arXiv:2606.08736v1 Announce Type: new Abstract: We study a capability the dominant paradigm in synthetic tabular data does not provide: exact satisfaction of a declared analytical outcome with no source data. Imitation methods (copulas, GANs, diffusion) learn a real distribution and sample from it, and are judged on fidelity to real data. A large, practical class of needs is different: generating data with no source data ("cold start") that reproduces a declared outcome (a revenue curve, a churn rate, a group share) across a relational schema. Off-the-shelf imitation tools offer no interface for such targets, and no sampler can hit an exact aggregate, because sampling has variance. On a real public dataset, off-the-shelf learned synthesizers trained on that very data miss the declared monthly aggregate by 74 to 86 percent; a per-period steelman cuts the miss to about 19 percent and still cannot reach 0; a closed-form generator reaches exactly 0. We name this task outcome-conformant synthesis, argue its evaluation axis is conformance rather than fidelity, and show the two axes are orthogonal. We contribute: (1) a formal account showing a widely-used family of exact-aggregate generators is exactly conditional-sum sampling of a Gamma population (via Lukacs' characterization), with closed-form exactness, a closed-form marginal CV, and scale-invariance; a controlled experiment maps the boundary, enforcing the exact aggregate costs at most 0.006 in 1-Wasserstein distance to an arbitrary external marginal, the rest being shape-family mismatch; (2) SpecBench, to our knowledge the first benchmark to measure conformance to analytical outcomes for cold-start relational synthesis; and (3) a closed-form, deterministic reference system. Exact aggregation alone is trivial; the contribution is conformance jointly with closed-form marginals, integrity, determinism, and zero source data. We concede fidelity to imitation where real data exists.
Science Journals
arXiv:2606.08793v1 Announce Type: new Abstract: The quality of software engineering is still under a challenge due to disjointed processes between requirements, testing, and production, which hinders the opportunity to implement quality strategies in consecutive releases. Existing approaches tend to be fixed-model or single-optimization approaches and lack production feedback learning mechanisms. The paper at hand proposes a closed-loop reference architecture of continuous software quality intelligence with AI enhancements. The model synthesizes requirement feature mining, risk-based test prioritization, defect prediction, and production incident analysis as an element of a feedback-based pipeline. A limited feedback learning model is introduced that is used to propagate the production signal-based on defect severity and incident impact- to the following release to ensure stability, and the time. The method is evaluated using a semi-synthetic test dataset of 4,500 requirements, 27,049 test cases, 13,089 defects and 7,841 incidents in six release cycles. The experimental results show that the proposed system reduces the defect leakage by 0.19 to 0.13, increases the effectiveness of the detection system to 0.72 to 0.84, and shortens the test execution by up to 35 percent compared to the non-adaptive baselines. The changes are stable release to release. The findings indicate that through the integration of feedback-based learning in a closed-loop architecture, it can be continued to enhance quality process, which offers practical foundation of adaptive quality engineering of software.
arXiv:2606.08807v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to provide automated feedback in introductory programming courses, yet empirical evidence from authentic classroom deployments comparing different feedback modalities remains limited. In this work, we present a large-scale classroom study in which AI-generated feedback was deployed through a randomized protocol in an introductory Python programming course. Students received one of three feedback conditions on incorrect submissions: natural language hints, AI-generated failing test cases, or no AI feedback. We release the resulting dataset, ProgFeed, which captures 6,693 submissions from 215 consenting students across 17 labs, including feedback conditions, execution-based performance measures, and fine-grained temporal information. Using this data, we analyze learning trajectories, feedback quality, and submission behavior over repeated attempts. We find that natural language feedback is significantly associated with higher completion rates and faster convergence to correct solutions. Test case feedback, by contrast, exhibits heterogeneous effects that depend critically on feedback validity. Our results suggest that the form of AI-generated feedback matters, and that evaluating feedback quality -- not just its presence -- is essential for understanding its pedagogical impact.
