Forskningsradar

Science Journals

Peer-reviewade publikationer — 51242 artiklar

arXiv (fysik & CS) Preprint 2026-05-20
Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
arXiv:2605.19956v1 Announce Type: new Abstract: Vision-Language Models (VLMs), such as CLIP, have achieved significant zero-shot performance on downstream tasks with various fine-tuning adaptation methods. However, recent studies have proven that adversarial attacks can significantly degrade the inference ability of VLMs, posing substantial risks to their practical applications. Prevalent test-time adaptation methods typically rely on multi-view augmentation to implement various fine-tuning strategies, which struggle to identify semantic information and are prone to destroying discriminative regions in fine-grained scenarios. To address these limitations, we propose Attention-Guided Test-Time Prompt Tuning (A-TPT), a semantics-preserving method designed for test-time adaptation. We first refine the gradient attention rollout mechanism to identify semantically meaningful regions surviving under adversarial attacks. Furthermore, we leverage them to guide the spatially varying augmentation intensities and multi-view ensemble for prompt tuning and inference. Extensive experiments demonstrate that A-TPT outperforms existing test-time adaptation methods on both adversarial and clean data. Codes are available at https://github.com/SEU-VIPGroup/A-TPT .
arXiv (fysik & CS) Preprint 2026-05-20
Learning Orthonormal Bases for Function Spaces
arXiv:2605.19959v1 Announce Type: new Abstract: Infinite-dimensional orthonormal basis expansions play a central role in representing and computing with function spaces due to their favorable linear algebraic properties. However, common bases such as Fourier or wavelets are fixed and do not adapt to the structure of a given problem or dataset. In this paper, we aim to represent these bases with neural networks and optimize them. Our key idea is that any target infinite-dimensional orthonormal basis can be viewed either as a point on the Lie manifold of the orthogonal group, or equivalently, as the endpoint of a continuous path on that manifold that connects a reference basis, e.g. Fourier, to that target. Paths on the Lie manifold satisfy ordinary differential equations (ODEs) governed by skew-adjoint integral operators. Using neural networks to define finite-rank generators of such ODEs allows us to parameterize and optimize orthonormal bases in function space. While relying on finite-rank generators to model infinite operators might seem restrictive, we prove a universality result: even with a rank-2 generator, the integrated solutions of the ODE are dense in the orthogonal group under the appropriate operator topology. In other words, for any target orthonormal basis, there exists a path originating from a reference basis and driven by finite-rank generators that gets arbitrarily close to that target basis. We demonstrate the flexibility of our framework by transforming the Fourier basis into the principal components of a functional dataset, eigenfunctions of linear operators, or dynamic modes of energy-preserving physical simulations.
arXiv (fysik & CS) Preprint 2026-05-20
Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes
arXiv:2605.19966v1 Announce Type: new Abstract: Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point detection problem over the token-level next-token entropy stream. Using the LLM system prompt to estimate a robust baseline, we standardize user-token entropies and apply a one-sided CUSUM statistic. The resulting detector, CPD Online (CPD), is model-agnostic, training-free, runs online, and localizes the adversarial suffix onset. On a benchmark of 1,012 optimization-based suffix attacks (GCG, AutoDAN, AdvPrompter, BEAST, AutoDAN-HGA) and 1,012 perplexity-controlled benign prompts, CPD improves F1 over the strongest windowed-perplexity baseline on all six open-weight chat models (LLaMA-2-7B/13B, Vicuna-7B/13B, Qwen2.5-7B/14B). On LLaMA-2-7B at the canonical CUSUM setting ($k=0$), CPD reaches AUROC $0.88$ and F1 $0.82$. Beyond prompt-level detection, CPD concentrates 79.6% of its triggers inside the adversarial suffix, versus 17-46% for windowed perplexity. Finally, when used as a lightweight gate for LLaMA Guard, CPD reduces guard calls by 17-22% on a high-volume, benign-dominated deployment while preserving guard-level detection quality
arXiv (fysik & CS) Preprint 2026-05-20
Block-Sphere Vector Quantization
