural causal models with finitely many endogenous variables. If $\operatorname{Graph}(F)$ extracts the dependencies of a mechanism family $F$, our main theorem is $\operatorname{Graph}(F^\iota)=\operatorname{Surg}(\operatorname{Graph}(F),T_\iota)$. Thus replacing target mechanisms removes exactly the dependencies removed by graph surgery. For a model $M=(G,F)$ whose graph may contain unused arrows, we characterize when the same equality holds with $G$ in place of $\operatorname{Graph}(F)$; it holds for every intervention exactly when $G$ records the dependencies of $F$ exactly. We then define the intervened model, characterize its run, show how sequential interventions combine, and prove that an outcome depends only on interventions at its actual dependency ancestors. All principal results are machine-checked in an accompanying Lean 4 development.
Read the full abstract

Robotics

OVIP-SG: Open-Vocabulary Instance-Preserving Scene Graphs for Mapping and Retrieval of Small, Fine-Grained Objects

Integrating open-vocabulary perception into object-level 3D scene graphs is a double-edged sword. While vision-language detectors recover long-tail categories and small, fine-grained objects overlooked by closed-set models, they also tend to fragment large surfaces and merge small objects into larger neighboring objects, compromising instance-level consistency and undermining mapping fidelity. Moreover, existing methods struggle to retrieve previously unmapped targets or determine whether a queried object is absent, hindering robust embodied open-world navigation and exploration. We present OVIP-SG, a unified framework for instance-preserving semantic mapping, functional scene partitioning, and language-guided small, fine-grained object retrieval. OVIP-SG uses a vision-language model (VLM) to enumerate scene-specific categories for robust open-world detection. Symmetric 3D Intersection over Union (IoU) association and area-weighted feature fusion preserve small independent instances, while VLM-inferred object functions partition scenes into compact functional search regions. A four-stage cascaded retrieval pipeline further incorporates voxel voting and determines target absence from exploration coverage. Under a unified evaluation protocol on Replica, OVIP-SG outperforms ConceptGraphs by 6.31 points in class-mean accuracy (mAcc) and 5.15 points in frequency-weighted mIoU (F-mIoU) while achieving a class-agnostic native-instance Panoptic Quality (PQ) of 0.398. It reduces the search area to 21.8% of the indoor floor space and reaches 0.773 balanced accuracy for object-presence classification. Real-world robotic experiments further demonstrate its practical effectiveness. Code is available at https://github.com/Agibot-Spatial-Intelligence/OVIP-SG.
Read the full abstract

All authors Tianjing Hao, Haiyu Lan, Angsong Li, Cheng Chen, Enyu Li, Jiarui Yang, Yuning Su, Peiwen Lin, Wang Chuang

Information Retrieval

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing systems usually rely on prompted expansions, independently trained modules, or staged optimization, leaving generated expansions only indirectly aligned with the retrieval loss that judges them. We train a single decoder-only LLM end to end, where the same model generates the expansion and encodes both the expanded query and candidate documents. This unified setting creates a moving-target problem: retrieval supervision should improve query-side expansion, but the same update also shifts the document embeddings that serve as retrieval targets. We introduce Document Embedding Preservation Tuning (DEPT), which keeps tuned document embeddings close to cached initial embeddings while allowing retrieval gradients to pass through straight-through decoding into the generator. DEPT converts joint query–document movement into query-side adaptation against approximately stable, whitened document embeddings that support index reuse and online hard-negative mining. Experiments with Qwen3-4B-Instruct-2507 and LLaMA-3.2-3B-Instruct on five datasets in BEIR benchmark show that DEPT improves average retrieval quality over training-free, independently trained, and staged unified baselines, while ablations isolate the effects of preservation, whitening, end-to-end expansion training, and online negatives. Code is available at https://github.com/ILSparkle/DEPT.
Read the full abstract

All authors Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li, Yanzhao Zhang

