Computation and Language
Visual Abstention in Unified Multimodal Models
Chufan Shi, Cheng Yang, Tiannuo Yang et al. (+4 more)
Unified
multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand about the task. We formalize visual abstention: when a requested visual transformation is impossible under the task's rules, the model should recognize that no valid solution exists, state this, and decline to generate. We introduce Draw-or-Decline (DoD), a
benchmark of 1,050 feasible-infeasible request pairs across 7 task categories that jointly measures editing success and the refusal of infeasible requests. Evaluating 8 UMMs, we find that editing ability and abstention are distinct capabilities: even the strongest editor, at 68.4% editing accuracy, refuses only 0.4% of infeasible requests under ordinary instructions. Their
reasoning shows why: the models rarely notice the conflict, and instead plan the edit as if the request were possible, often describing objects that are not in the image, or quietly change the request into one they can complete. Explicitly prompting these UMMs to report infeasibility increases textual refusals but reduces editing accuracy. We propose VisTA (Visual Transformation and Abstention), a training method that pairs feasible and infeasible examples so that a model judges feasibility before deciding whether to generate. We train VisTA-BAGEL to perform feasible edits and decline infeasible requests. Without any reminder, it refuses 93.0% of infeasible requests, up from 0.4% for the strongest editor, while falsely refusing only 0.8% of feasible ones. Unlike a reminder, this does not cost editing accuracy: VisTA-BAGEL completes 74.3% of feasible edits, more than any of the 8 evaluated UMMs.
Read the full abstract ▾
All authors Chufan Shi, Cheng Yang, Tiannuo Yang, Isadora White, Yiwei Chen, Taylor Berg-Kirkpatrick, Xuezhe Ma
Artificial Intelligence
ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning
Miao Xie, Xiao Zhang, Yuan Wang et al. (+2 more)
Dietary nutrition planning plays an important role in chronic disease management and maintaining a healthy body. In applications, it must simultaneously satisfy personalized constraints and reasonable multidimensional nutritional goals. These two aspects often conflict, and user constraints evolve with feedback, resulting in a substantial gap between generic guidelines and executable plans. To bridge this gap, we first propose the personalized fully quantified multiobjective dietary planning problem (MDP). To tackle MDP, we develop a nutrition
agent, ShanLiangRen. The system first transforms dietary specifications, nutrient data, user attributes and natural
language requirements into an individualized constrained planning instance. It then employs an exact
retrieval-augmented generation method to shrink the feasible candidate set from a large scale ingredient and recipe space. Finally, it adopts a refinement guided by Pareto principles, where an LLM iteratively revises candidate plans under deterministic nutrition computation and feedback from constraint verification. The system outputs fully quantified meal plans with explicit ingredients and portion sizes, together with reports on nutrition compliance that show constraint satisfaction and nutrient interval attainment. We have released the system online as a WeChat Program, ShanLiangRen. A demo
video is available at https://www.youtube.com/watch?v=652OtY5VlGA.
Read the full abstract ▾
All authors Miao Xie, Xiao Zhang, Yuan Wang, Ruixin Zhu, Chunli Lv
Machine Learning
Label-Efficient Deep Learning for ECG Delineation: A Multi-Dataset Benchmark against Widely Used Delineation Tools
Jeonghwa Lim, Minje Park, Yeongyeon Na et al. (+6 more)
Electrocardiogram (ECG) delineation, the identification of waveform boundaries, is a foundational step that translates raw ECG signals into clinically interpretable measurements. Deep learning has advanced this task but remains dependent on costly expert annotations. Label-efficient strategies such as self-supervised pretraining and semi-supervised learning are expected to ease this burden, yet it remains unclear whether they yield reliable delineation and whether the deep models they produce outperform the delineation tools used in practice. We address this in two stages. First, comparing self-supervised objectives with supervised or semi-supervised fine-tuning across one internal and four external
datasets, we find that pretraining helps but the objective matters, and that the value of semi-supervised fine-tuning depends on the pretraining objective. Second, we
benchmark the selected deep learning model against widely used open-source (NeuroKit2, Prominence, ECGdeli) and commercial (CalECG) tools using three complementary metrics. The model ranks best on every metric and
dataset, outperforming the strongest tool by a clear margin on the rhythm-diverse set (mIoU 71.3 vs. 54.8%; averaged point-wise sensitivity 92.6 vs. 76.4%), and degrades the least from sinus to arrhythmia. A rhythm-stratified and point-wise analysis further characterizes the distinctive behavior of each tool, yielding practical guidance for tool selection. These results provide systematic, multi-
dataset evidence that self-supervised pretraining is effective for ECG delineation and enables a label-efficiently trained deep learning model to outperform widely used delineation tools by leveraging abundant unlabeled data. This supports adopting such models in diverse, real-world clinical settings.
Read the full abstract ▾
All authors Jeonghwa Lim, Minje Park, Yeongyeon Na, Yujin Eom, Soyeon Lim, Young Ho Lee, Yu Jeong Kim, Sunghoon Joo, Ki Hong Lee
Numerical Analysis
Learned Adaptive Multiresolution Diffusion Imaging
Christian Tantardini, Stig Rune Jensen, Roberto Di Remigio Eikås et al. (+1 more)
Adaptive multiresolution methods reduce representation cost by concentrating fine-scale degrees of freedom where needed, but their tree updates are usually governed by fixed local criteria. We introduce Learned Adaptive Multiresolution
Diffusion Imaging (Learned AMDI), which preserves the AMDI fixed-tree propagator and hierarchy constraints while replacing the post-propagation selector with a shared local policy trained by proximal policy optimization. Regression tests reproduce deterministic AMDI trajectories to machine precision when identical trees are used. In the Haar implementation studied here, the deterministic one-step selector accepts no refinements in 54 decisions. Across nine held-out cases, Learned AMDI executes 393 refinements and reduces the mean terminal reference discrepancy from $0.17496$ to $0.13657$, while occupancy rises from $0.13737$ to $0.26660$. Step-resolved diagnostics reveal occasional small adaptation-energy increases; fixed-tree energy stability therefore does not guarantee monotonicity of the learned outer iteration. At comparable occupancy, a validation-tuned observed-detail threshold reaches a discrepancy of $0.13792$ with slightly better RMSE and SSIM, placing both methods on essentially the same accuracy–occupancy tradeoff. A decision-1-only control reaches $0.13742$, indicating that most of the improvement on this static
benchmark arises from the initial allocation. The shared actor transfers without retraining to $64\times64$ and $128\times128$ images, improving reference discrepancy, RMSE, and SSIM relative to deterministic AMDI, while the frozen threshold rule remains competitive. Learned AMDI thus provides a hierarchy-constrained, resolution-transferable mechanism for adaptive allocation and clarifies the contribution of sequential decisions.