arXiv:2606.08817v1 Announce Type: new Abstract: We present a low-variance randomised numerical linear algebra approach for multi-query finite element systems arising from parametric elliptic partial differential equations with applications to digital twins and online model calibration. The method relies on Galerkin subspace projection for reducing the dimensionality, and then combines parameter-oblivious leverage-score Bernoulli sampling with a control variates scheme to yield a reduced-variance `forward' sketch and an invertible `inverse' sketch that are then fused to a single efficient regularised estimator. Effectively, this reduces the computational cost in computing the projected system of equations while preserving the structure, stability, and accuracy of the underlying FEM formulation. We derive probabilistic bounds for the sketching error, invertibility, and estimator variance, and then validate the method on large-scale example problems. The results show that when the parameter fields do not vary too sharply, the synergy of control variates together with the sketch fusion can largely offset the loss incurred by the sub-optimal parameter-oblivious sampling. In this regime, our method achieves substantial savings in time, memory, and communication while maintaining accuracy levels that are acceptable for scientific simulation.
arXiv:2606.08828v1 Announce Type: new Abstract: Human manipulation videos are a convenient and intuitive source for robot learning. However, directly transferring human dexterity to robots remains challenging due to perception errors and embodiment gap. To address this, we introduce Video2Sim2Real, a full-stack framework for autonomous skill acquisition from a single human manipulation video. Our framework first uses off-the-shelf foundation models to reconstruct a simulator-ready digital twin and extract robot and object motion priors. Rather than treating the extracted robot motion as a reliable reference throughout execution, our key idea is to recover and leverage the most fundamental sources of supervision from the demonstrated skill: We identify object-centric keyframes to optimize the corresponding robot configurations using object information from the simulator, and use these configurations as anchors that refine the robot motion such that it ultimately has the desired impact on the environment. To bridge the remaining sim-to-real gap, we introduce a sim-to-real strategy that decouples robustness to noisy and incomplete perception from variations in hand-object interaction dynamics. Specifically, we learn to recalibrate robot configurations from noisy real-world point clouds via IL, and leverage residual RL to perform local finger-level adaptations to ensure for robust and effective interactions. Finally, a collision-aware motion planning module enables spatial generalization to novel object configurations. Across several everyday manipulation tasks, Video2Sim2Real improves simulated task success, safety, and trajectory coherence over numerous baselines, and achieves better sim-to-real transfer than existing techniques. These results demonstrate a promising path toward autonomous dexterous skill acquisition from human videos.
arXiv:2606.08854v1 Announce Type: new Abstract: Standard Reinforcement Learning with Verifiable Rewards (RLVR) training allocates a fixed rollout budget to every query, without regard for what each query's difficulty means for the current policy. This leads to two symmetric failure modes: easy queries produce near-zero advantage because the policy already solves them, while unsolvable queries produce no signal because the policy never solves them. Both regimes waste training FLOPs without contributing to a learning gradient. We introduce sorted Group Policy Optimization (sGPO), a compute-efficient strategy that trades a small budget of inference FLOPs for a large reduction in wasted training FLOPs. The key insight is that cheap inference compute can serve as a single offline proxy for query difficulty. By generating a small batch of parallel samples per query under the initial policy, we obtain a model-aware empirical success rate. This motivates setting the training rollout group size to the inverse of this success rate, a practical rule that maximizes sample efficiency by extracting the most advantage per generated rollout. This single profiling pass simultaneously drives data filtering (removing trivial queries and sub-sampling unsolvable ones), adaptive group size allocation, and curriculum construction (scheduling queries from easy to hard). sGPO matches or exceeds baseline performance while reducing total training compute by a factor of three, with the upfront inference profiling cost included.
arXiv:2606.08855v1 Announce Type: new Abstract: This paper examines the limitations of fully digital and partially digital e-assessment approaches in summative examinations in higher education. The analysis focuses on the didactic narrowing caused by closed question formats and on organizational, technical, and legal constraints that become particularly relevant in large student cohorts. As an alternative, the paper proposes a hybrid e-assessment approach that retains paper-based, problem-oriented examination tasks while enabling semi-automated grading. Assessment-relevant intermediate results are encoded in a structured answer format, entered by students by hand, and subsequently captured from table fields. The central technical bottleneck is reliable recognition of handwritten characters under realistic examination conditions. Recent vision-capable large language models, combined with a two-pass validation principle and comparison against a solution key, can reduce misclassifications and thereby improve the validity, fairness, and scalability of summative assessment.
