Emerging Technologies
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Monday 14 September
Near-term quantum and quantum-inspired solvers for portfolio optimization rely on local subproblem execution under severe size constraints, but this locality can omit cross-cluster covariance essential for global risk coordination. We propose Context-Aware Folding (CAF), a lightweight hybrid quantum-classical coordination layer between one-shot static decomposition and full-matrix optimization. CAF injects a compressed global risk state into each local subproblem via a state-dependent linear bias, decouples local candidate generation from global commitment, and retains a sequential acceptance rule with a monotonic non-divergence guarantee. On a 2016 Russell 3000 subset (N=484) with Simulated Annealing (SA), CAF improves the scalarized mean-variance objective by 6.59% over a static baseline (20/20 wins), and by 0.2579% on an additional 2018 panel (N=1397, 17/20 wins). We further report matched folded N=40 compatibility studies with the Quantum Approximate Optimization Algorithm (QAOA) and simulated quantum annealing (SQA) as local solvers, together with a frozen hardware-in-the-loop run on Origin Quantum's Wukong 180 (WK\_C180) for one warm-started QAOA subproblem at n=5. These results support CAF as a coordination architecture with strong classical large-scale evidence, cross-backend compatibility, and local executability on real quantum hardware in the noisy intermediate-scale quantum (NISQ) era.
Artificial Intelligence
New Conditions for Philosophers to Catch the Wave of Citizen Deliberation in the Age of Artificial Intelligence in advance
Powerful technologies labeled “AI”-without sufficient epistemic caution-are already reshaping political and private life, bringing both new dangers and new opportunities for citizen participation. These range from electoral and legislative engagement to the most ambitious form: political co-creation through citizens' assemblies. Large Language Models (LLMs) could support such processes through moderation, translation, facilitation, summarization, and writing assistance. But this potential remains largely unrealized. The Democratic Commons project takes a fundamentally interdisciplinary approach-from philosophy to computer science-to evaluate LLMs against five proposed democratic principles. At its core, the project is driven by the question of political bias: under what conditions can LLMs be used democratically within forms of citizen participation that are them- selves still largely experimental? Addressing these socio-technical questions requires grounding in political theory and, more broadly, in philosophy-disciplines that provide the normative frameworks without which the democratic evaluation of AI systems cannot be mean- ingfully conducted.
Read the full abstract
Artificial Intelligence
Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean benchmarks and offer little guidance to practitioners choosing an approach for a given task complexity. We address this gap with a measurement-grounded study and an open-source release. Across eleven systems (three commercial, two reasoning, five open-source VLMs in pretrained and fine-tuned form, and a non-LLM OCR->regex floor) scored on a 750-document held-out pool of synthetic checks, fine-tuning on 3K samples lifts the best open-source VLMs above F1 0.98-above every zero-shot commercial system on this task-while GPT-5 leads the commercial pool on F1 and Claude Sonnet 4.5 collapses on Date. To turn these measurements into actionable choices, we introduce a practitioner-oriented selection framework that maps a task profile (quality, latency, governance, volume) to a recommended approach via filtering and total-cost minimization, illustrated on a hypothetical mid-volume document-extraction scenario.
Read the full abstract
Quantum Physics
Detectability of Post-Quantum Correlations in Symmetry-Restricted Bell Scenarios
Searches for post-quantum correlations depend on two distinct ingredients: how abundant such correlations are in the underlying correlation space and how efficiently the chosen representation preserves their distinguishability from quantum correlations. We quantify these effects by introducing the popularity rate and the projection acceptance, whose product defines the search performance. We apply these concepts in binary-outcome Bell scenarios with symmetry-related sites, using the CHSH and pyramid representations. Particular attention is paid to the distinction between exchange-symmetric synchronous correlations and correlations satisfying only exchange symmetry. In the synchronous quantum sector, the common-vector representation follows automatically from synchrony, whereas exchange symmetry alone defines a substantially larger correlation space. We show that this distinction can qualitatively change the effectiveness of a projected search: the pyramid representation, which retains substantial discriminatory power in the synchronous sector, has no discriminatory power when only exchange symmetry is imposed. Our results provide a simple framework for assessing and comparing searches for post-quantum correlations.