Cryptography and Security · Cross-listed from quant-ph

Unclonable encryption from BB84 states: a simultaneous Goldreich-Levin reduction

Goldreich-Levin reductions are ubiquitous in cryptography: they convert an algorithm capable of guessing $\langle r, m \rangle$ (mod $2$) for a hidden string $m$ and a random challenge $r$, to one that is capable of extracting the entirety of $m$. Here, we describe a "simultaneous" Goldreich-Levin reduction for two entangled parties who are capable of guessing $\langle r, m \rangle$ given uniformly random identical challenges $r$. This allows to upgrade any unclonable encryption scheme satisfying "search" security to one satisfying the gold standard of unclonable "indistinguishability". As a corollary, we show that the simplest candidate unclonable encryption scheme from BB84 states satisfies unclonable indistinguishability. This result was discovered by GPT-5.6 Ultra after a few interactions. Our prompts included recent results on unclonable encryption by Ananth and Sahai, and Ragavan.
Read the full abstract

Robotics

Iterative Grasp Pose Refinement: A Deep Reinforcement Learning Approach for 2D Vision

Developing robots capable of understanding and manipulating objects requires compact, interpretable, and generalizable representations. This work proposes a reinforcement learning-based framework for robotic grasp refinement, integrating keypoint-based object representations with a Deep Q-Network (DQN). Using 2D overhead images captured in a simulated environment, a geometric-based algorithm generates initial grasp candidates, which are iteratively refined by the proposed framework, transforming failed grasps into successful ones. Experiments conducted on 300 objects from the Dex-Net dataset using a UR5 manipulator demonstrate the framework's effectiveness, achieving a 100% success rate on objects previously deemed ungraspable by geometrical methods. The framework's sim-to-real transferability is further validated through physical experiments on a Delta parallel robot, where a refined grasp successfully manipulates an object that was previously ungraspable. The findings underscore the effectiveness of reinforcement learning in addressing challenges in robotic grasping, offering a scalable and adaptable solution for contact-rich manipulation tasks.
Read the full abstract

All authors Amir Arsalan Nematollahi, Shayan Ahmadi, Mehdi Tale Masouleh, Ahmad Kalhor

Artificial Intelligence

Validated Adaptation for Aerial Crowd Monitoring at Mass Gathering Scale: A Deployment Protocol, a Severity Law, and a Diagnostic for Label-Free Drone Crowd Counting, Toward the FIFA World Cup 2034 (Saudi Arabia)

Saudi Arabia will host the 2034 FIFA World Cup and already operates crowd management at Hajj scale. Drone-based counting must hold accuracy on footage unlike anything in its training corpus, without labels, and must warn of dangerous inflow before a crush forms. We deliver a validated answer built on 525 controlled runs, a full-resolution corpus study, five falsification ablations, and a five-condition safety-interlock evaluation. Label-free adaptation recovers 31-49% of shift-induced error across four corruptions and five severities, with the strongest method gaining 41.8 MAE over the frozen source (95% CI [34.1, 49.6], p=7.5x10^-10, d=2.52). We establish a severity law separating methods with a constant absolute margin from the one whose margin grows, and a stability budget identifying which configuration is safe to fly. On a full-resolution corpus carrying a genuine +48 MAE aerial gap (source retrained to 14.6 validation MAE, a 34% improvement), adaptation repairs the dense-scene undercounting that would otherwise under-report a forming crush, and the flux-based risk module fires on real congestion episodes in 2 of 6 full-length clips. We localise the recoverable error: in a regime built to favor a physics-informed conservation prior (300-frame clips at 200ms spacing, five times wider than standard), the adaptation signal is normalisation-driven, not flow-driven; the continuity residual is invariant to the proportional counting errors domain shift produces, confirmed by four on/off ablations correlated at r=0.999 and a 40% input corruption moving accuracy by only 0.05 MAE. A label-free shift gate shows shift magnitude and accuracy damage are rank-independent (Spearman rho=0.20; rho=-0.60 among genuine shifts), quantifying the 58% of headroom a magnitude gate forgoes. We establish unconditional adaptation with tail monitoring as policy, closing with a six-point protocol.
Read the full abstract