Read the full abstract ▾
All authors Christian Tantardini, Stig Rune Jensen, Roberto Di Remigio Eikås, Joakim Henrik Beck
Computer Vision
Revar3r: gauge-aware perturbation uncertainty for feed-forward 3d reconstruction
Sammam Mahdi, Fariha Binta Salim, Rakin Bin Rabbani et al. (+1 more)
A correctly reconstructed distant point appears uncertain even when a frozen 3D model processes equivalent inputs because its output frame rotates fractionally. This exposes a weakness of trainingfree perturbation uncertainty: when outputs contain an unobserved
symmetry, run-to-run variation potentially reflects
symmetry rather than error. Existing alternatives have trade-offs: built-in confidence is outperformed in most evaluated conditions, while trained evidential heads require modelspecific supervision. For point maps, this research derives a closed-form, error-independent variance term that grows with scene extent and potentially overwhelms the desired signal. Simulation reproduces the effect; all 30 real VGGT view-sets tested exhibit its predicted $\|x_p\|^2$ signature. ReVar3R robustly registers predictions to a common similarity frame before computing per-point variance, without retraining or modifying the frozen model. Optional calibration and fusion use a held-out split. Across VGGT, {\pi}3, and MASt3R on six
datasets, the same
estimator on every backbone lowers AUSE below built-in confidence in 15 of 18 conditions. The staged evaluation yields 11 of 18 wins for the label-free core, 12/18 for label-free equal-weight fusion, 14/18 with held-out weights, and 15/18 when the built-in signal is included. Against a trained evidential head, the result is a trade-off: the head calibrates magnitude better and leads in its training domain, whereas ReVar3R transfers across backbones without adaptation. Its ranking improves point filtering, but it does not detect stable systematic bias, aid novel-view synthesis, or transfer calibration across domains.
Read the full abstract ▾
All authors Sammam Mahdi, Fariha Binta Salim, Rakin Bin Rabbani, Aniqua Nusrat Zereen
Robotics
CUSP: CUSUM-Governed Survival Hazard Alarms at the Perception Onset for Off-Road Navigation
Inuk Kang and Seung-Woo Seo
Off-road
navigation exposes a
robot to potentially hazardous terrain en route. Although learning-based
navigation uses safety supervision to choose which path to drive, it provides no runtime alarm when the
robot following that path is heading into danger. Such an alarm must be learned from field logs, where human intervention preempts the failure and the failure itself is therefore never observed. The human judges driving unsafe early but typically intervenes only once failure is clearly near, so the intervention marks that judgment late. That earlier judgment is what a runtime alarm must detect, yet no prior intervention-supervised method has targeted it. To address this problem, we introduce CUSP (CUSUM-governed Survival model of the Perception onset), a model-agnostic runtime hazard alarm that learns this moment from intervention-terminated logs. "Cusp" is a word for the point at which one state is about to turn into another, and the moment we target is exactly such a cusp: the point at which safe driving turns unsafe in a human's judgment. We call this point the perception onset and annotate it separately from the intervention. A visual hazard head is trained on the annotated onset with a discrete-time survival objective so that driving with and without an onset both supervise the head, and a CUSUM accumulates the predicted onset risk into alarms. We evaluate CUSP at five unseen sites, two autonomous and three teleoperated, with 142 events and every method tuned to the same rate of ten false alarms per hour. CUSP detected 85 events compared to 26 for the best of nine adapted baselines, and the margin comes from hazards to which every signal in the
navigation model is blind.
Read the full abstract ▾
Artificial Intelligence
Self-Referenced Social Preferences: Cooperation without Observing Others Rewards
Mohamed Ayman Mohamed, Harshil Kotamreddy and Marcos Menon Jose
Social preferences can promote cooperation in multi-
agent reinforcement learning, but existing approaches often require
agents to observe the rewards of their peers. In many real-world interactions, however, an
agent can, as humans do, observe others' behavior and outcomes without access to their private reward signals. We introduce self-referenced social preferences, in which each
agent learns a model of its own reward, applies it to other
agents' observed transitions to assess their outcomes from its own perspective, and feeds these self-referenced assessments into standard social preferences. We study two ways to incorporate these assessments: modifying the learning reward, or using them to weight policy updates. We evaluate the approach on three sequential social dilemmas, Escape Room, Clean Up, and Commons Harvest, which require volunteering, public-good contribution, and resource restraint, respectively. Across all three environments,
agents learn cooperative behavior without observing others' rewards, including in settings where independent learners fail to cooperate, and frequently achieve more equitable divisions of jointly produced returns than
agents with access to true rewards. The effective integration point depends on the social preference: inequity aversion works best in the reward together with a value look-ahead, whereas a purely benevolent preference benefits from policy-update weighting. Under partial observability, the policy-update approach continues to support cooperation. These results show that explicit access to other
agents' reward signals is not necessary for learning cooperative behavior: social preferences can instead be grounded in self-referenced assessments of others' outcomes derived from their observed behavior.
