arXiv:2602.23263v2 Announce Type: replace-cross
Abstract: Context. Primordial magnetic fields (PMFs) generated in the early Universe might have left observable imprints on present-day large-scale structure. However, the spatial scales on which primordial signatures are able to survive the nonlinear processes that accompany structure formation remain unclear. Aims. The aim of this study is to investigate the evolution of the statistical properties of PMFs during the onset of gravitational collapse. Methods. We performed a suite of high-resolution direct numerical simulations of isothermal self-gravitating, magnetized gas clouds. By varying the viscosity, we probed different Reynolds-number regimes and follow the coupled evolution of gravitational collapse and magnetohydrodynamic turbulence. Results. At sufficiently high Reynolds numbers, turbulence generated during collapse triggers the onset of a small-scale dynamo, which amplifies magnetic energy below the Jeans scale and modifies the magnetic energy spectrum significantly. The question of whether dynamo amplification dominates the magnetic field evolution is determined by the competition between the dynamo growth time and the free-fall time. Conclusions. Our results highlight the importance of resolving the Jeans scale and the associated turbulent inertial range in cosmological magnetohydrodynamic (MHD) simulations to accurately capture the interplay between gravitational compression and dynamo amplification and to assess which structures retain memory of primordial fields.
Science Journals
arXiv:2602.19799v2 Announce Type: replace-cross
Abstract: Despite recent algorithmic advances, we still lack principled ways to leverage the well-documented rescaling symmetries in ReLU neural network parameters. While two properly rescaled weights implement the same function, the training dynamics can be dramatically different. To offer a fresh perspective on exploiting this phenomenon, we build on the recent path-lifting framework, which provides a compact factorization of ReLU networks. We introduce a geometrically motivated criterion to rescale neural network parameters which minimization leads to a conditioning strategy that aligns a kernel in the path-lifting space with a chosen reference. We derive an efficient algorithm to perform this alignment. In the context of random network initialization, we analyze how the architecture and the initialization scale jointly impact the output of the proposed method. Numerical experiments illustrate its potential to speed up training.
arXiv:2602.15202v2 Announce Type: replace-cross
Abstract: We present an algebraic algorithm for quantum state tomography that leverages measurements of certain observables to estimate structured entries of the underlying density matrix. Under low-rank assumptions, the remaining entries can be obtained solely using standard numerical linear algebra operations. The proposed algebraic matrix completion framework applies to a broad class of generic, low-rank mixed quantum states and, compared with state-of-the-art methods, is computationally efficient while providing deterministic recovery guarantees.
arXiv:2602.11406v2 Announce Type: replace-cross
Abstract: We consider an online learning problem in environments with multiple change points. In contrast to the single change point problem that is widely studied using classical "high confidence" detection schemes, the multiple change point environment presents new learning-theoretic and algorithmic challenges. Specifically, we show that classical methods may exhibit catastrophic failure (high regret) due to a phenomenon we refer to as endogenous confounding. To overcome this, we propose a new class of learning algorithms dubbed Anytime Tracking CUSUM (ATC). These are horizon-free online algorithms that implement a selective detection principle, balancing the need to ignore "small" (hard-to-detect) shifts, while reacting "quickly" to significant ones. We prove that the performance of a properly tuned ATC algorithm is nearly minimax-optimal; its regret is guaranteed to closely match a novel information-theoretic lower bound on the achievable performance of any learning algorithm in the multiple change point problem. Experiments on synthetic as well as real-world data validate the aforementioned theoretical findings.