arXiv:2606.08895v1 Announce Type: new Abstract: We study finite-state finite-action Bayesian statistical decision problems. While exact error-exponent characterizations are known for several special cases, including hypothesis testing and hypothesis exclusion, the asymptotic behavior of the optimal Bayes regret is largely unknown for general decision problems. In this paper, we show that the optimal regret always decays exponentially fast and characterize its exact exponent for arbitrary loss functions. The exponent is given by the minimum multivariate Chernoff information over the minimal incompatible subsets of states, where an incompatible subset is a collection of states for which no single action is optimal for all states in the subset. Our result recovers the classical pairwise-minimum Chernoff exponent for symmetric multiple hypothesis testing and the multivariate Chernoff exponent for hypothesis exclusion, while also yielding, to the best of our knowledge, the first exact exponent characterization for list hypothesis testing.
arXiv:2606.08926v1 Announce Type: new Abstract: Knowledge graph completion (KGC) models are commonly evaluated using rank-based metrics such as MRR and Hits@K, despite different users often requiring different evaluation perspectives. In this demo, we present PROBE-Web, an interactive system for probing diverse evaluation landscapes for KGC models. PROBE-Web enables users to flexibly evaluate KGC models by adjusting two critical perspectives: (P1) predictive sharpness and (P2) popularity-bias robustness. Through a user-friendly GUI, users easily evaluate multiple KGC models and analyze their strengths and weaknesses. PROBE-Web provides four key functionalities: (1) conventional evaluation toolkit, (2) flexible perspective-aware evaluation, (3) explainable case studies, and (4) evaluation landscape exploration. We believe that PROBE-Web can help users better understand KGC models aligning with their objectives.
arXiv:2606.08979v1 Announce Type: new Abstract: Retrieving evidence pages from visually rich long documents is a key challenge in document question answering. Existing page-level visual retrievers operate under an independent matching paradigm: each page is scored in isolation based on query-page similarity. This paradigm can under-rank evidence pages whose signals are localized in fine-grained chunks or depend on document-internal associations. We propose EviProp, a retrieval method that recovers such pages via seeded relevance diffusion. EviProp models each document as a multimodal Chunk-Page graph with hierarchical, sequential, and similarity links. Given a query, it combines dense visual page priors with sparse chunk seeds, then runs Personalized PageRank to diffuse relevance over the graph. Experiments on MMLongBench-Doc and LongDocURL show consistent gains in evidence-page retrieval over independent visual retrieval and text-visual fusion baselines. Downstream QA results further show that improved retrieval translates into better answer accuracy, with negligible online retrieval overhead. Our code is released at https://github.com/Flyecnu/EviProp.
arXiv:2509.00462v4 Announce Type: replace Abstract: As artificial intelligence (AI) tools become widely adopted, large language models (LLMs) are increasingly involved on both sides of decision-making processes, ranging from hiring to content moderation. This dual adoption raises a critical question: do LLMs systematically favor content that resembles their own outputs? Prior research in computer science has identified self-preference bias -- the tendency of LLMs to favor their own generated content -- but its real-world implications have not been empirically evaluated. We focus on the hiring context, where job applicants often rely on LLMs to refine resumes, while employers deploy them to screen those same resumes. Using a large-scale controlled resume correspondence experiment, we find that LLMs consistently prefer resumes generated by themselves over those written by humans or produced by alternative models, even when content quality is controlled. The bias against human-written resumes is particularly substantial, with self-preference bias ranging from 67% to 82% across major commercial and open-source models. To assess labor market impact, we simulate realistic hiring pipelines across 24 occupations. These simulations show that candidates using the same LLM as the evaluator are 23% to 60% more likely to be shortlisted than equally qualified applicants submitting human-written resumes, with the largest disadvantages observed in business-related fields such as sales and accounting. We further demonstrate that this bias can be reduced by more than 50% through simple interventions targeting LLMs' self-recognition capabilities. These findings highlight an emerging but previously overlooked risk in AI-assisted decision making and call for expanded frameworks of AI fairness that address not only demographic-based disparities, but also biases in AI-AI interactions.