Read the full abstract ▾
Cosmology and Nongalactic Astrophysics
Stochastic Bubble Completion in de Sitter Space: Power Spectrum, Bispectrum, and Infrared Moment Hierarchies
Hyukjung Kim, Alp Kagan Ozmen and Heeseung Zoe
Stochastic bubble nucleation makes the local completion time of a first-order phase transition a random spatial field. We study its power spectrum and equilateral bispectrum in Minkowski and de Sitter backgrounds, with particular emphasis on the infrared consequences of a finite transition duration. In an eternally extended de Sitter history, rare bubbles nucleated in the remote past generate an ancient-bubble tail that produces a hierarchy of infrared-sensitive spatial moments. For the two-point function, the first finite-$k$ correction becomes tail sensitive at $H/\beta=1/5$, while the leading moment becomes singular at $H/\beta=1/3$. The corresponding three-point thresholds are $H/\beta=1/8$ and $1/6$, showing that the bispectrum is more infrared sensitive than the power spectrum. For any finite starting time, however, the ancient-bubble tail is cut off, all spatial moments remain finite, and the strict infrared spectra recover the analytic white-noise limits ${\cal P}_\tau\propto k^3$ and ${\cal B}^{\rm eq}_\tau\propto k^6$. The eternal-background thresholds instead control the duration dependence of the moment coefficients and the crossover into an intermediate tail-sensitive regime, in agreement with our numerical calculations. We further show that temporal localization of the nucleation history provides a smooth regulator of the ancient-bubble tail and restores the same analytic infrared limits. These results establish a general first-arrival framework for completion-time fluctuations and clarify how de Sitter expansion can generate distinct power-spectrum and bispectrum infrared hierarchies relevant to
curvature perturbations and non-Gaussianity.
Read the full abstract ▾
General Relativity and Quantum Cosmology
Scale-Invariant Non-Collapse from Raychaudhuri Comparison
Rohit Dhormare
We establish a scale-invariant spatial non-collapse estimate for hypersurface-orthogonal timelike geodesic congruences. The result extends a previous Raychaudhuri-based construction in which a comparison estimate for the expansion was used to control the volume of domains transported along the congruence. The additional ingredient here is a quantitative estimate of the spatial distance distortion induced by the expansion and shear. Assuming that the initial spatial geometry is non-collapsed up to a scale $r_0$, and that the expansion, shear, and timelike
Ricci curvature satisfy suitable uniform bounds, we obtain, before the first blow-up time of the Raychaudhuri comparison solution, \begin{equation*} \operatorname{Vol}_{h_\tau}\bigl(B_{h_\tau}(p_\tau,r)\bigr) \geq \kappa_{\mathrm{L}}(\tau)\, r^3, \end{equation*} where \begin{equation*} \kappa_{\mathrm{L}}(\tau) = \kappa_0 e^{-3K\tau} \exp\!\left(\int_0^\tau \Theta(s)\,ds\right), \qquad K = \frac{\Theta_0}{3} + \Sigma_0 . \end{equation*} Here $\Theta$ denotes the solution of the scalar Raychaudhuri comparison equation and $K$ controls the spatial metric distortion. For every finite time strictly before the comparison barrier, $\kappa_{\mathrm{L}}(\tau)$ is positive. When the comparison solution has a finite blow-up time, the explicit comparison coefficient approaches zero as that time is approached from below. The comparison barrier is a boundary of the estimate and is not, by itself, a statement that the physical congruence develops a focal point or spacetime singularity. The result is structurally analogous to scale-invariant non-collapse estimates in
geometric flow, but is mathematically distinct from Perelman's $\kappa$-noncollapsing
theorem for
Ricci flow.
Read the full abstract ▾
Mesoscale and Nanoscale Physics
Negative charging energy in LaAlO$_3$/SrTiO$_3$ quantum dots induced by SrTiO$_3$ polarization
J. Czarnecki, A. Sierant, B. Szafran et al. (+11 more)
We propose a microscopic mechanism for the negative charging energy in LaAlO$_3$/SrTiO$_3$
quantum dots, arising from the electrostatic image charge associated with the paraelectric response of SrTiO$_3$. Using a self-consistent configuration-interaction approach that accounts for both Coulomb repulsion and image-charge interactions, we find a robust regime of electron pairing whose strength is tunable through the confinement potential and the effective image-charge distance, set by the thickness of the interfacial two-dimensional electron gas. Our results establish dielectric image-charge effects as a route to controllable electron pairing in
oxide quantum dots and other materials with a strong dielectric response.
Read the full abstract ▾
All authors J. Czarnecki, A. Sierant, B. Szafran, P. Szumniak, T. S. Jespersen, G. Meucci, T. Jansen, R. Citro, A. Maiellaro, N. Bergeal, M. Bibes, M. Salluzzo, A. Kalaboukhov, P. Wójcik
Statistical Methodology
State-space representation of early-life child mortality dynamics: linking event history analysis and orbit-based models
Wendy Lefotlha, David Sherwell and Maria Vivien Visaya
Understanding early-life child mortality requires methods that capture both statistically significant risk factors and the structure of individual life trajectories. Event History Analysis (EHA) estimates associations between
covariates and mortality risk but may obscure rare or high-dimensional configurations of risk. Orbit Theory (OT) represents individuals as exact trajectories in a combinatorial state space, preserving full multivariate structure. We analyse longitudinal data across 12 variables for 31,081 children from the Agincourt Health and Demographic Surveillance System (South Africa, 1998-2008) using both methods. We show three things EHA alone cannot. First, maternal migration is structurally pivotal in the transition dynamics leading to child death despite being statistically non-significant in EHA. Second, maternal refugee status, while statistically significant, generates no trajectory dynamics and is correctly excluded from any structural reduction. Third, a three-variable subsystem (child status, mother status, mother migration) recovers EHA's principal findings within a reduced state space of at most 48 states while exposing small high-risk clusters invisible to regression-based analysis. Maternal death is the dominant EHA predictor; maternal migration organises 87% of the observable sequential transitions into child-death states. These are not contradictory: maternal death rarely appears as a preceding state because its role is terminal rather than sequential. Early-life mortality can be read at two levels simultaneously - statistically, through effect estimates, and structurally, through observed transitions.