Read the full abstract
Networking
AI-Native Open RAN: A Roadmap from xApps and rApps to Autonomous Network Agents
Open Radio Access Networks (O-RAN) have emerged as a transformative paradigm for future wireless systems by introducing openness, virtualization, disaggregation, and programmable intelligence through the RAN Intelligent Controller (RIC). The availability of standardized interfaces and near-real-time control loops has created unprecedented opportunities for integrating artificial intelligence (AI) into radio access network management and optimization. Over the past several years, a broad range of AI techniques have been proposed to address key O-RAN challenges such as radio resource management, network slicing, traffic prediction, mobility management, interference mitigation, and spectrum sharing. Despite significant progress, existing solutions often remain task-specific, require extensive retraining, and exhibit limited generalization across deployment environments and network conditions. This paper presents a comprehensive review of AI-enabled O-RAN systems and provides a unifying perspective on the evolution of intelligence in wireless networks. We first examine the O-RAN architecture and the role of intelligence within near-real-time and non-real-time RIC frameworks. We then develop a taxonomy of AI approaches for O-RAN, covering machine learning, deep reinforcement learning (DRL), digital-twin-assisted optimization, and emerging foundation-model-based architectures.
Read the full abstract
Group Theory
The variety generated by all semirings of order three is nonfinitely based
We prove that the variety generated by all semirings of order three is nonfinitely based, where addition is not required to be commutative and the signature has no constants. The same conclusion holds for the variety generated by all additively idempotent semirings of order three. We establish these conclusions by excluding a uniform bound on the number of variables in an identity basis. Our proof uses identities associated with anchored odd cycles. Three small commutative test semirings isolate a polynomial equivalence class consisting of exactly two polynomials. For a cycle of length $n$, every first nontrivial deduction between them requires an identity with at least $n+1$ variables, even under polynomial substitutions. A retraction followed by a band quotient transfers absorption identities to arbitrary addition and identifies the ai-subvariety of the full joint variety with the joint variety of the ai-generators. Validity of the cycle identities follows from a structural analysis of chain and flat addition. An elementary sixth-power lemma for semigroups of order at most three supplies the retraction.
Read the full abstract
Machine Learning
Backward SDEs-based Diffusion for Physics-Constrained Generation
Pretrained score-based diffusion models provide strong unconditional priors, yet enforcing measurement or physics consistency in inverse problems is often handled by heuristic guidance, intermittent projections, or task-specific conditional training, with limited guarantees of feasibility at the end of inference. We propose terminal-conditioned inversion for score-based SDE priors. Given a frozen Score-SDE prior and a task-defined terminal feasibility specification, we construct an associated backward stochastic differential equation whose adapted solution defines a principled inverse map from the terminal requirement to a prior state at a chosen noise level. Under standard regularity conditions, we establish existence and uniqueness of the adapted solution and obtain terminal consistency by construction. We further develop a practical neural BSDE solver that composes arbitrary pretrained diffusion priors with domain constraints without modifying the score-defined coefficients, producing an anchored prior state that enables neighborhood sampling for uncertainty characterization. Experiments on toy datasets validate stable terminal-conditioned inversion and distributionally consistent neighborhood sampling. As a real-world case study, we apply the framework to sparse-view CT reconstruction and achieve improved reconstruction quality over representative training-free baselines while satisfying strict measurement feasibility under the prescribed terminal specification. Project is available in: \href{https://laplacelab.github.io/BSDEDiffusion/}{https://laplace.center/icmlbsdeI/}
Read the full abstract
Statistical Methodology
Extended Joint Models for Longitudinal and Time-to-Event Data: A Tutorial
Shared-parameter joint models for longitudinal and time-to-event data are powerful tools for analyzing repeatedly measured biomarkers, clinical events, and the complex relationships between them. Recent methodological advances have extended the basic framework, which was originally developed for a single event time and a continuous longitudinal biomarker, to more complex scenarios. This tutorial provides a step-by-step guide to fitting extended joint models for longitudinal and time-to-event data using the R package JMbayes2. We cover a range of applications, including models with competing risks, recurrent events, multistate processes, flexible association structures, and multiple longitudinal outcomes following different distributions. Each model is illustrated using simulated data that closely resemble a real-world dataset, with detailed explanations of data organization, model specification, fitting, diagnostics, and interpretation. The tutorial is designed for applied researchers who are interested in analyzing their own data with extended joint models using accessible and reproducible R code.