arXiv:2605.19972v1 Announce Type: new Abstract: Vector quantization is a fundamental primitive for scalable machine learning systems, enabling memory-efficient storage, fast retrieval, and compressed inference. Recent rotation-based quantizers such as EDEN, RabitQ, and TurboQuant have introduced strong guarantees and empirical performance, but the surrounding comparisons have been difficult to interpret because they rely on different distortion criteria, probability regimes, and implementation assumptions. As our first contribution, we provide a unified theoretical comparison of these methods and show that their relative advantages are criterion-dependent rather than absolute: EDEN and TurboQuant are favorable for MSE distortion, EDEN is also effective for expected inner-product distortion, and RabitQ provides strong high-probability control. This comparison further clarifies that EDEN provides particularly strong guarantees for expected distortion measures. As our second contribution, we introduce Block-Sphere Quantization (BlockQuant), a new rotation-based block quantization algorithm designed around the spherical geometry of randomly rotated vectors. Unlike coordinate-wise quantizers, BlockQuant quantizes blocks on the sphere, preserving the geometry of rotated embeddings more faithfully. We prove that this block-spherical design theoretically improves over the baselines considered in this paper for both reconstruction MSE and expected inner-product distortion. Our experiments on real embedding datasets and long-context LLM inference tasks show practical gains that are consistent with our theoretical improvements.
arXiv (fysik & CS) Preprint 2026-05-20
Computing Certificates in Archimedean Univariate Saturated Quadratic Modules
arXiv:2605.18980v1 Announce Type: new Abstract: A new symbolic algorithm to compute sums of squares multipliers (certificates) to witness the membership of non-negative univariate polynomials in a saturated univariate quadratic module is presented. Certificates are first computed in terms of natural generators introduced by Kuhlmann and Marshall for an Archimedean saturated quadratic module; natural generators can be easily read-off from a semialgebraic set. In the univariate case, an Archimedean quadratic module is also a preordering since it is closed under multiplication; certificates have different representations when a polynomial is viewed as a member in a quadratic module versus in a preordering An algorithm is given to compute certificates of natural generators in terms of the original generators; it uses a construction introduced by Kuhlmann, Marshall, and Schwartz known as the ``Basic Lemma'', which splits the non-negative factors of generators. To compute a quadratic module certificate, certificates of products of natural generators are computed using a detailed case analysis based on the types of natural generators. An implementation of the algorithms proposed in Maple is also discussed. The certificates obtained using this implementation are compared with those generated by RealCertify. We discuss examples where RealCertify is unable to find certificates while the proposed method is successful.
arXiv (fysik & CS) Preprint 2026-05-20
Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks
arXiv:2605.18988v1 Announce Type: new Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary attack surface. Empirical observations indicate that adversaries employ progressive, cross-modal perturbations that evade turn-specific guardrails by distributing malicious intent across longitudinal conversational trajectories. Static defense mechanisms, constrained by the Markov property, evaluate inputs in isolation and fail to detect cumulative structural poisoning. To handle this limitation, this paper formulates safety verification as a dynamic survival prediction and trajectory dynamics problem. The Triple-tier Anomaly Defense (TRIAD) framework is proposed as a predictive model that maps multimodal and multi-turn conversational flow as a continuous trajectory. The framework integrates structural anomaly detection to monitor covariance shifts, a Ledoit-Wolf regularized Mahalanobis distance to monitor covariance shifts in high-dimensional spaces, and topological trajectory acceleration to differentiate benign creative exploration from continuous malicious drift. These kinematic and geometric features are integrated into a time-varying Cox Proportional Hazards model via a Bayesian Hidden Markov Model (HMM) feedback loop. Theoretical analysis demonstrates that the TRIAD framework provides a mathematically bounded expected time-to-failure under adversarial perturbations, ensuring that malicious acceleration diverges positively. This framework provides a computationally efficient, interpretable, and predictive safeguard for real-time agentic AI systems, establishing a rigorous foundation for continuous safety alignment without relying on empirical retraining.