Read the full abstract ▾
Probability
A very short proof of the subgaussian convex-order comparison theorem
Antoine Song and Michel Talagrand
We provide a very short proof of the following comparison
theorem, which has recently played an important role: every centered subgaussian random vector is dominated in convex order, up to a universal constant, by a standard Gaussian random vector.
Cryptography and Security
Don't Let One Lie Survive A Hundred Truths: A Selective Bayesian Trust Estimator for Collaborative Perception
Yutong Liu, Chenyi Wang, Ming F. Li et al. (+1 more)
Collaborative perception (CP) enables connected vehicles to see beyond their own sensors but makes them dependent on messages they cannot independently verify. A compromised collaborator can surgically conceal a single safety-critical object or inject a non-existing one while correctly reporting many others. Existing
Bayesian trust mechanisms pool agreement across objects, which, while effective against blatant untargeted attacks, either incurs high false-positive rates (FPR), or allows unrelated correct reports to dilute persistent attack evidence for stealthy single-object attackers. To address this problem, we propose SABER, a selective two-tier
Bayesian trust
estimator. The first tier maintains broad
agent and object trust, preserving the ability to downweight benign but low-quality contributors. Cumulative-sum screening selects
agent–object pairs with persistent omissions or unsupported reports for focused
Bayesian assessment. The second tier checks these pairs against other
agents' evidence and maintains a separate, reference-weighted Beta state for each. The lowest pair score constrains
agent trust, preventing unrelated reports from diluting a targeted attack. We establish sufficient conditions for stronger attacker-side trust reductions with bounded additional benign false alarms at fixed thresholds. Compared with state-of-the-art CP defenses, SABER improves attack detection while reducing benign FPRs. On OPV2V, SABER improves defense ROC-AUC over MATE by up to 0.427 in late fusion and 0.337 in intermediate fusion. Against advanced intermediate-fusion data fabrication attacks, it increases detection rates over ROBOSAC and LUCIA by up to 96.40 and 67.07 percentage points, respectively, while reducing FPRs.
Read the full abstract ▾
All authors Yutong Liu, Chenyi Wang, Ming F. Li, Qingzhao Zhang
Machine Learning
On-Policy Distillation with Negative-Policy Rollouts
Jaehui Hwang, Dongyoon Han, Sangdoo Yun et al. (+1 more)
On-policy
distillation (OPD) has been widely studied as a post-training method in which a student model obtains
token-level supervision from a stronger teacher on its own rollouts. Recent studies have improved OPD through alternative
distillation reward formulations and teacher configurations, while the objective of
distillation remains centered on mimicking the teacher. However, when a stronger teacher has limited distributional overlap with the student, such positive guidance can provide insufficient learning signals. In this work, we introduce Negative-Policy OPD (NP-OPD), which complements teacher supervision with rollouts from a lower-performing, lower-capability negative policy that serves as a negative reference for the student. Rather than modifying the
distillation reward formulation, NP-OPD introduces the negative policy at the rollout stage, continuously supplying
tokens preferred by the negative policy over the teacher so that they remain exposed to teacher supervision throughout training. This provides an explicit negative signal through negative-policy rollouts while preserving the positive teacher supervision used in OPD. Through extensive experiments, we show that NP-OPD improves OPD across model scales, generation modes,
reasoning domains, and different OPD variants. Furthermore, our analyses show that NP-OPD effectively suppresses
tokens preferred by the negative policy over the teacher and moves the student away from the negative policy. These results support our design of introducing negative signals through negative-policy rollouts and provide new insight into the role of the rollout policy in OPD. Code will be available at https://github.com/naver-ai/np-opd.
Read the full abstract ▾
All authors Jaehui Hwang, Dongyoon Han, Sangdoo Yun, Byeongho Heo
Cryptography and Security
Preparing an AI-Augmented SIEM for the EU Cyber Resilience Act: A Practitioner Case Study
Georgios Koutidis, Nikolaos Kekatos, Marina Korgiala-Karyda et al. (+2 more)
The EU Cyber Resilience Act (CRA), Regulation (EU) 2024/2847, makes product cybersecurity a lifecycle obligation for products with digital elements on the EU
market: risk assessment, vulnerability handling, conformity documentation, and Article 14 incident- and vulnerability-reporting readiness must be operational before
market placement. Small and medium-sized enterprises that build security products are doubly exposed, since their products are in scope while their customers expect them to be exemplary. This case study documents a CRA preparedness pilot for one such product, SEUXDR, an AI-augmented security monitoring product with a large-
language-model active-response component, on the open-source CYBERFORT platform. We contribute a reproducible six-step recipe (Scope and Classify, Asset Registration, Produce Evidence, Map to CRA, Gap and Actions, Audit Pack), two end-to-end traceability threads, and a pilot snapshot tracing product risks through baseline and AI-specific controls and policies to CRA objectives. It offers practitioners a replicable starting point for translating CRA legal text into operational preparedness for incident response, vulnerability reporting, and conformity assessment.