Read the full abstract
Probability
Uniform-in-time approximation and convergence of invariant measuresfor the damped stochastic Korteweg-de Vries equation
To quantitatively characterize the long-time dynamics of the periodic damped stochastic Korteweg–de Vries (sKdV) equation driven by additive noise, we investigate the uniform-in-time error estimates for a Lie–Trotter operator splitting approximation. This splitting combines the exact deterministic KdV flow with the exact Ornstein–Uhlenbeck solution map for linear damping and additive forcing. Long-time error analysis for the sKdV equation is highly nontrivial because of the interplay among the lack of dissipative smoothing, the loss of one spatial derivative arising from the Burgers-type nonlinearity, and the fluctuations of stochastic forcing. To overcome these difficulties, we develop new strategies based on exponential Lyapunov estimates, the continuous dependence estimate, and the local error decomposition. We establish strong and weak order \(1\) convergence uniformly in time under sufficiently large damping, as well as strong order \(1\) convergence on finite time intervals under a weaker damping condition. Under stronger assumptions, the splitting approximation admits a unique invariant probability measure on \(H_0^2\), which approximates the invariant measure of the exact dynamics with order \(1\). To the best of our knowledge, these constitute the first uniform-in-time strong error and quantitative invariant-measure approximation results for the periodic damped sKdV equation with additive noise. Our results provide an avenue for long-time simulation of the damped sKdV equation.
Read the full abstract
Lattice Field Theory
Renormalized Polyakov loop in accelerated gluodynamics
In this paper we investigate accelerated gluodynamics for a broad intervals of temperature and acceleration. Our study is carried out within lattice simulation in the co-moving reference frame parameterized by the Rindler coordinates. We developed the renormalization prescription that allowed us to calculate renormalized Polyakov loop as a function of coordinate in the Rindler spacetime. Using the data for the renormalized local Polyakov loop, we calculated spatial dependence of the static quark free energy and effective mass of static quark. Besides the Rindler coordinates, it is believed that accelerated gluodynamics can be approximated utilizing non-accelerated gluodynamics with a properly adjusted temperature gradient in accordance with the Tolman-Ehrenfest law. We compared these approaches for the observables under study. It was found that they agree quite well close to the critical temperature and demonstrate disagreement at higher temperatures. We believe that this disagreement might be attributed to the Tolman-Ehrenfest law corrections which appear in the Rindler gluodynamics.
Read the full abstract
Complex Variables
Sharp degree bound for rational proper maps from $\mathbb B^2$ to $\mathbb B^4$
We prove that every rational proper holomorphic map from $\mathbb{B}^2$ to $\mathbb{B}^4$ has degree at most $5$, confirming D'Angelo's conjecture in this case. This sharp bound follows from Meylan's degree estimates and an intersection-theoretic argument ruling out degree $6$.
Quantum Physics
OpenQARP: a modular framework for quantum application research
We introduce OpenQARP, the Open Quantum Application Research Package: an open-source Python framework for quantum application research, built on a compiled C++ core. In OpenQARP, an application is assembled from an algorithm library that orchestrates three interchangeable layers: blocks describe circuits, primitives describe what to extract from them, and engines describe how they run. The release spans near-term through fault-tolerant methods, targeting problems from electronic structure to combinatorial optimization, with device-aware compilation, circuit cutting, and resource estimation over a single set of numerical conventions that the code must follow. Every numerical feature is checked against an independent oracle, and every published timing carries a correctness check. Against OpenFermion, Qiskit/Aer, PennyLane/Lightning, Qulacs, qsim, and pytket, OpenQARP is one to two orders of magnitude faster on operator algebra and among the fastest on simulation. It matches mature compilers on two-qubit gate count, and expresses a complete algorithm in the lines a framework needs rather than the plumbing a primitive stack demands.
Read the full abstract
Human-Computer Interaction
More Than Just Access: Generative AI as Communication Intermediary for Blind and Low-Vision Users
Generative AI (GenAI) tools are increasingly woven into how blind and low-vision (BLV) people communicate, not only with digital information, but with the physical world and with other people. Tools such as ChatGPT, Google Gemini, Be My AI, and Seeing AI translate visual and textual content into accessible form, and are beginning to substitute for interpersonal requests for help, such as asking a family member to read a label or describe a scene. Drawing on semi-structured interviews with 19 BLV participants, we examine GenAI as a communication intermediary and how it succeeds and fails as an alternative for reading, describing, and even asking another person for help. We also investigated what BLV users gain and risk when these tools take over that role. We conclude with design and policy implications for GenAI systems that communicate uncertainty honestly, protect information, and support BLV users' independence rather than substitute for it unsafely.