arXiv (fysik & CS) Preprint 2026-05-20
Concave is the New Linear: The Impossibility of Anti-Plutocratic DAO Governance
arXiv:2605.18990v1 Announce Type: new Abstract: Decentralized Autonomous Organizations (DAOs) run protocol governance by letting token holders vote on proposals. The dominant rule, voting power proportional to wallet balance, concentrates control among a small number of large holders, fueling the token-control governance attacks that have already compromised real protocols. To counter this concentration, the community has turned to anti-plutocratic voting mechanisms such as Quadratic Voting (QV), which assign sublinear voting power per token with the goal of dampening the influence of large holders. We prove that no voting rule that derives power solely from wallet balance can succeed on a permissionless blockchain. Through a costed model of on-chain voting that captures realistic blockchain frictions -- including per-wallet splitting and voting costs, fixed setup costs, and minimum-balance requirements -- we show that whenever a wallet of any size yields nonzero voting power, a Sybil attacker who splits tokens across many wallets achieves total voting power that grows at least linearly in their token holdings. For concave rules actually proposed to dampen governance power -- those that are positive, increasing, and finite -- we show that the optimal strategy yields power that is asymptotically linear in token holdings, regardless of the cost scheme. Instantiating the model on real DAOs reveals attack costs orders of magnitude below the value at stake. Replaying the ten most recent finalized proposals of five major DAOs (ENS, Compound, Uniswap, Arbitrum, and ZKsync) under linear, quadratic, logarithmic, and power-($\beta = 0.25$) voting, we measure Sybil amplification factors between $1,172\times$ and $4,039\times$ under Quadratic Voting, and exceeding $229,000\times$ under steeper power rules.
arXiv (fysik & CS) Preprint 2026-05-20
Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction
arXiv:2605.19975v1 Announce Type: new Abstract: Neural policies have shown promise in solving vehicle routing problems due to their reduced reliance on handcrafted heuristics. However, current training paradigms suffer from a fundamental limitation: they primarily focus on next-node prediction for solution construction, resulting in myopic decision-making that undermines long-horizon planning capacity. To this end, we introduce Multi-node Lookahead Prediction (MnLP), a novel training strategy that extends the supervised learning paradigm to predict multiple future nodes simultaneously. We incorporate causal and discardable MnLP modules that operate exclusively during training, facilitating models to anticipate multi-step decisions while preserving inference-time efficiency. By incorporating multi-depth auxiliary supervision into the loss function, MnLP equips neural policies with the ability of long-range contextual understanding. Experimentally, MnLP outperforms existing training methods, improving the generalization capability of neural policies across various problem sizes, distributions, and real-world benchmarks. Moreover, MnLP can be seamlessly integrated into diverse neural architectures without introducing additional inference overhead.
arXiv (fysik & CS) Preprint 2026-05-20
Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection
arXiv:2605.19122v1 Announce Type: cross Abstract: Tensor-valued data arise naturally in neuroimaging, genomics, climate science, and spatiotemporal networks, where multilinear dependencies across modes carry information that is destroyed under vectorization. Existing approaches either impose a single low-rank structure, which can miss localized signal, or treat the tensor as a long vector, which discards its multiway geometry. We propose a *Dual-Channel Tensor Neural Network* (DC-TNN) that decomposes each tensor input into a low-rank core and a sparse refinement, and processes the two components through coupled neural channels. The framework is structure-agnostic and accommodates CP, Tucker, and tensor-train cores within a single architecture. For estimation, we establish non-asymptotic risk bounds for the DC-TNN estimator that decompose into network approximation, core estimation, and refinement-selection terms, and show that the effective dimension is determined jointly by the core rank and refinement sparsity rather than by the ambient tensor size. For inference, we develop a *structure-aware conformal ROC* procedure that calibrates within the core-refinement latent space and produces ROC and AUC confidence bands with finite-sample, distribution-free coverage. Building on this, we propose a *conformal structure selector* that, to our knowledge, is the *first distribution-free procedure* for choosing among candidate tensor decompositions with finite-sample validity. Simulations and an analysis of a protein dataset demonstrate competitive predictive accuracy, reliable uncertainty quantification, and consistent recovery of the tensor structure.