arXiv:2606.09006v1 Announce Type: new Abstract: Both digital economy and digital technology researchers increasingly recognize the need to better address the role that artificial intelligence (AI) plays in shaping the evolution of the environmental, social and governance aspects of development. It appears that sustainability and AI research converge on the features of wicked problems that are complex, interconnected and dynamic. Building off such convergence, this article aims to map out the necessary, challenging, and promising intersections by providing an overview of the state of art research. Based on 541 bibliographic data collected from the Web of Science (WoS) database, the findings reveal the increasingly central body of work on green and sustainable science and technology in bridging various disciplines, main journals and key topics and concepts. The findings reveal how such interactions can be necessary, challenging, and promising. The article concludes with few general arguments regarding how to diversify and expand the community of practice regarding AI for sustainable development, especially in the areas of expected AI application areas and institutions.
arXiv:2509.17446v4 Announce Type: replace Abstract: Multimodal intent recognition (MMIR) suffers from weak semantic grounding and poor robustness under noisy or rare-class conditions. We propose MVCL-DAF++, which extends MVCL-DAF with two key modules: (1) Prototype-aware contrastive alignment, aligning instances to class-level prototypes to enhance semantic consistency; and (2) Coarse-to-fine attention fusion, integrating global modality summaries with token-level features for hierarchical cross-modal interaction. On MIntRec and MIntRec2.0, MVCL-DAF++ achieves new state-of-the-art results, improving rare-class recognition by +1.05\% and +4.18\% WF1, respectively. These results demonstrate the effectiveness of prototype-guided learning and coarse-to-fine fusion for robust multimodal understanding. The source code is available at https://github.com/chr1s623/MVCL-DAF-PlusPlus.
arXiv:2606.09178v1 Announce Type: new Abstract: Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target languages - an approach that converts surface-level linguistic form while failing to reflect the cultural context embedded in threat scenarios, social norms, and legal frameworks. We construct paired DT and culturally-adapted (CA) datasets via 1:1 seed matching for four languages - Korean (KO), Japanese (JA), Thai (TH), and Khmer (KM) - and compare Attack Success Rate (ASR) and Cultural Realism scores across four open-source LLM. CA prompts yield Delta-ASR > 0 across all 16 language x model combinations (mean +9.3 pp), and DT-based evaluation underestimates risk in 44 of 48 category x language combinations. Language-level analysis reveals that the distribution of threat forms is heterogeneous across languages. Cultural Realism analysis further shows that DT Cultural Depth (C3) scores remain consistently below 1.0 out of 3.0 across all four languages (mean 0.17), whereas CA scores reach up to 2.51, indicating that direct translation produces inputs systematically divergent from those encountered in real-world multicultural settings. These findings demonstrate that adapting benchmarks to language-specific cultural contexts - rather than relying on linguistic translation alone - is necessary for valid multilingual LLM safety evaluation.
arXiv:2606.09188v1 Announce Type: new Abstract: Bearing-only target localization is a fundamental problem in optical measurement and finds extensive applications in unmanned aerial vehicle (UAV) technology. Effective trajectory planning establishes favorable observation geometries, thereby enhancing the target localization accuracy of bearing-only UAV systems. This paper proposes an trajectory optimization method for unmanned aerial vehicles (UAVs) in bearing-only target localization scenarios. By leveraging the Fisher Information Matrix (FIM), the proposed approach dynamically integrates the geometric configuration and vehicle maneuverability into the optimization framework. Specifically, we introduce a spectrally-weighted FIM objective function that provides better gradient dynamics near degenerate configurations, enabling the planner to rapidly escape from poor observation conditions. For dual-UAV scenarios, an intersection angle sine term is introduced to optimize triangulation geometry by improving the sight-line intersection angle, thereby preventing trajectory aggregation. Furthermore, we propose an improved Particle Swarm Optimization (PSO) algorithm with motion model constraints and particle normalization to ensure the physical feasibility of the trajectory and enhance the compatibility with the objective functions. Simulation results demonstrate that the proposed method reduces the median localization error by 99.21% compared to conventional FIM-based approaches in single-UAV scenarios, and achieves a 69.70% improvement for dual-UAV configurations, exhibits superior performance in long-duration bearing-only target localization of maneuverability targets at extended ranges.