Read the full abstract ▾
All authors Georgios Koutidis, Nikolaos Kekatos, Marina Korgiala-Karyda, Alexios Lekidis, Tom Nianios
Computers and Society
Online Sign Language Interpretation System
Christophe Ponsard and Jean-François Molderez
The Walloon Region commissioned this study to improve deaf people's access to public services for the new millennium. It focuses on sign
language users, about 25,000 adults in the French-speaking Community, for whom written French is close to a foreign
language. The core problem is a severe shortage of interpreters: only about twenty work in French-speaking Belgium, so appointments take weeks to arrange and emergencies cannot be covered. The study assessed three options. The recommended one, remote
video interpretation, could be deployed at the time of writing: a professional interpreter joins the deaf person and the employee by videoconference, saving travel time and enabling an emergency service. Similar services already ran in Sweden, Finland, the Netherlands and France. Prototype tests in May 2003 were a clear success and showed that interpretation needs at least CIF
video above 256 kbps, ideally 384 kbps. The system suits simple administrative tasks better than emotional, medical or legal situations. The second option, fully automated interpretation, was not yet feasible, although partial systems using
speech recognition and signing avatars could already serve kiosks, websites and routine procedures. The third option looks further ahead: UMTS and WiFi could eventually support mobile signed
video calls and remote interpretation, provided quality of service is guaranteed. The main recommendation is a first pilot in real conditions before any wide rollout, supported by high-bandwidth links as part of e-government modernisation. The system is meant to relieve interpreters, not replace them, so their training, status and numbers should improve. The authors also call for digital training for deaf people, awareness among public-service staff, more sign
language content online, and a multidisciplinary avatar project with Belgian, French and European partners.
Read the full abstract ▾
Information Theory
LEO Signals-of-Opportunity for Navigation in Urban Environments: A GLRT-Assisted Off-Grid SBL Approach
Maedeh Sotoodenia, Mohammad Hossein Kahaei and Alireza Nezamalhosseini
The vulnerability and unavailability of global
navigation satellite system (GNSS) signals in dense urban environments have motivated the use of low earth orbit (LEO) signals of opportunity (SoOP) for positioning,
navigation, and timing (PNT). However, multipath and non-ideal noise can significantly degrade delay–Doppler estimation and, consequently,
navigation accuracy. This paper proposes a hybrid generalized likelihood ratio test (GLRT) and off-grid sparse
Bayesian learning (SBL) framework for LEO-SoOP
navigation under multipath and non-Gaussian, temporally correlated noise. First, a GLRT-based framework is developed, demonstrating reliable detection under ideal Gaussian noise but degraded estimation under heavy-tailed or colored noise and unresolved multipath. Next, an off-grid SBL framework is introduced for high-resolution separation and estimation of line-of-sight (LOS) delay–Doppler parameters. The estimated LOS parameters are subsequently tracked and incorporated into an extended Kalman filter (EKF) to obtain the
navigation solution. Simulation results demonstrate that, in urban environments, the proposed method reduces delay RMSE by up to 77% and position RMSE by 88.5% compared with GLRT-based estimation. These results demonstrate the potential of the proposed framework for robust and accurate LEO-SoOP
navigation.
Read the full abstract ▾
Cryptography and Security
Plug-and-Play Quantum-Resistant BLE Pairing for Medical Implants via NFC Out-of-Band
Muhammad Asim Javaid, Muhammad Shafay Tanveer Hassan, Faaiz Umer et al. (+5 more)
Bluetooth Low Energy (BLE) pairing establishes the cryptographic foundation for secure device communication. However, mainstream man-in-the-middle (MITM)-resistant pairing methods, such as Numeric Comparison and Passkey Entry, require user interfaces that implantable medical devices (IMDs) inherently lack, making Near-Field Communication (NFC)-assisted Out-of-Band (OOB) pairing an attractive alternative. Existing NFC-assisted OOB schemes authenticate a classical BLE key exchange that remains vulnerable to
quantum attacks, while the NFC channel itself is susceptible to eavesdropping and active injection under stronger threat models. To address these limitations, we propose a lightweight, plug-and-play NFC-based OOB pairing protocol that performs a post-
quantum key encapsulation mechanism (KEM) entirely over the NFC channel, ensuring that no shared secret is transmitted over NFC while reducing long-range
radio-frequency (RF) exposure during pairing. The proposed protocol requires no modifications to the BLE stack and inherently resists RF battery-depletion attacks. Evaluation on an IMD-class proof-of-concept testbed demonstrates that post-
quantum OOB pairing is practical on resource-constrained devices, reducing projected battery life by less than 0.57% for Kyber-1024 and 0.56% for FireSABER under an operational usage model relative to the MITM-vulnerable Just Works method.
Read the full abstract ▾
All authors Muhammad Asim Javaid, Muhammad Shafay Tanveer Hassan, Faaiz Umer, Sotirios Panagiotou, Christos Strydis, Naveed Anwar Bhatti, Muhammad Adeel Pasha, Muhammad Ali Siddiqi
Functional Analysis
Higher-order differentiability of Korevaar–Schoen energy forms and energy measures
Ryosuke Shimizu
In this paper, we investigate the differentiability of Korevaar–Schoen $p$-energy forms and the associated $p$-energy measures. We obtain higher-order derivatives by virtue of explicit realizations of Korevaar–Schoen $p$-energy forms and the associated $p$-energy measures as subsequential pointwise limits of certain double integrals.