arXiv (fysik & CS) Preprint 2026-05-20
GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards
arXiv:2605.20006v1 Announce Type: new Abstract: Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hindered by the cost of annotating a vast and combinatorial question space. We propose GeoX, a self-play framework that acquires spatial logic through executable programs that yield verifiable rewards, without relying on large-scale human-curated data Given a satellite or aerial image, our framework employs a single multimodal policy that proposes spatial problems as executable programs and solves them under three reasoning modes-abduction, deduction, and induction-over spatial primitives and an image understanding tool. A verifier executes each program to covert a reward signal that jointly optimizes the two roles via reinforcement learning. GeoX consistently improves its base VLMs by up to 5.5 points on average, matching or exceeding conventional baselines trained on millions of curated data. Along-side the proposed method, we release a benchmark for geospatial understanding accumulated through self-play.
arXiv (fysik & CS) Preprint 2026-05-20
Learning from Language Feedback via Variational Policy Distillation
arXiv:2605.15113v2 Announce Type: replace Abstract: Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing language feedback to generate dense, token-level supervision. However, these approaches rely on a fixed, passive teacher to interpret the feedback. As the student policy improves, the teacher's zero-shot assessment capabilities plateau, ultimately halting further learning. To overcome this, we propose Variational Policy Distillation (VPD), a framework that formalizes learning from language feedback as a Variational Expectation-Maximization (EM) problem. VPD co-evolves both policies: in the E-step, the teacher is actively refined on trajectory outcomes via an adaptive trust-region update, translating textual feedback into a dynamically improved target token distribution. In the M-step, the student internalizes this dense distributional guidance on its own on-policy rollouts. By continuously improving the teacher's ability to extract actionable signals from textual critique, VPD overcomes the limitations of passive distillation. Evaluated across diverse sources of diagnostic feedback on scientific reasoning and code generation tasks, VPD consistently outperforms both standard RLVR and existing self-distillation baselines. Finally, by stress-testing our framework on rigid mathematical reasoning and cold-start regimes, we illuminate the fundamental bounds of feedback-driven self-distillation compared to pure environment-driven RL.
arXiv (fysik & CS) Preprint 2026-05-20
A Systematic Failure Analysis of Vision Foundation Models for Open Set Iris Presentation Attack Detection
arXiv:2605.19020v1 Announce Type: new Abstract: Vision foundation models have demonstrated strong transferability across diverse visual recognition tasks and are increasingly considered for biometric applications. Their suitability for iris Presentation Attack Detection (PAD), particularly under realistic open-set operating conditions, remains insufficiently examined. This work presents a systematic failure analysis of general-purpose vision foundation models for open-set iris PAD using periocular imagery. Five representative foundation models are evaluated under three open-set protocols that explicitly separate different sources of distribution shift: unseen Presentation Attack Instruments (PAIs), unseen datasets captured with different sensors and cross-spectral transfer from near-infrared (NIR) to visible spectrum (VIS) imagery. Both frozen feature representations and parameter-efficient task adaptation using Low-Rank Adaptation (LoRA) are assessed within a unified experimental framework. The results indicate that foundation models can transfer across datasets with similar sensing characteristics, but fail to generalise reliably to unseen attack instruments and degrade sharply under cross-spectral evaluation. While LoRA improves performance in certain cross-dataset settings, it frequently amplifies failure under attack-level and spectral shifts. Additional validation experiments using segmented iris inputs, full backbone fine-tuning, joint cross-dataset and cross-PAI shifts, and reverse VIS to NIR transfer further confirm that these failures are not simply artefacts of periocular input, weak adaptation, or one-directional spectral evaluation. These findings show that strong closed-set or cross-dataset performance should not be treated as evidence of robust open-set security, and highlight the need for PAD representations that maintain sensitivity to presentation artefacts while remaining stable under realistic deployment variation.