Computers and Society

Governing Delegation to Generative Artificial Intelligence: Human Direction, Work-Related Orientation, and Modes of Use

Delegating cognitive operations to generative artificial intelligence redistributes execution and raises a governance problem: where human direction of the task remains. We distinguish two routes. Specified delegation places that direction before execution, through instructions, constraints, or criteria that delimit the task. Iterative coproduction places it during production, through interventions that correct or redirect provisional outputs. To examine both routes, we use aggregate monthly cells from the Anthropic Economic Index for April and May 2026. The AEI distinguishes two modes of use: 1P API, which corresponds to direct traffic through Anthropic's API, and Claude.ai, which combines activity from Chat and Cowork. On this basis, we test whether a stronger work-related orientation of human-AI interaction is associated with more specified delegation within each mode and whether the increase in the iterative profile is greater in Claude.ai than in 1P API. The main analysis uses level-0 O*NET tasks and estimates how both profiles change when an eligible record reallocates ten percentage points from personal use to work-related use. The iterative comparison is restricted to 1,411 node-month pairs observed and eligible in both modes. Specified delegation increases by 2.76 points in 1P API (95% CI: [2.30, 3.22]) and by 1.45 in Claude.ai (95% CI: [0.93, 1.97]). On the common support, iterative coproduction changes by-0.30 points in 1P API and by 0.15 in Claude.ai, yielding a between-mode difference of 0.45 points (95% CI: [0.15, 0.75]). These findings show that work-related orien tation is associated with stronger traces of prior human direction and that the observable iterative response varies across modes of use. The article shifts attention from how much the AI executes to when human direction leaves observable traces.
Read the full abstract

Computer Vision

RetiWave-Mamba: A Dual-Stream Network for Retinal Disease Detection based on Multi-scale Context and Feature-Adaptive Mamba Projection

Retinal diseases are a leading cause of irreversible vision impairment, making early and accurate diagnosis essential for effective treatment. Optical Coherence Tomography (OCT) serves as a critical imaging modality for this purpose, yet its automated analysis is hindered by inherent speckle noise, varying lesion scales, and subtle inter-class similarities. To address these challenges, we propose a novel framework, RetiWave-Mamba, which integrates spatial-frequency domain learning with state-of-the-art state space models. The framework utilizes Discrete Wavelet Transform (DWT) to decompose OCT images into low- and high-frequency streams, enabling decoupled processing of structural context and fine-grained details. For the low-frequency branch, we design a Multi-scale Contextual Localization Module (MCLM), which synergizes multi-scale dilation with spatial attention to expand the global receptive field and precisely localize lesion regions. For the high-frequency branch, we introduce an Attention-Guided High-Resolution Network (AG-HRNet) equipped with an intelligent gating mechanism to suppress noise propagation during multi-scale interactions. Furthermore, a Feature-Adaptive Mamba Projector (FAMP) is incorporated to form complementary channel-wise feature paths and adaptively reweight them using Mamba-generated gates. Extensive experiments on the OCT-C8 dataset demonstrate that our approach achieves a state-of-the-art (SOTA) classification accuracy of 98.38, surpassing existing methods. These results highlight the effectiveness of RetiWave-Mamba in identifying retinal pathologies and support its potential for computer-aided OCT image analysis.
Read the full abstract

Numerical Analysis

Joint Near-Field Holotomography Reconstruction with a Phase-Guided Bregman TV Regularization