Read the full abstract ▾
Computer Vision
CueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal Encoders
Sunchan Park, Beomkwon Cho and Kyeongbo Kong
Large
language model
agents have been used to search over symbolic structures such as programs and equations. We propose CueRator, an agentic framework for policy-aware decision-rule discovery, which adapts frozen contrastive
multimodal encoders by searching for the decision rule that converts their cross-modal similarities into predictions. We validate it on open-vocabulary audio-visual event perception, where existing methods involve a trade-off between adaptivity and generalization to unseen categories: trained modules adapt at the cost of generalization, and fixed rules the reverse. The framework pairs a symbolic formulation for generalization with a lightweight policy that predicts its parameters per
video for adaptivity. A report-guided multi-
agent loop discovers the formulation offline, evaluating each candidate on its expressive ceiling and on whether a trained policy can realize it. On OV-AVEBench, CueRator raises the total average from 57.8 to 60.2 and unseen-category performance from 55.8 to 59.9 over the best existing method, reducing the seen-unseen gap from 7.1 to 1.2. Ablations attribute the gains to both the formulation and the policy and show that both feedback signals are necessary for effective search. CueRator also improves over the respective baselines on two further audio-visual event perception tasks, and the discovered rule remains competitive across encoders with only the policy retrained. Code is available at https://github.com/cvsp-lab/cuerator.
Read the full abstract ▾
Quantum Algebra
quantum-group: Exact symbolic verification of R-matrix and Yang–Baxter identities for $U_q(\mathfrak{sl}_2)$ and $GL_q(2|1)$
Taha Berk Terekli
Explicit R-
matrices of
quantum groups are routinely transcribed from the literature, yet whether they satisfy an identity depends on basis order, tensor placement, the coproduct and, for superalgebras, the Koszul sign rule.
quantum-group is a Python package that builds such
matrices exactly with SymPy and returns every identity as an exact residual
matrix, whose nonzero entries locate the convention that disagrees. It covers U_q(sl_2) modules, tensor products and the fundamental R-
matrix, and the graded Yang–Baxter equation for GL_q(2|1). Applied to the thesis it was written for, it exposed an R-
matrix that satisfies the Yang–Baxter equation but intertwines the opposite coproduct.
Read the full abstract ▾
Cryptography and Security
The Amplifier Effect: Human-Factor Risks of AI-Suggested Correlation and Auto-Propagation in Multi-Framework GRC Self-Assessment
Nikolaos Kekatos, Michael Ioannou, Marina Korgiala-Karyda et al. (+2 more)
Multi-framework Governance, Risk and Compliance (GRC) platforms increasingly automate the link between an organisation's self-assessment answer and the compliance obligations that answer is said to satisfy. Cross-framework control mapping, AI-suggested question correlation, and automatic propagation of answers and evidence across correlated questions all serve the legitimate efficiency goal of reducing duplicate work for small and medium-sized enterprises under the EU Cyber Resilience Act, NIS2 and GDPR. The same mechanisms, however, amplify the consequences of any human-factor bias in a single answer: one optimistically-graded control, one rubber-stamped attestation, or one AI-drafted answer can be silently replicated as evidence of compliance with many obligations across multiple frameworks. We call this the amplifier effect: a platform-design property (coarse-grained attestation and un-gated propagation) rather than a failing of individual users. Using two EU-funded SME-facing GRC platforms, CYBERFORT and CYBER-BRIDGE, as examples, we (i) describe the amplification mechanism in concrete data-model terms, (ii) propose a six-dimension scoring framework for evaluating any GRC tool's exposure to the effect, (iii) instantiate the framework on a thirteen-tool comparison covering enterprise IRM, mid-
market platforms, compliance-automation tools, and the two EU SME projects, and (iv) outline a measurement protocol that a consortium with access to production self-assessment data can run. The thirteen-tool comparison is a structured design assessment, not an empirical measurement of user behaviour. The EU SME platforms score lowest on the amplifier dimensions because their burden-reduction design deliberately trades sign-off granularity for throughput; we report this as a design trade-off, not a verdict on the platforms. Our contribution is the framing and the measurement protocol.
Read the full abstract ▾
All authors Nikolaos Kekatos, Michael Ioannou, Marina Korgiala-Karyda, Alexios Lekidis, Tom Nianios
Atomic Physics
Kaonic Atom X-ray Spectroscopy: From SIDDHARTA-2 to the EXKALIBUR Program
F. Sgaramella, L. Abbene, F. Artibani et al. (+31 more)
X-ray spectroscopy of kaonic atoms offers a unique experimental window on the interplay between low-energy strong interaction and precision atomic physics studies. This article reviews the scientific progress achieved with SIDDHARTA-2 at DAFNE and discusses how it shapes the next generation measurements. Particular emphasis is given to EXKALIBUR, a multifacility program designed to perform measurements of kaon-
nucleus interactions across the periodic table and to extend kaonic atom spectroscopy toward precision tests of bound-state QED and the charged-kaon mass extraction. The first proposed strong interaction campaign at J-PARC aims to investigate kaonic atoms with solid Li, Be, and B targets using new 1-mm-thick Silicon Drift Detectors and high-resolution TES microcalorimeters, exploiting isotope pairs to isolate
nuclear-structure and kaon-multinucleon effects. Measurements of Mg, Al, Si, and S with CdZnTe detectors will broaden this study toward heavier
nuclei. EXKALIBUR will establish a systematic experimental framework for testing low-energy strong interaction with strangeness and bound-state QED predictions across a broad range of kaonic atoms.