arXiv (fysik & CS) Preprint 2026-05-20
OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives
arXiv:2605.20044v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically address this by either distilling high-dimensional feature embeddings into Gaussians or by lifting 2D mask labels into 3D via heuristic refinement. However, feature-based approaches incur heavy storage and decoding overhead, while lifting-based pipelines remain vulnerable to label contamination: Gaussians necessary for appearance reconstruction often receive incorrect object labels during 2D-to-3D projection. We propose OP2GS, an object-aware Gaussian representation that augments each primitive with an explicit instance identity and a dedicated instance opacity $\sigma^{*}$ for object-mask rendering. The original opacity $\sigma$ remains responsible for visual reconstruction, while $\sigma^{*}$ models whether a Gaussian should contribute to a particular object mask. This dual-opacity formulation decouples visual existence from instance occupancy: mislabeled Gaussians can remain available for image rendering while becoming transparent in the object-mask branch. To learn this representation, we introduce a random object loss that optimizes the 1D instance occupancy field using the standard transmittance-based visibility of 3DGS. Semantic descriptors are then attached at the object level through multi-view aggregation, eliminating per-Gaussian feature storage. Compared with feature-training approaches, OP2GS achieves competitive open-vocabulary performance while significantly reducing computational overhead. Compared with training-free pipelines, it leverages physically consistent occupancy learning to resolve visibility ambiguities.
arXiv (fysik & CS) Preprint 2026-05-20
Hunting Vulnerability Variants in AI Infra: Measurement and Reference-Driven Detection
arXiv:2605.20051v1 Announce Type: new Abstract: AI infra has become a shared execution layer for model training, deployment, and agent orchestration. Because many projects reimplement similar model-centric workflows, a vulnerability disclosed in one repository can recur as a variant in another repository with a related design. Yet the prevalence and detectability of these variants remain poorly understood. This paper presents a measurement study of vulnerability variants in AI infra. Analyzing 688 GitHub repositories and 251 publicly disclosed vulnerabilities, we find that AI infra projects frequently share overlapping functionality and recurrent vulnerable patterns, creating a concrete basis for cross-repository variants. Building on this finding, we study how to automatically identify such variants from known disclosures. We propose INFRASCOPE, a reference-driven multi-agent framework that extracts transferable vulnerability semantics from known cases and uses them to locate and validate variants in new repositories. Evaluating INFRASCOPE on 20 real-world AI infra repositories, we uncover over 20 vulnerabilities, including 11 acknowledged cases and 4 cases that have been assigned CVEs so far.
arXiv (fysik & CS) Preprint 2026-05-20
Convergence of Consensus-Based Particle Methods for Nonconvex Bi-Level Optimization
arXiv:2605.19667v1 Announce Type: cross Abstract: In this paper, we study a consensus-based optimization method for nonconvex bi-level optimization, where the objective is to minimize an upper-level function over the set of global minimizers of a lower-level problem. The proposed approach is derivative-free, and constructs its consensus point via smooth quantile selection combined with a Gibbs-type Laplace approximation. We establish convergence guarantees for both the associated \textit{mean-field} dynamics and its \textit{finite-particle} approximation. In particular, under suitable assumptions on smooth quantile localization, error bounds, and stability, we show that the mean-field law reaches any arbitrary prescribed Wasserstein neighborhood of the target bi-level solution with an explicit exponential rate up to the hitting time. Numerical experiments on a two-dimensional constrained problem and neural network training further support the theoretical results.