arXiv:2602.11189v2 Announce Type: replace-cross
Abstract: Modeling peptide cyclization is critical for the virtual screening of candidate peptides with desirable physical and pharmaceutical properties. This task is challenging because a cyclic peptide often exhibits diverse, ring-shaped conformations, which cannot be well captured by deterministic prediction models derived from linear peptide folding. In this study, we propose MuCO (Multi-stage Conformation Optimization), a generative peptide cyclization method that models the distribution of cyclic peptide conformations conditioned on the corresponding linear peptide. In principle, MuCO decouples the peptide cyclization task into three stages: topology-aware backbone design, generative side-chain packing, and physics-aware all-atom optimization, thereby generating and optimizing conformations of cyclic peptides in a coarse-to-fine manner. This multi-stage framework enables an efficient parallel sampling strategy for conformation generation and allows for rapid exploration of diverse, low-energy conformations. Experiments on the large-scale CPSea dataset demonstrate that MuCO significantly and consistently outperforms state-of-the-art methods in physical stability, structural diversity, secondary structure recovery, and computational efficiency, making it a promising computational tool for exploring and designing cyclic peptides. The demo of the proposed method can be found at https://github.com/mianqiu00/MuCO.
arXiv:2601.21868v2 Announce Type: replace-cross
Abstract: Understanding the stability and long-time behavior of generative models is a fundamental problem in modern machine learning. This paper provides quantitative bounds on the sampling error of score-based generative models by leveraging stability and forgetting properties of the Markov chain associated with the reverse-time dynamics. Under weak assumptions, we provide the two structural properties to ensure the propagation of initialization and discretization errors of the backward process: a Lyapunov drift condition and a Doeblin-type minorization condition. A practical consequence is quantitative stability of the sampling procedure, as the reverse diffusion dynamics induces a contraction mechanism along the sampling trajectory. Our results clarify the role of stochastic dynamics in score-based models and provide a principled framework for analyzing propagation of errors in such approaches.
arXiv:2601.07144v3 Announce Type: replace-cross
Abstract: Ensuring fairness in matching algorithms is a key challenge in allocating scarce resources and positions. Focusing on Optimal Transport (OT), we introduce a novel notion of group fairness requiring that the probability of matching two individuals from any two given groups in the OT plan satisfies a predefined target. We first propose a modified Sinkhorn algorithm to compute perfectly fair transport plans efficiently. Since exact fairness can significantly degrade matching quality in practice, we then develop two relaxation strategies. The first one involves solving a penalized OT problem, for which we derive novel finite-sample complexity guarantees. Our second strategy leverages bilevel optimization to learn a ground cost that induces a fair OT solution, and we establish a bound on the deviation of fairness when matching unseen data. Finally, we present empirical results illustrating the performance of our approaches and the trade-off between fairness and transport cost.
arXiv:2105.10184v3 Announce Type: replace
Abstract: Inspired by the famous Target Set Selection problem, we propose a new discrete model to simultaneously spread two opinions within a social network and perform an initial study of its complexity. Here, we are given a social network, a seed-set of agents for each opinion, two thresholds for each agent, a budget, and a number of rounds. The first threshold represents the willingness of an agent to adopt an opinion if the agent has no opinion at all, while the second threshold states the willingness to acquire a second opinion if the agent already has one. The goal is to add at most budget-many agents to the initial seed-sets such that the process started with these extended seed-sets stabilizes within the given number of rounds, with each agent having either both opinions or none. That is, our goal is to ensure that the spread of opinions is balanced.
We show that the problem is NP-hard, and thus we study the problem from the perspective of parameterized complexity. In particular, we show that the problem is FPT when parameterized by the number of rounds, the maximum threshold, and the treewidth combined. This algorithm also applies to the combined parameter, the treedepth and the maximum threshold. Finally, we show that the problem is FPT when parameterized by the vertex cover number, the $3$-path vertex cover number, or the vertex integrity of the input network alone. To complement our tractability results, we show that the problem is W[1]-hard with respect to a) the sizes of the initial seed-sets and the feedback-vertex set number combined, even if all thresholds are bounded by a constant, and b) the budget, the 4-path vertex cover number, and the feedback-vertex set number combined, even if every activation process stabilizes in at most 4 rounds.