Read the full abstract ▾
All authors F. Sgaramella, L. Abbene, F. Artibani, M. Bazzi, G. Borghi, D. Bosnar, M. Bragadireanu, A. Buttacavoli, A. Clozza, F. Clozza, R. Del Grande, L. De Paolis, K. Dulski, C. Fiorini, I. Friščić, C. Guaraldo, T. Hashimoto, M. A. Iliescu, M. Iwasaki, A. Khreptak, S. Manti, J. Marton, P. Moskal, H. Ohnishi, F. Principato, A. Scordo, M. Silarski, D. Sirghi, F. Sirghi, M. Skurzok, A. Spallone, K. Toho, J. Zmeskal, C. Curceanu
Astrophysics of Galaxies
Complex Organic Molecules in Protostars with ALMA Spectral Surveys (COMPASS): I. Overview of the ALMA Large Program
J. K. Jørgensen, A. Coutens, M. N. Drozdovskaya et al. (+27 more)
It remains a fundamental research question in astrochemistry to characterize the inventory of complex organic molecules formed during the early stages of
star formation, which may affect the eventual chemical composition of protoplanetary disks and potentially
planets. The Atacama Large Millimeter/submillimeter Array (ALMA) provides the angular resolution and sensitivity to zoom in on the hot (T > 100 K) gas surrounding embedded
solar-type protostars and chart their molecular inventories with high accuracy. The ALMA Large Program Complex Organic Molecules in Protostars with ALMA Spectral Surveys (COMPASS) aims to provide comprehensive inventories of the molecular content of a sample of protostellar sources to understand the chemical impact of their environments and evolutionary stages. COMPASS is an unbiased spectral survey of 11 line-rich Class 0 and I protostellar sources in the spectral range from 279.0 to 311.7 GHz at 0.15-0.5" angular resolution with ALMA, corresponding to the inner ~100 au (radius) around the targeted sources. This paper provides an overview of the COMPASS program and the adopted strategy in terms of observational setups and targeted sources. We also present a qualitative comparison of the spatial distributions of selected molecules and the relative strengths of the line fluxes of selected complex organics. The qualitative comparisons suggest that chemical differences between sources may be present, for example, between the abundances of groups of oxygen- and nitrogen-bearing species, but also that such variations occur at levels smaller than an order of magnitude. Quantitative comparisons of abundances at these levels require the large bandwidth of the survey, as well as a careful analysis of the excitation and strengths of the several thousands of lines detected toward each source in the survey, as will be explored in forthcoming papers.
Read the full abstract ▾
All authors J. K. Jørgensen, A. Coutens, M. N. Drozdovskaya, J.-E. Lee, A. L. Plunkett, S. Maret, A. Belloche, D. Harsono, Z. Telkamp, F. Cruz-Sáenz de Miera, M. L. R. van 't Hoff, Á Kóspál, M. Rao, J. Bergner, J.-H. Jeong, S. Spezzano, B. A. McGuire, P. Nazari, Y.-L. Yang, H.-S. Yun, A. Andreu, J. Ferrer Asensio, C.-H. Kim, N. F. W. Ligterink, Y. Lin, S.-Y. Liu, M. Lützen, P. Marchand, C. Xue, S. Zeng
Computation and Language
ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents
Yupeng Su, Jiayi Tian, Zheng Zhang et al. (+1 more)
Long-horizon LLM
agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessions exceed the context window. Existing methods manage the context through context requirement prediction, relying on additional model calls, heuristic rules, or trained policies. However, these predictive approaches introduce runtime overhead, invalidate prefix caches, and permanently discard content with no guarantee of recovery. To overcome these limitations, we introduce ReFold: a training-free rendering layer that preserves the underlying interaction history while compressing only the model's rendered context. It removes two kinds of inter-turn redundancy without an auxiliary predictor: content an earlier turn already displayed, replaced by a stub, and turns the
agent itself reports finished, folded into a one-line note. Both operators use chunked rendering, rewriting the cached prefix once every few steps rather than at every step. Every removal is strictly reversible, a wrong removal costs one restore from the history rather than permanent content loss. Because it operates at the rendering layer, ReFold is plug-and-play across standard ReAct-style harnesses. Evaluations across five long-horizon
benchmarks and two frontier LLMs demonstrate that ReFold reduces
token consumption by up to 2.5x and halves the KV-cache
memory per session without degrading task success rates. Under capped context budgets, it avoids up to 92% of forced compactions. Under concurrent serving workloads, it reduces request queuing delays by up to 100%, accelerating inference by up to 1.7x, while cutting inference costs by up to 3.4x.
Read the full abstract ▾
All authors Yupeng Su, Jiayi Tian, Zheng Zhang, Souvik Kundu
Materials Science
A self-learning scientific agent for X-ray diffraction
Bin Cao, Huichi Zhou, Runyu Yang et al. (+7 more)
A central challenge for scientific
agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning
agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM. Together, these engines span phase identification, multiphase decomposition and physics-constrained whole-pattern modelling. Gan Jiang converts analytical experience into executable skills by diagnosing failures, revising skill instructions and code, and validating revisions before reuse, without retraining the
language model or changing the underlying physical models. Skills selected using development data and frozen before held-out evaluation achieve higher refinement scores than the original expert-designed skills across FullProf, GSAS-II and PyWPEM. The
agent resolves strongly overlapping reflections, quantifies a five-phase ancient Egyptian cosmetic, tracks
lattice evolution in an operating battery and compares atomic configurations in a disordered
oxide catalyst. On DeltaXRDbench, it leads the evaluated methods in single- and multiphase identification across simulated and experimental data. Without supplied composition, single-phase top-1 accuracies reach 96.30%, 81.78% and 40.83% on MP500, RRUFF and opXRD, respectively, compared with 58.00%, 58.47% and 26.45% for the strongest comparator. These results demonstrate how an integrated scientific tool ecosystem can support
agents that extract structural knowledge from measurements while accumulating validated analytical expertise that transfers to new samples.