arXiv (fysik & CS) Preprint 2026-05-20
Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
arXiv:2605.20061v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete observations cause agent beliefs to drift over time, while delayed rewards obscure the causal impact of intermediate decisions, exacerbating temporal credit assignment challenges. To address this, we propose ReBel (Reward Belief), a process-level reinforcement learning algorithm that explicitly models structured belief states to summarize interaction history and guide subsequent policy learning. ReBel introduces belief-consistency supervision, converting discrepancies between predicted beliefs and observed feedback into dense self-supervised signals without requiring external step-wise annotations or verifiers. It also employs belief-aware grouping to compare trajectories under similar belief states, yielding more robust and lower-variance advantage estimates. We evaluate ReBel on challenging long-horizon benchmarks, including ALFWorld and WebShop. ReBel improves task success by up to $20.4$ percentage points over the episode-level baseline GRPO and increases sample efficiency by $2.1\times$. These results suggest that belief-aware self-supervision is a promising direction for reliable long-horizon decision-making under partial observability. Code is available at: https://github.com/Fateyetian/Rebel.git.
arXiv (fysik & CS) Preprint 2026-05-20
Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP
arXiv:2605.20066v1 Announce Type: new Abstract: Knowledge graph question answering seeks to translate natural language questions into executable queries over knowledge graphs, but existing approaches often rely on large models or full supervision in the form of gold query annotations. This study examines whether reinforcement learning with outcome-based rewards can train a small instruction-tuned language model to perform zero-shot Text-to-SPARQL generation in the scholarly domain. Group-Relative Policy Optimization (GRPO) is applied to the Qwen3-1.7B model on DBLP-QuAD, using prompts that combine natural language questions with symbolic hints about entities and relations. Training relies on execution feedback, structural constraints, and answer-level rewards, with an additional variant that incorporates gold-query-based shaping. The resulting models are compared to the unmodified zero-shot baseline and to a supervised DoRA-finetuned baseline across answer-level accuracy, execution accuracy, category-wise scores, and generalization to held-out templates. GRPO substantially improves over the zero-shot baseline and exhibits competitive generalization, while supervised DoRA finetuning achieves higher overall accuracy on the same model scale. Ablation analyses indicate that execution-based rewards account for most gains, with additional shaping yielding limited additional benefit, suggesting that outcome-based reinforcement learning is a viable training strategy when gold queries are unavailable for token-level supervision.
arXiv (fysik & CS) Preprint 2026-05-20
Towards Distillation Guarantees under Algorithmic Alignment for Combinatorial Optimization
arXiv:2605.20074v1 Announce Type: new Abstract: Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowledge about the task can guide the choice of a target architecture that is algorithmically aligned with the underlying problem. Building on recent learning-theoretic analyses of decision-tree (DT) distillation (Boix-Adsera, 2024), we study when distillation succeeds for combinatorial optimization tasks. We focus on the case where the target model is a graph neural network whose architecture is aligned with a dynamic programming (DP) algorithm for the task. Assuming that the source model is sufficiently rich, formalized through the linear representation hypothesis (LRH) (Elhage et al., 2022; Park et al., 2024), we show that the distillation problem can be solved efficiently in the complexity parameters of the DP transition function, represented as a DT. Our results provide a rigorous sufficient condition for successful distillation in the flavour of algorithmic alignment.
arXiv (fysik & CS) Preprint 2026-05-20
BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation
arXiv:2605.20084v1 Announce Type: new Abstract: Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the model-only answer is reliable. This motivates cascaded RAG: each query is first handled by an LLM-only branch, escalated to a RAG fallback only if the primary branch is uncertain, and abstained from when neither branch is sufficiently trustworthy. However, calibrating such cascades stage by stage may be conservative, since the final utility depends on joint uncertainty thresholding of LLM-only and RAG. In this work, we develop BalanceRAG to certify threshold pairs at a target risk level. Given uncertainty scores from the two branches, BalanceRAG frames each threshold pair as an operating point on a two-dimensional lattice and identifies safe operating points using sequential graphical testing. This enables risk-adaptive threshold calibration, controlling the system-level error rate among accepted points, while retaining more examples. Furthermore, BalanceRAG extends to multi-risk calibration, allowing retrieval usage to be bounded together with the selection-conditioned risk. Experiments on three open-domain question answering (QA) benchmarks across multiple LLM backbones demonstrate that BalanceRAG meets prescribed risk levels, preserves higher coverage and more accepted correct examples, and reduces unnecessary retrieval calls compared with always-on RAG.