arXiv:2512.06553v2 Announce Type: replace-cross
Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of large language models (LLMs). Our work is motivated by the rapid emergence of numerous new LLM families with distinct architectures and training strategies, evaluated on an increasing number of benchmarks. This heterogeneity makes a single global scaling curve inadequate for capturing how performance varies across families and benchmarks. To address this, we propose a latent variable modeling framework in which each LLM family is associated with a latent variable that captures the common underlying features in that family. An LLM's performance on different benchmarks is then driven by its latent skills, which are jointly determined by the latent variable and the model's own observable features. We develop an estimation procedure for this latent variable model and establish its statistical properties. We also design efficient numerical algorithms that support estimation and various downstream tasks. Empirically, we evaluate the approach on 12 widely used benchmarks from the Open LLM Leaderboard (v1/v2).
arXiv:2511.20075v4 Announce Type: replace-cross
Abstract: The pinch-off of bubbles in viscoelastic liquids is a fundamental process that has received little attention compared to viscoelastic drop pinch-off. While these processes exhibit qualitative similarities, the dynamics of the pinch-off process are significantly different. When a drop of a dilute polymer solution pinches off, a thread is known to develop that prevents breakup due the diverging polymer stresses. Conversely, our experiments reveal that this thread is absent for bubble pinch-off in dilute polymer solutions. We show that a thread becomes apparent only for high polymer concentrations, where the pinch-off dynamics become very sensitive to the size of the needle from which the bubble detaches. The experiments are complemented by numerical simulations and analytical modeling using the Oldroyd-B model, which capture the dilute regime. The model shows that polymer stresses are still singular during bubble pinch-off, but the divergence is much weaker as compared to drop pinch-off. This explains why, in contrast to droplets, viscoelastic bubble-threads do not appear for dilute suspensions but require large polymer concentrations
arXiv:2511.03000v2 Announce Type: replace-cross
Abstract: Comparing clusterings is central to evaluating unsupervised models, yet the many existing similarity measures can produce widely divergent, sometimes contradictory, evaluations. Clustering similarity measures are typically organized into two principal families, pair-counting and information-theoretic, reflecting whether they quantify agreement through element pairs or aggregate information across full cluster contingency tables. Prior work has uncovered parallels between these families and applied empirical normalization or chance-correction schemes, but their deeper analytical connection remains only partially understood. Here, we develop an analytical framework that unifies these families through two complementary perspectives. First, both families are expressed as weighted expansions of observed versus expected co-occurrences, with pair-counting arising as a quadratic, low-order approximation and information-theoretic measures as higher-order, frequency-weighted extensions. Second, we generalize pair-counting to k-tuple agreement and show that information-theoretic measures can be viewed as systematically accumulating higher-order co-assignment structure beyond the pairwise level. We illustrate the approaches analytically for the Rand index and Mutual Information, and show how other indices in each family emerge as natural extensions. Together, these views clarify when and why the two regimes diverge, relating their sensitivities directly to weighting and approximation order, and provide a principled basis for selecting, interpreting, and extending clustering similarity measures across applications.
arXiv:2509.23385v5 Announce Type: replace-cross
Abstract: Simulation-based inference (SBI) is transforming experimental sciences by enabling parameter estimation in complex non-linear models from simulated data. A persistent challenge, however, is model misspecification. In a Bayesian setting, targeting posterior distributions, errors may arise from the simulator, the noise or prior modelling. These model components are only approximations of reality, and severe mismatches can yield biased or overconfident posteriors. We address this issue by introducing Flow Matching Corrected Posterior Estimation (FMCPE), a framework that leverages the flow matching paradigm to refine simulation-trained posterior estimators using a small set of calibration samples. Our approach proceeds in two stages: first, a posterior approximator is trained on abundant simulated data; second, flow matching transports its predictions toward the true posterior supported by calibration observations. We rely on the later to guide the correction, without requiring explicit knowledge of the misspecification form or of which model components are affected. This design enables FMCPE to combine the scalability of SBI with robustness to distributional shift. Across synthetic benchmarks and real-world datasets, we show that our proposal consistently mitigates the effects of misspecification, delivering improved inference accuracy and uncertainty quantification compared to standard SBI baselines, while remaining computationally efficient.