Read the full abstract
Artificial Intelligence
NoteVQA: Benchmarking VLMs on Real-Life Questions from Human Communities
Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains challenging. Existing benchmarks often target predefined capabilities, such as multi-hop retrieval or long-form synthesis, whereas users ask photo-grounded questions spanning a long tail of everyday scenarios. Despite advances in VLMs, users on Xiaohongshu, a mainstream Chinese image-sharing platform, continue to turn to other people for help with everyday visual questions. Motivated by this behaviour, we curate NoteVQA from these questions, yielding 252 items across 12 topical categories and 7 user intents. Each item includes a concise reference distilled from expert community responses and a human-audited interleaved reference answer that combines textual explanations with supporting visual evidence. We evaluate both short-answer correctness and interleaved-answer quality. To support the latter, we introduce AgenticInterleave, a single-agent ReAct framework for retrieval-supported answer generation, together with IVR-12, a 12-dimensional rubric for assessing the content, presentation, and image quality of interleaved references and model outputs. Across 9 frontier VLMs, the highest short-answer accuracy is 52.8%, while adding agentic search to Qwen3.5-397B-A17B improves accuracy by only 2.0%. For interleaved answers, the same model running AgenticInterleave scores 3.52 under IVR-12, compared with 4.65 for the human-audited references, with the largest gap in content quality. These results highlight the challenges that everyday visual questions pose for current VLMs in both answer accuracy and the quality of visually grounded explanations.
Read the full abstract
Analysis of PDEs
Harnack Inequality for Parabolic Fractional $p$-Laplace Equations
We establish an intrinsic Harnack inequality with an optimal tail term for weak solutions of parabolic fractional $p$-Laplace equations with $p>2$ and $s\in(0,1)$ whose kernels are symmetric, measurable, and comparable to $|x-y|^{-n-sp}$. It constitutes the nonlocal analogue of the intrinsic Harnack inequality of DiBenedetto, Gianazza and Vespri. In contrast to the exponential change of variables and expansion-of-positivity used in the local case, our technique is nonlocal and relies on comparison arguments and barriers in a variational framework. Indeed, we obtain the stronger conclusion where the forward comparison starts immediately after the reference time, without an additional time gap, which is false in the local case. The latter leads to elliptic-type Harnack estimates for parabolic equations. Our result is new even in the linear case.
Read the full abstract
Cryptography and Security
HYDRA: Quantifying Botnet Resource Thresholds for Efficient Link-Flooding Attacks on LEO Satellite Networks
Low Earth orbit (LEO) satellite constellations, such as Starlink and Kuiper, are rapidly emerging as a critical backbone for low-latency global connectivity. As these systems expand, they become more attractive attack targets, necessitating increased resilience and security. Threat actors seek to exploit constellation-specific properties such as predictable motion, time-varying topologies, and reliance on inter-satellite and ground-satellite links. Recent work has shown that link-flooding attacks (LFAs) can exploit these properties to congest strategic network bottlenecks. Yet, prior work does not quantify the resilience of LEO networks to targeted disruption. We present HYDRA, a modeling and optimization framework that formulates LFA variants as botnet minimization problems. HYDRA quantifies network resilience to LFAs by measuring the smallest active subset of bots and the corresponding traffic allocation required to disrupt communication between targeted geographic areas. Under matched stealth constraints, HYDRA achieves the same targeted disruption as ICARUS while using 34% fewer bots and 23% less aggregate attack traffic. HYDRA achieves over 97% success in sustaining continuous attacks as the network topology evolves. Finally, HYDRA evaluates five mitigation strategies, showing how routing diversification, ingress policing, distance-based traffic constraints, source throttling, and botnet attrition reduce attack success and improve network resilience to targeted disruption.