Read the full abstract ▾
All authors Bin Cao, Huichi Zhou, Runyu Yang, Jingsong Li, Shuchen Sun, Yan Song, Hanyu Gao, Zhongwei Yu, Tong-Yi Zhang, Jun Wang
Astrophysics of Galaxies
COSMOS-3D: Spectro-photometric Confirmation of Shabgard, a Cool, Metal-poor Brown Dwarf in the COSMOS Field
Bahareh S. Salmasi, Priyanka Jalan, Tomotsugu Goto et al. (+19 more)
Brown
dwarfs are unique laboratories for studying cool atmospheres, the low-mass end of
star formation, and the transition between
stars and
giant planets. Identifying and characterizing the coldest brown
dwarfs remains challenging, particularly at faint magnitudes in deep extragalactic surveys. We investigate COSMOS2025 ID639188, hereafter Shabgard, a compact source previously selected as a brown-
dwarf candidate from COSMOS-Web photometry. We use serendipitous JWST/NIRCam F444W wide-field slitless spectroscopy from COSMOS-3D, combined with COSMOS2025 NIRCam photometry and multi-epoch imaging. We extract a local-background-subtracted, profile-weighted $4.05$-$4.85\mu{\rm m}$ spectrum and compare the data with six atmosphere-model families. The LOWZ atmosphere-grid fit, using PCA interpolation and MCMC sampling, gives $T_{\rm eff}=718.6^{+10.6}_{-10.2}$ K and $[{\rm M/H}]=-1.00^{+0.07}_{-0.08}$, favoring a cool, subsolar-
metallicity atmosphere near the late-T/Y transition. A fixed-atmosphere molecular-opacity test strongly favors a contribution from CH$_4$ to the observed $4$-$5 \mu{\rm m}$ spectral shape, although the restricted wavelength coverage prevents a molecule-by-molecule abundance determination. Model-dependent physical estimates span approximately $23$-$52 {\rm M_{\rm Jup}}$ and $140$-$180$ pc. We measure a proper motion of $|\mu|=89.2\pm0.4$ mas yr$^{-1}$, while the LOWZ MCMC flux scaling gives a distance of $176.2^{+18.4}_{-17.8}$pc. Together, these results support the classification of Shabgard as a cool, metal-poor
Galactic brown
dwarf and demonstrate the ability of JWST deep-field surveys to discover and characterize faint substellar objects.
Read the full abstract ▾
All authors Bahareh S. Salmasi, Priyanka Jalan, Tomotsugu Goto, Tetsuya Hashimoto, Feige Wang, Tayyaba Zafar, Koki Kakiichi, Ece Kilerci, Srivardini Ayyappan, Romain A. Meyer, Anilkumar Mailvaganam, Tamal Mukherjee, Xuanyi Lyu, Imam Uzma Aalia, Arihant Raidani, Samuel Carlson, Jose Luis Carrillo Martinez, Andreas L. Faisst, Marko Shuntov, Hollis B. Akins, Zihao Li, the COSMOS-3D Collaboration
Artificial Intelligence
WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration
Qi Cheng, Shengyu Chen, Wei Cheng et al. (+4 more)
Multi-
agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions. We present WorkflowOps, a multi-
agent workflow orchestration framework that learns
agent collaboration priors from historical workflows and expands its
agent pool on demand to cover new capability requirements. Our approach introduces three coupled mechanisms. First, a transition probability
matrix captures pairwise
agent collaboration frequencies from past workflows and applies them as soft guidance during DAG workflow construction through intra-layer ordering optimization, probability-thresholded edge suggestion, and transitive reduction for parallelism maximization. Second, a sufficiency-driven
agent creation loop detects capability gaps via semantic matching scores, generates specialized
agents through an LLM, and simultaneously injects them into the collaboration
matrix, so that newly created
agents are immediately usable with predicted collaboration priors. Third, a layered semantic matching strategy uses pre-trained sentence
embeddings for fast, deterministic capability matching as a first pass, invoking LLM verification only for low-confidence cases, thereby reducing LLM routing calls by over 80% compared to pure-LLM approaches. Experiments on mixed code, math, and question-answering suites show that WorkflowOps improves end-to-end pass rates over recent workflow-construction baselines, with the largest gains on structured, decomposable tasks where past
agent handoff patterns transfer.
Read the full abstract ▾
All authors Qi Cheng, Shengyu Chen, Wei Cheng, Zhengzhang Chen, Xiaowei Jia, Haoyu Wang, Haifeng Chen
Machine Learning
Tram-FL: Reducing Communication and Computation Costs through Sequential Model Circulation in Decentralized Federated Learning
Kota Maejima, Takayuki Nishio, Asato Yamazaki et al. (+1 more)
Conventional decentralized
federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individually, and undertaking model exchange and integration. While fully leveraging computational resources can shorten training times, it can also lead to significant computational and communication waste. This is especially pronounced with non-independent and identically distributed (non-IID) data, where achieving high model accuracy demands extra resources. This research shifts focus to the model itself, aiming to realize DFL with minimal computation and communication costs. To this end, we propose Tram-FL (Traveling Model Training Mechanism for Decentralized
Federated Learning), a mechanism designed to efficiently address these challenges. It sequentially trains a single model by circulating it among nodes. We address the training scheduling problem in model circulation-based training, specifically determining which nodes should update the model and the number of updates to perform. This is approached by considering the model's circulation route and update iteration allocation, for which we propose simple yet effective methods. Additionally, with quantized momentum, Tram-FL achieves high accuracy with fewer model circulations while controlling communication load per transmission. Experimental results show that the proposed
algorithm, even with non-IID data, converges to a global model with reduced communication and computation.
Read the full abstract ▾
All authors Kota Maejima, Takayuki Nishio, Asato Yamazaki, Yuko Hara-Azumi
Game Theory
On the Complexity of Mixed Equilibria in First-Price Auctions with Correlated Priors
Mark Chen, Xi Chen, Hao Cui et al. (+2 more)
We show that computing an approximate mixed Bayes-Nash
equilibrium in a discrete first-price auction with correlated priors is PPAD-complete. The key intermediate step in our reduction is the PPAD-completeness of computing an approximate Nash
equilibrium in a new normal-form game, the hypergraph discrete first-price auction, which may be of independent interest.
Read the full abstract ▾
All authors Mark Chen, Xi Chen, Hao Cui, William Pires, Jonah Stockwell