arXiv:2509.21597v2 Announce Type: replace-cross
Abstract: With the prevalence of artificial intelligence (AI)-generated content, such as audio deepfakes, a large body of recent work has focused on developing deepfake detection techniques. However, existing benchmarks employ a narrow set of datasets, leaving detector generalization to real-world conditions uncertain. In this paper, we systematically review 31 existing audio deepfake datasets and present an open-source benchmarking toolkit called AUDDT (https://github.com/MuSAELab/AUDDT). The goal of this toolkit is to automate the evaluation of pretrained detectors across a wide range of speech and non-speech audio datasets, giving users direct feedback on the advantages and shortcomings of their deepfake detectors under diverse manipulation types and recording conditions. We start by showcasing the usage of the developed toolkit, the composition of our benchmark, and the breakdown of different deepfake subgroups. Next, we highlight how AUDDT differs from existing benchmarking efforts by enabling large-scale, diverse evaluation across modern spoofing methods and richer attribute-level analysis through comprehensive metadata annotation. Using a widely adopted pretrained deepfake detector, we present in- and out-of-domain detection results, revealing notable performance variability across different conditions and audio manipulation types. Lastly, we also analyze the limitations of these existing datasets and their gaps relative to practical deployment scenarios.
arXiv:2506.23546v2 Announce Type: replace-cross
Abstract: Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used to find them for generative learning of a real dataset. We call this type of generative model a neural Langevin machine, which derives an asymmetric and firing-rate-speed adjusted learning rule requiring only local neural signals, thereby bearing biological relevance in terms of local predictive learning. An interesting out-of-equilibrium regime of the generative process is revealed, together with a memorization-to-generalization transition with increasing training data size. The neuro-inspired machine can also realize a continuous exploration of the phase space for different kinds of generative images and can denoise a corrupted image as well.
arXiv:2503.18721v3 Announce Type: replace-cross
Abstract: Identification of joint dependence among several random vectors plays an important role in many statistical applications, where the data may contain sensitive or confidential information. In this paper, we consider the $d$-variable Hilbert-Schmidt independence criterion (dHSIC) in the context of differential privacy. Given that the limiting distribution of the empirical estimate of dHSIC is a complicated Gaussian chaos, constructing tests in the non-private regime is typically based on permutation and bootstrap methods. To detect joint dependence under privacy constraints, we propose a dHSIC-based testing procedure employing a differentially private permutation methodology. We show that our method enjoys privacy guarantees, a valid level, and pointwise consistency, whereas the bootstrap counterpart suffers from inconsistent power. We further investigate the uniform power of the proposed test under the dHSIC and $L_2$ metrics, showing that the proposed test attains the minimax optimal power across different privacy regimes. As a byproduct, we show that the non-private permutation dHSIC test proposed in Pfister et al. (2018) is a special case of our differentially private permutation test, and our results also establish its pointwise and uniform power--thus resolving an open problem from that work. Both numerical simulations and real data analysis in causal inference suggest that our proposed test performs well empirically.
arXiv:2502.05349v2 Announce Type: replace-cross
Abstract: Two-stage stochastic programs (2SPs) are widely used for decision-making under uncertainty, but their practical deployment is often limited by the large number of scenarios needed to approximate the conditional distribution of uncertain outcomes. We study contextual scenario generation: given contextual information, learn to produce a small, user-specified set of surrogate scenarios that, when used as input into the 2SP, lead to high-quality 2SP decisions. Existing scenario generation methods either ignore contextual information or are computationally burdensome in this setting. We propose contextual scenario generation (CSG), which learns a mapping from context to a set of surrogate scenarios. We develop two complementary methodologies: (i) a distributional approach that learns a mapping from context to scenarios by minimizing a kernel-based distance to the conditional distribution, and (ii) a task-based approach that selects the mapping to optimize decision quality via differentiating through a learned surrogate of the downstream 2SP objective. Both approaches are broadly applicable and require only repeated solution of the underlying subproblems and 2SPs defined on the generated scenarios. We provide finite-sample generalization guarantees and demonstrate strong empirical performance across multiple 2SP classes.