Read the full abstract
Neural and Evolutionary Computing
Complete Suffix Prediction for Recommendation via Latent Retrieval over Process Graphs
Complete suffix prediction is challenging in sequential decision settings, where the same prefix can remain compatible with several plausible suffixes. We propose a graphbased metric-learning framework that reformulates complete suffix prediction as latent retrieval over process graphs. Prefixes and suffixes are represented as directed attributed graphs and encoded by edge-conditioned graph neural networks, allowing event-level activities and transition-level durations to be modelled jointly. Prefix representations are projected into the latent suffix space through a predictor trained with a joint reconstruction and contrastive objective strengthened using process-aware hard negatives. To stabilise the learned retrieval geometry, spectral normalisation, and retrieval robustness, spectral normalisation is applied to enforce a Lipschitz constraint on both encoders and predictor. Experiments on two real-life process datasets demonstrate that the proposed framework achieves the best overall results across nearly all evaluated criteria. It improves semantic suffix accuracy measured by normalized Damerau-Levenshtein distance, yields strong retrieval quality through Recall@1, Recall@5, and MRR@5, and maintains temporal plausibility according to Mean Absolute Error. These results show that graph-based latent retrieval is an effective alternative to sequential suffix prediction for recommendation-oriented process monitoring under structural and KPI-related constraints.
Read the full abstract
Algebraic Geometry
A blowup criterion for regularity
We prove that a Noetherian integral domain is regular if, and only if, the derived pushforward of the structure sheaf along every blowup is a perfect complex. For suitable local rings, we give a construction which realizes a shift of the residue field as a direct summand of the derived pushforward of the structure sheaf along an explicit blowup.
Read the full abstract
Combinatorics
Laurent Symmetric Functions
We describe the ring of Laurent symmetric polynomials in terms of generators and relations, giving an analogue of the Fundamental Theorem of Symmetric Polynomials. We extend the Hall inner product, and give an algebraic proof that the Laurent Schur polynomials form an orthonormal basis of this ring. In the case of infinitely many variables, we realize the ring of Laurent symmetric functions as a direct limit of inverse limits, and relate them to characters of rational and algebraic representations of general linear groups.
Read the full abstract
Quantum Physics
Distribution of light-matter quantum correlations with a temporally multiplexed solid-state quantum memory array
Multiplexed quantum memories increase the entanglement distribution rate in long-distance quantum repeater architectures by harnessing storage in several degrees of freedom. Here, we report on the distribution of light-matter quantum correlations using an array of time-multiplexed solid-state quantum memories. We store telecom-heralded single photons sequentially in up to ten memory cells using the full atomic frequency comb protocol with on-demand read-out in a Pr$^{3+}$:Y$_2$SiO$_5$ crystal. Leveraging both spatial and temporal multiplexing, we demonstrate quantum correlations between the telecom photon and up to 60 spatio-temporal modes of the quantum memory array. We then transmit the heralding telecom photon over 39.1 km of deployed optical fiber in the Metropolitan Area of Barcelona. In a realistic scenario where the generation rate is limited by the two-way communication time, we show that up to 15 % of the $393 \mu s$ round-trip communication time is filled with communication trials, leading to a 60-fold enhancement in the rate of detected telecom photons correlated with the quantum memory array, compared to a single-mode memory. With increased storage times and efficiencies, our multiplexed quantum memory array will constitute the backbone of a long-distance quantum network, establishing remote entanglement at high rates.
Read the full abstract
Analysis of PDEs
Finite Morse index solutions of the Allen-Cahn equation with energy bound
We study bounded entire solutions of the Allen-Cahn equation in dimension three with quadratic energy growth. We prove that such a solution of finite Morse index I has at most 2I ends. Furthermore, we show that Morse index one solutions have two ends and are axially symmetric, which generalizes an earlier result by Florit-Simon.
Read the full abstract
Artificial Intelligence
EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models
EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding, but their black-box nature limits clinical trust and neuroscientific validation. We propose a unified attribution framework for interpreting EEG foundation models across heterogeneous architectures. The framework integrates gradient-, perturbation-, and activation-based explanation methods to analyze model behavior in spatial, temporal, and frequency dimensions. Spatially, it identifies critical EEG channels and visualizes their distributions using topographic maps. Temporally, it highlights decision-relevant signal segments through attribution heatmaps. In the frequency domain, it quantifies the contributions of canonical EEG rhythms via spectral perturbation analysis. To assess explanation reliability, we introduce a population-level evaluation combining Area Over the Perturbation Curve (AOPC) and cross-method consistency analysis. The framework further leverages Large Language Models (LLMs) to transform structured attribution outputs into natural-language reports, bridging low-level neural representations and high-level semantic reasoning. Experiments on benchmark datasets, including Mumtaz2016 and TUAB, demonstrate that the generated explanations are consistent with established neurophysiological markers, validating meaningful neural representations while exposing potential dependencies on artifacts and spurious patterns. The proposed framework provides a standardized approach for evaluating the interpretability, reliability, and physiological plausibility of EEG foundation models.