Near-field holotomography combines coherent diffraction imaging with tomographic acquisition to recover the three-dimensional complex refractive index of a specimen. Since the measured diffraction intensities are generated by a nonlinear object transmission and wave propagation process, the resulting inverse problem is intrinsically nonlinear and ill-posed. We study a direct variational reconstruction framework based on a fully nonlinear wave propagation model that avoids both intermediate phase retrieval and linearization under the weak-object approximation. We analyze the forward operator in appropriate Banach spaces, establish its Fréchet differentiability, and derive explicit gradient expressions for variational reconstruction. To improve quantitative reconstruction of weak absorption features, we further develop a phase-guided Bregman TV regularization framework that exploits structural correlations between phase and absorption components. This enables multi-material reconstruction without imposing a globally fixed ratio between the two components. We perform numerical studies on synthetic phantoms and experimental data. The results demonstrate stable three-dimensional reconstructions and improved recovery of the absorption contrast compared to state-of-the-art methods.
Read the full abstract

Machine Learning

OOD Detection for EEG-based Machine Learning in High-Risk Environments

Machine learning models for electroencephalography (EEG) analysis show great promise across a wide range of applications, but their deployment in high-risk domains is hindered by their vulnerability to distribution shifts. Encountering out-of-distribution (OOD) data can lead to catastrophic, overconfident predictive failures. While OOD detection methods can mitigate these risks, they remain heavily under-explored for EEG. Moreover, evaluations in the broader literature typically evaluate OOD detection performance in isolation, ignoring their practical impact on downstream applications. To bridge this gap, we introduce a benchmark for EEG OOD detection, evaluate a broad range of methods, and furthermore evaluate their value in two clinical downstream prediction task. Our results disentangle OOD detection and model uncertainty estimation capabilities, which are frequently conflated in the literature, provide actionable insights about the current state of the art for EEG OOD detection and model uncertainty estimation, and demonstrate how complementary methods for both aspects can be combined to form a robust safety net for the deployment of EEG-based machine learning models in real-world applications.
Read the full abstract

Information Retrieval

From Student Risk Prediction to SC2R: Semantics-Constrained Counterfactual Recourse for Educational Decision Support

Learning analytics models can identify students at risk of poor performance, but they do not directly indicate which interventions are feasible, actionable, and compatible with educational constraints. This paper introduces SC2R, a semantics-constrained counterfactual recourse framework for educational decision support. SC2R combines a calibrated predictive model, integer-programming-based recourse generation over discrete action variables, a lightweight RDF vocabulary for intervention-plan representation, and SHACL validation for enforcing timing, budget, immutability, and availability constraints. The framework is evaluated offline on the OULAD dataset using snapshots constructed relative to each assessment at two decision horizons. Results show that the predictive component provides strong performance, that compact intervention plans can be generated at scale, and that semantic validation reveals infeasible plans that lighter optimization-only settings would otherwise accept. Rather than claiming causal improvement in student outcomes, this work shows that counterfactual recourse becomes more operationally meaningful in education when recommendations are not only model-valid, but also semantically feasible and machine-checkable.
Read the full abstract

Artificial Intelligence

MoNe: Modular Neural Memory for Efficient Long Context Inference

We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to enable long-context inference without retraining. MoNe reads context in fixed-size segments via test-time learning of fast-weight neural memory networks with layer-localized gradient updates; at inference, the memory generates keys and values from the query tokens alone, with no context tokens re-read. This two-phase design decouples inference cost from context length, achieving $O(N)$ preprocessing and $O(1)$ query cost with peak GPU memory that does not grow with $N$. At 128K tokens, MoNe reduces both compute and peak GPU memory by approximately 80% compared to ICL with only 6.4% parameter overhead. MoNe generalizes to context lengths far beyond the backbone's native window, achieving strong performance on needle-in-a-haystack and word extraction benchmarks from RULER, where ICL degrades sharply.
Read the full abstract

All authors Wonguk Cho, Kyubyung Chae, Tribhuvanesh Orekondy, Sunghyun Park, Hyoungwoo Park, Jeongho Kim, Arash Behboodi, Kyuwoong Hwang, Sungrack Yun

Numerical Analysis

Fast high-order solvers for the Lippmann–Schwinger equation in piecewise-smooth heterogeneous media