arXiv:2606.09191v1 Announce Type: new Abstract: We prove that $\rho\text{-}\mathrm{NPTS}_{\mathrm{SG}}$, an anchor-free nonparametric Thompson Sampling algorithm for risk-averse bandits, achieves regret matching the instance-dependent lower bound to leading order in $\log n$, establishing it as asymptotically optimal for any continuous risk functional $\rho$ (CVaR, mean-variance, Sharpe ratio, distortion risk measures, and more) on the class of distributions with bounded density and sub-Gaussian tails, including Gaussian arms. Both this result and its bounded-support counterpart require only continuity of $\rho$: strictly weaker than the dominance condition of prior parametric Thompson Sampling results, and strictly weaker than the Lipschitz condition of UCB-type algorithms, yielding the first instance-optimal guarantees for non-Lipschitz functionals such as the Sharpe ratio without parametric reward assumptions. The bounded-support case is developed first as a stepping stone sharing the same proof structure. The key technical contributions are a discretisation lemma (bounded support) and a truncated discretisation lemma (sub-Gaussian tails), each projecting the growing-alphabet Dirichlet posterior onto a fixed grid via the Dirichlet aggregation property, holding all polynomial prefactors at fixed degree independent of sample size and breaking the super-exponential barrier that blocked prior proofs.
arXiv:2606.09423v1 Announce Type: new Abstract: Monochromators are routinely used in Transmission Electron Microscopy and Electron Energy Loss Spectroscopy, to improve both spatial and energy resolution. State-of-the-art monochromators, however, are complex instruments that typically require additional electron optical correctors, limiting their implementation to the high-end, most expensive microscopes. Miniaturized monochromation relying on purely electrostatic fringe fields has recently been proposed as a means to realize a simpler and thereby more cost-effective and easier to operate high-resolution monochromator. Here, we present a design for such a compact, fully electrostatic fringe-field based monochromator. Our design consists of a superposition of an Einzel lens with a series of electrostatic deflectors and is entirely based on dimensions that can be realized with MEMS fabrication technology. Thanks to mild mechanical and electrostatic potential tolerances, the MEMS-fabricated electrodes can be passively aligned and only need seven regular power supplies. We present an analysis of spectral broadening due to diffraction in our monochromator design as well as particle simulations including stochastic Coulomb interactions. This analysis shows that our design can achieve a resolution of 19 meV while maintaining 128 pA of beam current and thus potentially achieve energy filtering comparable to state-of-the-art monochromators. Our MEMS monochromator could therefore bring the application of energy filtering into the domain of SEM and specifically allow higher resolution imaging in chromatic-aberration dominated low-voltage SEM.
arXiv:2606.09424v1 Announce Type: new Abstract: Social robots must interact robustly not only with users assumed by speech-centered systems but also with diverse users whose communication relies on different modalities, e.g., sign language. One important capability gap is predictive turn-taking with signing users. Although Voice Activity Projection (VAP) has been successfully used to model future voice activity in spoken interaction, it remains unclear whether the framework transfers to sign language interaction. This paper presents an initial transfer study of adapting a VAP architecture to dyadic sign language interaction. Using interaction recordings from the Public DGS Corpus, we derive binary signing activity streams from lexical sign annotations and formulate proxy tasks for turn-taking prediction. The model uses pose-derived hand, eye-region, and mouth-region features extracted for each signer. The results show that SHIFT/HOLD prediction is promising, especially with hand cues, while SHIFT-prediction remains difficult. These findings provide initial evidence for both the promise and the current limitations of transferring predictive turn-taking models from spoken interaction to sign language interaction. Predictive modeling of sign language interaction still requires sign-language-specific event definitions that go beyond speech-derived categories.