Read the full abstract
Software Engineering
Technostress in the Age of AI: A Preliminary Study with Software Professionals
The rapid adoption and evolution of AI are changing software engineering work and requiring professionals to repeatedly adapt their knowledge, practices, and skills. Although technological adaptation has long characterized software development, less is known about how these new and recurring pressures manifest as technostress. This preliminary exploratory study investigates AI related technostress among software professionals. We conducted a survey and performed a thematic analysis of responses from 121 software professionals across 26 countries reporting their recent experiences with AI at work. Our findings suggest that AI related technostress emerges not only from adapting to rapidly changing technologies, but also from having to manage the work, technical responsibilities, and professional changes that accompany their adoption. This characterization shows that AI introduces pressures beyond learning and using new tools, affecting how software professionals perform and remain accountable for technical work and how they prepare for the future of their careers.
Read the full abstract
Human-Computer Interaction
Can a Neural Encoding Model Replicate an fMRI Visualization Study?
Most knowledge of graphical perception comes from behavioral studies. Understanding from a neural perspective is much more limited due in part to neuroimaging studies' expensiveness and difficulty to conduct. In this paper, we evaluate whether Meta's Tribe V2 neural encoding model can recover neural contrasts from a visualization fMRI study. Specifically, we evaluate Tribe V2 through a conceptual replication of the visualization-viewing component of a prior comparison of Bubble charts and three-dimensional Surface charts in color and grayscale. We generate TRIBE-predicted cortical responses for the original stimuli and compare the resulting contrasts with those reported in the human study. The model reproduced the direction of 11 of 14 reported cortical effects, with agreement concentrated in visual-processing regions. This agreement characterizes the model's alignment with the prior human-generated fMRI results rather than independently confirming them. We discuss the limitations encountered when working with this model for in-silico replication and hope to encourage future work exploring this new avenue for neuroimaging studies in visualization. Supplemental materials are available at https://osf.io/8a96x/.
Read the full abstract
Computation and Language
RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language Agents
Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill patch without explicitly maintaining how failure explanations relate to candidate repairs or how unsuccessful retests should influence later edits. We introduce RESKILL, a structured repair framework that maintains an explicit repair state across repair rounds. Given a failed rollout, the framework links failure hypotheses to candidate skill patches, selects local repairs through coverage-based attribution, retests the edited skill set in the environment, and uses retest outcomes to guide subsequent repair updates. The language model supplies structured repair factors, while the repair procedure records them, compares local skill patches by how well they address active failure explanations, and carries unsuccessful retest outcomes into later repair rounds. We evaluate RESKILL on ALFWorld and TextCraft across three model sizes under fixed repair budgets. RESKILL obtains the strongest final success in all six benchmark-model settings, improving average final success by 3.7 percentage points over direct repair and 3.3 points over hypothesis-conditioned repair. These results suggest that explicit attribution alone is insufficient; durable improvement emerges when attribution is integrated with repair selection and persistent retest-conditioned update.
Read the full abstract
Computer Vision
V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments
While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particularly regarding video demonstrations in interactive environments. For multimodal agents, learning from videos presents unique challenges: they must translate in-context demonstrations into executable policies, ground these policies in novel visual states, and iteratively refine actions based on environmental feedback. We introduce V-ICAL, a novel benchmark designed to evaluate video-based ICL for multimodal agents. Comprising 342 interactive tasks across 37 environments, V-ICAL utilizes human-curated demonstration videos as task-specific behavioral exemplars, evaluating agents through sustained interaction from a target initialization. The benchmark seamlessly connects in-context knowledge induction with core agentic capabilities, including state grounding, temporal memory, planning, and adaptation in dynamic environments. Extensive evaluations across 19 state-of-the-art multimodal agents reveal significant limitations: the best-performing model, Seed-2.1-Pro, achieves a score of only 54.4/100, while other leading models (e.g., Gemini-3.1-Pro, GPT-5.6) fail to surpass 50, far below the human baseline of 83.6. Controlled comparisons further demonstrate that current agents struggle to reliably translate video exemplars into effective policies, failing to yield consistent performance gains. Ultimately, V-ICAL exposes a critical gap in the ICL capabilities of multimodal agents, underscoring an urgent need for future research.