arXiv:2512.05277v4 Announce Type: replace
Abstract: Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances. Reliable temporal understanding is essential for such agents to anticipate events, attribute causes, and act safely in dynamic environments, yet this remains a significant challenge even for state-of-the-art (SoTA) VLMs. Prior video benchmarks have emphasized other content (sports, cooking, etc.), yet no existing benchmark focuses exclusively on temporal understanding for both short- and long-form AD footage. To fill this gap, we present the Temporal Understanding in Autonomous Driving (TAD) benchmark, comprising nearly 6000 question-answer (QA) pairs across 7 tasks, and evaluate 9 closed- and open-source generalist as well as AD-specialist models. Current SoTA models perform substantially below human accuracy on TAD. To improve the temporal reasoning of VLM-based driving agents, we propose two novel training-free solutions: Scene-CoT, which uses Chain-of-Thought (CoT) reasoning, and TCogMap, which incorporates an ego-centric temporal cognitive map produced by a trajectory-analysis module that operates as an agentic tool around the VLM. Integrated with existing VLMs, our methods improve average accuracy on TAD by up to $17.72\%$ and by up to $10.35\%$ on STSBench. By introducing TAD, benchmarking SoTA models, and proposing effective enhancements, this work aims to catalyze further progress on temporal understanding for agentic AD systems operating in the wild. The benchmark and evaluation code are available at ${\href{https://huggingface.co/datasets/vbdai/TAD}{\text{Hugging Face}}}$ and ${\href{https://github.com/vbdi/tad_bench}{\text{GitHub}}}$, respectively.
arXiv:2606.03402v2 Announce Type: replace
Abstract: Audio-driven human motion video generation aims to synthesize realistic and temporally coherent human animations from a single static image, with applications in talking-head synthesis, co-speech gesture generation, and dynamic presentations. Moving beyond conventional keypoint-based methods that often struggle to capture subtle motion dynamics, We propose a novel implicit-motion framework for generating realistic and temporally coherent human motion videos from a single static image and audio. Our approach uses a two-stage pipeline that decouples motion prediction from rendering. The first stage integrates appearance priors and hierarchical depth cues into a region-aware attention mechanism to model latent motion features. The second stage employs a Mamba-enhanced diffusion model to directly predict these features from audio and the source image, enabling unsupervised learning of fine-grained motion patterns. This decoupled architecture enhances flexibility and efficiency. Trained on a new 380-hour high-quality dataset, our method outperforms prior work across multiple public benchmarks and our collected data in accuracy, naturalness, and temporal coherence, setting a new state-of-the-art.
arXiv:2606.03393v2 Announce Type: replace
Abstract: We propose a novel diffusion model, Flicker-DDPM, which incorporates flicker (1/f) noise inspired by self-organized criticality (SOC), a widely observed phenomenon in natural systems. Unlike denoising diffusion probabilistic models (DDPMs), which employ isotropic white noise in the forward process, Flicker-DDPM adopts colored noise with power-law spectra to better match the spectral statistics of natural images, whose power spectra typically follow P(k) proportional to 1/k^{\alpha}. To this end, we develop a colored-noise module based on a spatial correlation kernel, {\sigma}(d) = (d + 1)^{-\eta}, and theoretically establish that adjusting {\eta} controls the spectral exponent {\alpha} of the generated 1/f{\alpha} noise, enabling adaptation to datasets with diverse spectral characteristics. On CIFAR-10, Flicker DDPM matches or surpasses the generation quality of a standard DDPM baseline using 3.33 times fewer sampling steps, with negligible additional computational cost per step. We further develop a frequency-domain linear theory demonstrating that spectrally matched colored noise linearizes the reverse trajectory, theoretically explaining the observed sampling acceleration.