arXiv:2606.09428v1 Announce Type: new Abstract: Effective crisis response requires spatially grounded communication that bridges linguistic guidance of civilians with the physical environment, accounting for structural bottlenecks, evolving threats, and agent-specific contexts. Yet, current NLP research in crisis communication remains mainly limited to static, text-only classification settings, overlooking the critical communicative role of AI operators in dynamic, embodied scenarios. We address this gap with a novel benchmarking framework for evaluating Vision-Language Models (VLMs) tasked with guiding civilian agents through simulated evacuations. We test two communication strategies (narrowcast vs. broadcast), two environment representations (visual vs. graph-based), and two threat behaviors (static vs. moving) across nine maps of varying structural complexity. Our results show that Narrowcast consistently reduces civilian Fail rates compared to Broadcast across all difficulty levels. Guidance quality depends heavily on how the VLM operator represents the world: the visual modality drives performance, while adding an adjacency graph is model-dependent and often harmful. Moving threats raise Fail rates across all conditions as communication must continuously adapt over time. Together, these findings show that deploying VLMs as AI operators in evacuation scenarios remains a non-trivial challenge, where the choice of communication strategy and input representation can directly determine the success or failure of the intervention.
arXiv:2606.09432v1 Announce Type: new Abstract: Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies. Graph neural networks (GNNs) provide a natural representation but typically rely on autoregressive rollouts and treat spatial and temporal dynamics separately, leading to error accumulation over long horizons. Existing approaches also focus on local interactions and short temporal contexts, limiting their ability to capture multi-hop dependencies and global structure. We introduce the Graph Mamba Operator (GraMO), a latent-space simulator that integrates state-space models with graph-based interaction learning. In contrast to prior work that sequences nodes or applies spatial and temporal updates in separate stages, GraMO couples graph-based interactions and temporal state updates within a single recurrence. The update is linear in the latent state, with input-dependent coefficients that adapt across regimes. We evaluate GraMO on N-body systems, motion capture, and robotics datasets, achieving the lowest error across benchmarks and the largest gains in long-horizon prediction.
arXiv:2606.09490v1 Announce Type: new Abstract: In the presence of stratification, turbulent flows exhibit intermittency not only at small scales but also at large scales, comparable to the mean flow, as observed in the atmosphere and oceans. We study such flows through a large parametric exploration using direct numerical simulations of the Boussinesq equations with different forcing types. We examine two Prandtl numbers (1 and 6) and vary the Froude number ($Fr$) over a range of geophysical interest values, $0.01\le Fr \le 1$, corresponding to a variation in terms of the buoyancy Reynolds number ($R_{IB}$) of $0.06\le R_{IB} \le 2300$. We analyze the dependence on $R_{IB}$ of the buoyancy flux ($B_f$), the mixing efficiency, the shear parameters, and the vertical momentum flux. Strongly non-Gaussian tails in the spatio-temporal distribution of the $B_f$ are observed, with kurtosis reaching $\approx 10^2$, indicating the potential for stratified geophysical flows to be characterized by highly variable transport properties along the direction of gravity even under stable stratification. This is associated with long-time intermittent behavior of vertical velocity and temperature at large scale, which produces local turbulence and enhances dissipation and transport. We present evidence that the skewness of $B_f$ increases with $R_{IB}$ as a power-law and saturates in the passive-scalar limit. We also show that the domain-averaged $B_f$ exhibits two distinct trends: logarithmic growth with $R_{IB}$ and approach to a small offset as stratification strengthens. A simple model for the temporal evolution of energy and $B_f$ indicates that the defect between vertical and potential energy drives strong $B_f$ events. This trend directly leads to convective instabilities, the formation of two-dimensional and three-dimensional eddies, and rapid dissipation on a turnover timescale, allowing the energetic cycle to restart-also occurring in bursts.
arXiv:2606.09600v1 Announce Type: new Abstract: Covering codes in finite Hamming spaces ask for small sets of words whose Hamming balls cover the whole space. This paper presents a Lean 4 formalization of the elementary theory of q-ary covering codes, centered on certificate predicates for upper bounds, lower bounds, and exact covering numbers $K_q(n,r)$. The formalization proves the q-ary Hamming-ball volume formula, the sphere-covering lower bound, elementary exact cases, product and relation rules, and selected small exact certificates. It also demonstrates an end-to-end workflow for checking explicit upper bounds transcribed from van Laarhoven et al. (1989). The accompanying database is proof-carrying: stored bounds have traces that replay to Lean proofs of the corresponding upper- or lower-bound predicates. The contribution is not new record bounds or a reproduction of known tables, but a reusable, auditable foundation for machine-checked covering-code certificates.