This article presents a fast, high-order Nyström solver for the two-dimensional Lippmann–Schwinger equation arising from time-harmonic scattering by penetrable, piecewise-smooth heterogeneous media. Relying on high-order evaluation of the Newtonian potential on unstructured grids adapted to interfaces of discontinuity, the methodology achieves high-order accuracy using existing fast algorithms such as the fast multipole method. As an iterative method the solver exhibits rapid convergence when coupled to a preconditioning strategy that exploits a class of structured-grid solvers—fast solution methods offering quasi-linear time and memory complexity and nearly-constant iteration counts, but long limited in accuracy. The preconditioning strategy couples the Nyström discretization—given by high-order quadrature nodes over a (curved) unstructured mesh conforming to the support of the spatially varying contrast—to a uniform Cartesian grid underlying the fast preconditioner via a pair of transfer operators. The resulting preconditioner inherits the frequency-robust behavior of its Cartesian counterpart without sacrificing the geometric flexibility and high-order accuracy of the unstructured discretization. We prove that invertibility of the proposed preconditioner holds under explicit conditions on the mesh sizes and on the Cartesian preconditioner. Numerical experiments demonstrate that the preconditioned system requires significantly fewer GMRES iterations than its unpreconditioned counterpart, with iteration counts almost independent of mesh size and wavenumber, and illustrate the method's robustness for inhomogeneities with piecewise-smooth refractive indices and jump discontinuities across interfaces.
Read the full abstract

All authors Thomas G. Anderson, Juan Burbano-Gallegos, Luiz M. Faria, Carlos Pérez-Arancibia

Multiagent Systems

Adaptive Incentive Design in Dynamic Principal-Agent Problem via Kernelized Bandits

We consider the dynamic principal-agent problem under asymmetric information, wherein a principal sequentially designs contracts to incentivize an agent with unknown preferences and hidden actions. A fundamental bottleneck in the existing literature is the assumption of deterministic agent utility, which renders the principal's expected utility discontinuous and forces computationally intractable discretizations of the contract space. In this paper, we address this limitation by introducing a stochastic counterpart into the agent's utility model, capturing the inherent physical and behavioral variations in realistic subsystems. We formally prove that this stochastic formulation restores the continuity of the principal's expected utility. Leveraging this continuous geometric structure, we formulate the interaction as a structured multi-armed bandit problem subject to heteroscedastic noise. We propose a Heteroscedastic GP-UCB algorithm that utilizes a Neural Network (Arcsin) kernel, chosen to capture the non-stationary, sigmoidal geometry of the utility landscape. For an $m$-dimensional compact contract space, we establish a high-probability cumulative regret bound of $O\left(\sqrt{T}(\log T)^{m+1}\right)$. Finally, we demonstrate the practical efficacy of our theoretical framework by formulating the Vehicle-to-Grid (V2G) incentive design problem, proving its equivalence to a dynamic principal-agent problem, and showing superior economic performance for grid aggregators.
Read the full abstract

All authors Arghya Mallick, Anuj S. Vora, Sergio Grammatico, Peyman Mohajerin Esfahani

Information Retrieval

Once Generated, Ranked: End-to-End Generative Slate Recommendation with Unified Semantic-Collaborative IDs

Slate recommendation treats a slate rather than an individual item as the recommendation unit, requiring joint optimization of item interactions and slate utility. Existing approaches typically separate candidate generation from ranking and restrict optimization to retrieved candidates. Generative recommendation with Semantic IDs (SIDs) offers a path to end-to-end recommendation, but existing SID construction often lacks recommendation-aware semantics and effective local collaborative signals, while next-token prediction is misaligned with slate-level objectives. We propose OGR, an end-to-end framework that directly generates ordered slates-"Once Generated, Ranked." OGR first introduces TUSID, which adaptively fuses item-specific semantic and local collaborative information into hierarchical SIDs. It then uses list-wise preference planning and pipelined position-wise SID decoding to model global preferences and inter-item dependencies while generating ordered slates. We further propose SPA, a reward-guided conservative policy optimization method that aligns generated slates with user preferences beyond likelihood imitation. Offline experiments show that OGR outperforms representative baselines, with 48.2% and 27.2% relative NDCG@5 gains on industrial and public datasets, respectively. Online A/B testing on Kuaishou further yields a 1.120% improvement in Effective Views.
Read the full abstract