arXiv (fysik & CS) Preprint 2026-05-20
Reliable sampling-based RKHS norm estimation via superconvergence
arXiv:2605.20091v1 Announce Type: new Abstract: Kernel methods are one of the cornerstones of learning-based control, modern system identification, surrogate modelling, and related fields. A key advantage of this class of learning and function approximation methods is the availability of quantitative error bounds, which in turn play a key role in guaranteeing the safety of learned controllers and related learning-based algorithms. However, these error bounds rely on a particular property of the target function -- its reproducing kernel Hilbert space (RKHS) norm -- which is usually impossible to obtain in practice. Motivated by this severe shortcoming, we present a novel sampling-based RKHS norm estimation approach with a solid theoretical foundation, leveraging very recent advances in the theory of superconvergence in kernel methods. Our method is applicable to a broad range of practically relevant function classes and requires only reasonable prior knowledge about the target function. Extensive numerical experiments demonstrate the efficacy and practical applicability of the proposed method. By providing a reliable RKHS norm estimation approach, we remove a major obstacle to the practical deployment of learning-based control algorithms.
arXiv (fysik & CS) Preprint 2026-05-20
Hermitian hull-variation of vector rank-metric codes and self-orthogonal generalized Gabidulin codes
arXiv:2605.20109v1 Announce Type: new Abstract: We study the Hermitian hull-variation problem for vector rank-metric codes. Except for one parameter pair, we show that the Hermitian hull dimension of such a code can be reduced to any smaller value within its equivalence class, and in particular every such code is equivalent to a Hermitian LCD code. We then address the existence of maximum rank distance (MRD) codes with prescribed Hermitian hull dimension. To this end, we introduce the notion of a \emph{scaled trace-self-dual basis} of a finite field extension, which exists in all cases, and use it to construct Hermitian self-orthogonal generalized Gabidulin codes for every prime power. Combined with the hull-variation theorem, this yields MRD codes attaining every admissible Hermitian hull dimension.
arXiv (fysik & CS) Preprint 2026-05-20
On Approximability of Satisfiable k-CSPs: V
arXiv:2408.15377v4 Announce Type: replace Abstract: We propose a framework of algorithm vs. hardness for all Max-CSPs and demonstrate it for a large class of predicates. This framework extends the work of Raghavendra [STOC, 2008], who showed a similar result for almost satisfiable Max-CSPs. Our framework is based on a new hybrid approximation algorithm, which uses a combination of the Gaussian elimination technique (i.e., solving a system of linear equations over an Abelian group) and the semidefinite programming relaxation. We complement our algorithm with a matching dictator vs. quasirandom test that has perfect completeness. The analysis of our dictator vs. quasirandom test is based on a novel invariance principle, which we call the mixed invariance principle. Our mixed invariance principle is an extension of the invariance principle of Mossel, O'Donnell and Oleszkiewicz [Annals of Mathematics, 2010] which plays a crucial role in Raghavendra's work. The mixed invariance principle allows one to relate 3-wise correlations over discrete probability spaces with expectations over spaces that are a mixture of Guassian spaces and Abelian groups, and may be of independent interest.
arXiv (fysik & CS) Preprint 2026-05-20
Entry-level guide to the use of large language models for medical research
arXiv:2410.18856v4 Announce Type: replace Abstract: Frontier large language models (LLMs), such as GPT-5, Claude 4.5, Gemini 3, Llama 4, and DeepSeek-R1, represent a transformative class of AI tools capable of revolutionizing various aspects of healthcare by generating human-like responses across diverse contexts and adapting to novel tasks following human instructions. Their potential application spans a broad range of medical tasks, such as clinical documentation, matching patients to clinical trials, and answering medical questions. In this paper, we propose an actionable guideline to help healthcare professionals more effectively and efficiently utilize LLMs in their work, along with a set of best practices. The overall workflow consists of several main phases, including formulating the task, choosing LLMs, prompt engineering, fine-tuning, and model deployment. We start with the discussion of critical considerations in identifying medical tasks that align with the core capabilities of LLMs and selecting models based on the selected task and data, performance requirements, and model interface. We then review the strategies, such as prompt engineering and fine-tuning, to adapt standard LLMs to specialized medical tasks. Deployment considerations, including regulatory compliance, ethical guidelines, and continuous monitoring for fairness and bias, are also discussed. By providing a structured step-by-step methodology, this entry-level tutorial aims to equip healthcare professionals with the tools necessary to effectively integrate LLMs into clinical practice, ensuring that these powerful technologies are applied in a safe, reliable, and impactful manner.