Read the full abstract
Optics
Setup and performance of focal-plane characterization benches for high precision astrometry
Detecting Earth-like exoplanets requires micro-arcsecond astrometry, which relies on a precisely calibrated focal plane equipped with high-resolution detectors. Accurate calibration depends on characterizing detector imperfections and systematic effects. Optical benches have been developed to assess the sensor's behavior: an integrating-sphere setup for electro-optical parameters, an interferometric bench for pixel-level geometry, and a star-field projection system for intrinsic distortion. This work presents the characterization benches built for a 46-Megapixels (MP) imaging sensor, based on the same technology as the four 220-MP detectors foreseen for the final focal-plane, and the performance metrics obtained from these setups in the context of NASA's HWO and ESA's M-class missions. Upgrades will bring the test environment closer to operational conditions: a second 46-MP sensor will be added for multi-detector tests, plus an adjustable-angle fringeprojection system and improved alignment.
Read the full abstract
Distributed Computing
Scalability and Performance Evaluation of Federated Learning Frameworks: A Comparative Analysis
This paper presents a systematic examination and experimental comparison of the prominent Federated Learning (FL) frameworks FedML, Flower, Substra, and OpenFL. The frameworks are evaluated experimentally by implementing Federated Learning over a varying number of clients, emphasizing a thorough analysis of scalability and key performance metrics. The study assesses the impact of increasing client counts on total training time, loss and accuracy values, and CPU and RAM usage. Results indicate distinct performance characteristics among the frameworks, with Flower displaying an unusually high loss, FedML achieving a notably low accuracy range of 66% to 79%, and Substra demonstrating good resource efficiency, albeit with an exponential growth in total training time. Notably, OpenFL emerges as the most scalable platform, demonstrating consistent accuracy, loss, and training time across different client counts. OpenFL's stable CPU and RAM underscore its reliability in real-world scenarios. This comprehensive analysis provides valuable insights into the relative performance of FL frameworks, offering good understanding of their capabilities and providing guidance for their effective deployment across diverse user bases.
Read the full abstract
Robotics
Volumetric Harmonic Field Navigation for Quadrotors
Quadrotor navigation in cluttered 3-D environments requires global guidance while local motion remains subject to collision and motion limits. Harmonic potentials provide dense guidance from a global boundary value problem, but coupling a volumetric harmonic field to constrained physical quadrotor motion remains an open experimental problem. We couple a precomputed volumetric harmonic field with a constrained predictive planner that queries the field at predicted positions instead of extracting a global reference path. In Structured 3-D tests, harmonic guidance yields larger minimum clearance and lower RMS jerk than matched Dijkstra guidance, at the cost of longer paths; the same pattern remains when both methods use the same passage. Long maze tests span routes far beyond one prediction horizon, and Crazyflie trials validate physical execution. To the best of our knowledge, this is the first physical quadrotor demonstration of volumetric harmonic field navigation. The results show that globally constructed harmonic guidance can directly support local constrained motion generation on a physical quadrotor.
Read the full abstract
Optimization and Control
Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional Optimization
This paper studies projection-free algorithms for stochastic constrained multi-level compositional optimization. In this context, the objective function is a nested composition of several smooth functions, and the decision set is closed and convex. Since projection onto the constraint set can be computationally expensive, we develop projection-free methods that rely on linear minimization oracles. For non-convex objectives, we propose variance-reduced projection-free algorithms and establish complexity guarantees under both the Frank-Wolfe gap and the gradient mapping criteria. We also develop momentum-based methods that achieve convergence guarantees under weaker smoothness assumptions. Additionally, by using a stage-wise design, we derive a parameter-free variant that preserves the same complexities for the Frank-Wolfe gap. Such a design can be further used to develop algorithms for convex and strongly convex functions whose rates match those of single-level projection-free counterparts. Finally, we consider finite-sum problems and derive complexities for non-convex, convex, and strongly convex objectives. Numerical experiments across multiple tasks demonstrate the effectiveness of the proposed methods.