All authors Yang Hu, Jiayi Guo, Jingui Ma, Ning Li, Jiangling Qin, Yanming Li, Yang Deng, Xiaoshuang Chen, Kaiqiao Zhan

Cryptography and Security · Cross-listed from quant-ph

Towards the Impossibility of Imperfectly Complete Key Agreement in the QROM

We make progress towards the impossibility of quantum-computation, classical-communication (QCCC) key agreement by giving the first unconditional polynomial-query attacks that tolerate imperfect completeness in the following settings. First, we give a quantum attack on protocols with arbitrarily many rounds in which both parties' oracle queries and communication are classical before the final round, while local computation may be quantum throughout, and the final round may involve quantum oracle queries and one quantum message. Second, we give a classical attack on constant-round QCCC protocols in which Alice has classical oracle access and Bob may make quantum queries throughout. In both settings, the attacker is computationally unbounded and makes $poly(\lambda)$ queries to recover the key with nonnegligible probability whenever each party's total honest query bound is at most $poly(\lambda)$ and the valid agreement probability is inverse-polynomial. As consequences, we rule out query-bounded IND-CPA security for quantum public-key encryption with classical public and secret keys and classical messages of polynomially bounded length in the QROM in either of two settings: (i) key generation has classical oracle access, while encryption, decryption, and the ciphertext may be quantum; or (ii) encryption has classical oracle access and ciphertexts are classical, while key generation and decryption may have quantum oracle access. Both results assume negligible correctness error and polynomial honest query complexity. Combining the constant-round attack with the constructions of Bartusek and Khurana (CRYPTO 2025), we also rule out constant-round oblivious state preparation with polynomial honest query complexity and negligible correctness error in the QROM against computationally unbounded quantum receivers making polynomially many oracle queries.
Read the full abstract

All authors Fuyuki Kitagawa, Ryo Nishimaki, Agi Villanyi, Takashi Yamakawa

Computer Vision

PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts

Whole-slide pathology reasoning requires models to integrate gigapixel-scale visual evidence across complete case-linked slides, yet current question-answering benchmarks primarily measure final answer accuracy–a metric vulnerable to linguistic priors and benchmark regularities, and insufficient to establish that predictions are grounded in the supplied tissue. We introduce PathoArgus-Bench, a benchmark and evaluation protocol that explicitly tests the full evidence chain: availability, accessibility, use, and responsiveness. PathoArgus-Bench comprises 22,078 four-choice questions from 4,913 patients across 15 TCGA projects, covering six pathology capabilities across three levels of evidence demand, and operates under a fixed reader budget that retains only a small fraction of the gigapixel context. To further isolate evidence-grounded reasoning, we contribute ESG (Evidence State Quartets), a controlled set of 483 quartets where the question text is fixed while the target WSI set is moved, replaced, or removed, requiring consistent predictions across all states. Evaluating 20 general-purpose, medical, and pathology-specific systems reveals a stark gap: while GPT-5.6 achieves 57.09% overall accuracy and 57.04% on ESG, it correctly completes only 19 of 483 quartets (3.93% QExact), exposing that row-level accuracy does not translate into reliable evidence grounding. We also introduce PathoArgus, a fixed-budget reader that allocates context via question relevance and spatial coverage, attaining 50.39% overall accuracy yet only 1.86% QExact–demonstrating that improved context access alone does not ensure consistent evidence-based prediction. Our benchmark and diagnostics establish that acquiring useful whole-slide context is necessary but far from sufficient, and call for a shift from answer-centric to evidence-grounded evaluation in computational pathology.
Read the full abstract