arXiv (fysik & CS) Preprint 2026-05-20
An Efficient Multilevel Preconditioned Nonlinear Conjugate Gradient Method for Incremental Potential Contact
arXiv:2604.19892v1 Announce Type: cross Abstract: Incremental Potential Contact (IPC) guarantees intersection-free simulation but suffers from high computational costs due to the expensive Hessian assembly and linear solves required by Newton's method. While Preconditioned Nonlinear Conjugate Gradient (PNCG) avoids Hessian assembly, it has historically struggled with poor convergence in stiff, contact-rich scenarios due to the lack of effective preconditioners; simple Jacobi preconditioners fail to capture the global coupling, while advanced hierarchy-based preconditioners like Multilevel Additive Schwarz (MAS) are computationally prohibitive to rebuild at every nonlinear iteration. We present MAS-PNCG, a method that unlocks the power of hierarchical preconditioning for nonlinear optimization. Our key technical innovation is a Sparse-Input Woodbury update algorithm that incrementally adapts the fine-level MAS components to rapidly evolving contact sets. This bypasses the need for full preconditioner rebuilds, reducing maintenance cost to near-zero while capturing the complex spectral properties of the contact system. Furthermore, we replace heuristic PNCG search directions with a Hessian-aware 2D subspace minimization that optimally combines the preconditioned gradient and previous direction. We also apply a fast per-subdomain conservative CCD method that ensures penetration-free trajectories while avoiding overly restrictive global step sizes. Experiments demonstrate that our MAS-PNCG outperforms state-of-the-art Newton-PCG solvers, GIPC and StiffGIPC, both preconditioned with MAS up to 5.66$\times$ and 2.07$\times$ respectively.
arXiv (fysik & CS) Preprint 2026-05-20
3D Modeling and Automated Measurement of Concrete Cracks via Segment Anything Refinement and Visual Inertial LiDAR Fusion
arXiv:2501.09203v2 Announce Type: replace Abstract: Visual-Spatial Systems has become increasingly essential in concrete crack inspection. However, existing methods often lacks adaptability to diverse scenarios, exhibits limited robustness in image-based approaches, and struggles with curved or complex geometries. To address these limitations, an innovative framework for two-dimensional (2D) crack detection, three-dimensional (3D) reconstruction, and 3D automatic crack measurement was proposed by integrating computer vision technologies and multi-modal Simultaneous localization and mapping (SLAM) in this study. Firstly, building on a base DeepLabv3+ segmentation model, and incorporating specific refinements utilizing foundation model Segment Anything Model (SAM), we developed a crack segmentation method with strong generalization across unfamiliar scenarios, enabling the generation of precise 2D crack masks. To enhance the accuracy and robustness of 3D reconstruction, Light Detection and Ranging (LiDAR) point clouds were utilized together with image data and segmentation masks. By leveraging both image- and LiDAR-SLAM, we developed a multi-frame and multi-modal fusion framework that produces dense, colorized point clouds, effectively capturing crack semantics at a 3D real-world scale. Furthermore, the crack geometric attributions were measured automatically and directly within 3D dense point cloud space, surpassing the limitations of conventional 2D image-based measurements. This advancement makes the method suitable for structural components with curved and complex 3D geometries. Experimental results across various concrete structures highlight the significant improvements and unique advantages of the proposed method, demonstrating its effectiveness, accuracy, and robustness in real-world applications.