arXiv:2512.15422v2 Announce Type: replace Abstract: Ensuring the safety and reliability of Automated Driving Systems (ADS) remains a critical challenge, as traditional verification methods such as large-scale on-road testing are prohibitively costly and time-consuming.To address this,scenario-based testing has emerged as a scalable and efficient alternative,yet existing surveys provide only partial coverage of recent methodological and technological advances.This review systematically analyzes 31 primary studies,and 10 surveys identified through a comprehensive search spanning 2015~2025;however,the in-depth methodological synthesis and comparative evaluation focus primarily on recent frameworks(2023~2025),reflecting the surge of Artificial Intelligent(AI)-assisted and multimodal approaches in this period.Traditional approaches rely on expert knowledge,ontologies,and naturalistic driving or accident data,while recent developments leverage generative models,including large language models,generative adversarial networks,diffusion models,and reinforcement learning frameworks,to synthesize diverse and safety-critical scenarios.Our synthesis identifies three persistent gaps:the absence of standardized evaluation metrics,limited integration of ethical and human factors,and insufficient coverage of multimodal and Operational Design Domain (ODD)-specific scenarios.To address these challenges,this review contributes a refined taxonomy that incorporates multimodal extensions,an ethical and safety checklist for responsible scenario design,and an ODD coverage map with a scenario-difficulty schema to enable transparent benchmarking.Collectively,these contributions provide methodological clarity for researchers and practical guidance for industry,supporting reproducible evaluation and accelerating the safe deployment of higher-level ADS.
arXiv:2606.09612v1 Announce Type: new Abstract: Controlling product selectivity in plasmonic catalysis, particularly in CO2 reduction (CO2R), remains a central unsolved challenge with direct implications for light-driven fuel and chemical synthesis. Here, we deploy quantitative operando scanning photoelectrochemical microscopy (photo-SECM) to provide a direct demonstration that tuning photon energy switches CO2R selectivity through an electronically driven pathway. On plasmonic Au/p-GaN photocathodes, interband excitation (460-560 nm) drives selective CO production while intraband excitation (640-800 nm) favors H2 evolution. By maintaining constant absorbed power across wavelengths and confirming linear power dependence, we isolate the role of hot-carrier energy from photonic and photothermal contributions. Density functional theory calculations reveal that higher-energy interband excitation progressively increases the overlap between hot-electron-accessible states and the CO-producing intermediate, selectively promoting CO over formate, in excellent agreement with experiment. We further show that selectivity is geometrically gated by hot-carrier transport: sub-100 nm nanostructures sustain CO2R activity, while ~300 nm nanodisks suffer transport losses that suppress it, consistent with ab initio hot-carrier transport calculations. Together, these results establish photon energy, carrier transport, and nanostructure geometry as coupled design parameters for plasmonic CO2R selectivity, resolve a longstanding debate on the origin of plasmon-driven selectivity effects, and position photo-SECM as a broadly applicable operando platform for photo(electro)catalysis.
arXiv:2606.09615v1 Announce Type: new Abstract: Dexterous manipulation presents substantial challenges for imitation learning due to its high-dimensional action space and complex contact-rich dynamics. Policies trained purely from demonstrations often suffer from compounding errors during deployment and require large amounts of expert data to achieve reliable performance. To move beyond the limitations of demonstration data, in this work, we propose DexPIE, a post-training framework for dexterous policy improvement from experience collected through real-world deployment. First, DexPIE enables effective exploration coverage through a dexterous-hand-adapted intervention system and multi-stage DAgger-style data collection across initial and intermediate task stages, providing reliable supervision for accurate policy evaluation. To reduce temporal noise between post-training rollouts and demonstration data, we introduce asynchronous inference in the relative action space, which better aligns rollout data with demonstrated behavior and allows the critic to learn a value function induced by a more consistent underlying policy. Finally, DexPIE improves the policy through conditioning on a continuous optimality indicator, allowing the policy to leverage the quality of data in a more fine-grained manner. Across three challenging real-world dexterous manipulation tasks, DexPIE achieves a 37% improvement in success rate over the demonstration-based reference policy, outperforming all baseline methods and demonstrating stronger robustness. The source code and dataset will be made publicly available.