Computation and Language

Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges

Conversational AI is moving beyond isolated text prompts toward sustained, multimodal interaction. In real conversations, users clarify goals, revise requests, interrupt responses, switch topics, and introduce new evidence while expecting systems to preserve context across turns. This makes multi-turn dialogue a distinct challenge requiring systems to maintain and update memory, ground responses across modalities, tools, and external knowledge, and adapt across languages and cultures. This study reviews multi-turn conversational AI across text-only dialogue, AudioLLMs and speech-native systems, multimodal and omni-modal systems, and tool-augmented agents. We organize the literature around datasets and benchmarks, modeling paradigms, training strategies, evaluation setups, and cross-cutting challenges. Our analysis shows that support for multiple modalities has advanced faster than the ability to sustain coherent interaction across a session. Despite stronger capabilities to perceive, speak, and act across modalities, current systems still struggle with persistent memory, cross-turn grounding, full-duplex interaction, robust evaluation, and cultural alignment. We conclude with a research agenda for systems that can remember, revise, ground, speak, listen, act, and adapt across turns, modalities, and cultures. (https://github.com/faiza-sfa/multiturn-conversational-ai-survey)
Read the full abstract

All authors Syeda Faiza Ahmed Sara, Zien Sheikh Ali, Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

Robotics

Physics-Informed Sliding-Window Particle Filtering for Tactile-Only In-Hand 6-DoF Object Pose Refinement

This paper studies tactile-only 6-DoF pose refinement and belief maintenance for grasped objects in static and short quasi-static in-hand configurations where vision is unavailable or heavily occluded. The key difficulty is tactile partial observability: whole-hand taxel contacts are sparse, intermittent, and ambiguous under limited excitation and object symmetries. We propose a physics-informed particle filter on $\mathrm{SE}(3)$ that updates pose beliefs from dense whole-hand tactile measurements. The likelihood combines active-contact signed-distance consistency, force-normal alignment, friction-cone feasibility, zero-force negative evidence, and optional feasibility guards. A sliding-window log-likelihood fuses recent tactile frames to reduce single-frame ambiguity, while a potential-field-guided proposal steers particles away from hand–object penetration. Symmetry-aware resampling preserves multiple plausible modes. Experiments on an Allegro Hand V5 with five objects show lower normalized ADD-S than tactile-only geometric, particle-filter, and learning baselines, and ablations confirm the benefits of temporal fusion, potential guidance, and mode preservation.
Read the full abstract

All authors Lingjun Shao, Ying Zhang, Xiangfei Li, Xiangyang Li, Huan Zhao, Zhenyu Wang, Han Ding

Robotics

LIBERO-VIFO: Benchmarking the Capability and Safety of Visual Cue Following in Vision-Language-Action Models

Visual cues are increasingly adopted to guide robot learning, but whether Vision-Language-Action (VLA) models can reliably follow authorized cues while disregarding unauthorized ones remains unclear. Existing work covers only a narrow range of cue forms and focuses on final task success, providing only a coarse assessment of cue-following capability. Treating all visual cues as authorized also leaves safety risks of unauthorized following unexplored. To address these gaps, we introduce LIBERO-VIFO, a benchmark to evaluate both the capability and safety of visual cue following in VLA models. LIBERO-VIFO defines eight visual cue families spanning diverse forms. A total of four protocols in two parts are defined: Part I tests cue understanding and authorized following, while Part II evaluates unauthorized visual cue following under language-cue conflict and empty language conditions. Evaluating seven VLA models reveals that although visual cue understanding does not reliably translate into execution, current VLAs are able to execute cue-indicated tasks without language instruction, exposing an emerging risk of unauthorized visual cue following. Extended experiments on scene-instantiated cues, safety-critical settings, and real-robot deployment corroborate these findings. LIBERO-VIFO brings both the capability and safety of visual cue following into systematic evaluation, establishing visual-centric safety as a new perspective for the VLA community.
Read the full abstract

All authors Zhengyan Qian, Rui Yan, Alex Jinpeng Wang, Jinhui Tang