arXiv:2606.03376v2 Announce Type: replace
Abstract: Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans, thereby addressing the hallucination issue. Despite its success, this paradigm has yet to specifically target the perceptual bottleneck in attended regions or address insufficient Visual Robustness against image degradation. Furthermore, existing preference pairs are often vision-agnostic and their inherently off-policy nature limits their effectiveness in guiding model learning. To address these challenges, we propose Perceptual Processing Direct Preference Optimization (P$^2$-DPO), a novel training paradigm in which the model generates and learns from its own preference pairs, thereby directly addressing the identified visual bottlenecks while inherently avoiding the issues of vision-agnostic and off-policy data. It introduces: (1) an on-policy preference pairs construction method targeting Focus-and-Enhance perception and Visual Robustness, and (2) a well-designed Calibration Loss to precisely align visual signals with the causal generation of text. Experimental results demonstrate that with a comparable amount of training data and cost, P$^2$-DPO outperforms strong baselines that rely on costly human feedback on benchmarks. Furthermore, evaluations on Attention Region Fidelity (ARF) and image degradation scenarios validate the effectiveness of P$^2$-DPO in addressing perceptual bottleneck in attended regions and improving Visual Robustness against degraded inputs.
arXiv:2606.03323v2 Announce Type: replace
Abstract: The rise of LLM-as-a-Service and other confidential cloud workloads demands cryptographic proof that user data is processed in a trusted, untampered environment. Existing solutions, notably Confidential Containers (CoCo), enforce a strict "one Pod per VM" model that attests only the Guest OS stack, leaving container-level identity unverified and incurring prohibitive per-VM resource overhead. We present dstack-capsule, a Kubernetes platform that enables Pod-level remote attestation on Intel TDX by allowing multiple Pods to share a single Confidential VM while each retains independent, hardware-backed proof of identity. Our key insight is a two-layer attestation architecture: static platform measurements are frozen in RTMR[3] via an irreversible privilege fuse, while dynamic Pod identities (pod_uid, pod_spec_hash, workload_id) are embedded in the TDX Quote's report_data field and signed by hardware on every request. dstack-capsule introduces (1) a Pod-level attestation protocol binding Pod spec digests to hardware-signed Quotes; (2) a privilege fuse mechanism that atomically transitions a node from setup mode to secure mode; (3) a multi-layer sandbox spanning storage, runtime, admission, API, and network isolation layers; and (4) a complete open-source implementation based on Kubernetes 1.32, Intel TDX, and Sysbox. We evaluate the security properties, attestation correctness, and performance characteristics of dstack-capsule, demonstrating that it achieves Pod-granularity verification without the resource overhead of per-VM isolation.
arXiv:2606.05080v1 Announce Type: new
Abstract: Scientific and engineering progress is fundamentally a long-horizon iterative process: proposing changes, running experiments, measuring outcomes, and continuously refining artifacts. Yet existing benchmarks for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons. To address this gap, we introduce AutoLab, a new benchmark for ultra long-horizon closed-loop optimization. AutoLab consists of 36 realistic, expert-curated tasks spanning four diverse domains: system optimization, puzzle & challenge, model development, and CUDA kernel optimization. Each task begins with a correct but deliberately suboptimal baseline and challenges agents to improve it within a strict wall-clock budget. Evaluating 17 state-of-the-art models reveals the dominant predictor of success is not the quality of an agent's initial attempt, but its persistence in repeatedly benchmarking, editing, and incorporating empirical feedback. While claude-opus-4.6 exhibits strong long-horizon optimization capabilities, most frontier models, including several proprietary ones, either terminate prematurely or exhaust their budgets with minimal progress. These results underscore the importance of time awareness and persistent iteration in autonomous agents. We open-source the full benchmark, evaluation harness, and task artifacts, to accelerate research toward truly capable long-horizon agents.
arXiv:2606.03307v2 Announce Type: replace
Abstract: Graph foundation models (GFMs) emerged as a dominant paradigm in graph representation learning by leveraging large-scale pre-training for cross-domain inference. However, the parameterized knowledge encoded within these models is insufficient to cope with distribution shifts, limiting their generalization ability. To mitigate this issue, retrieval-augmented generation (RAG) has been introduced to incorporate external knowledge at inference time. Nevertheless, existing RAG frameworks operating in Euclidean space suffer from a fundamental geometric limitation: the polynomial volume growth of Euclidean space is inherently mismatched with the tree-structured external knowledge bases. This mismatch leads to the loss of semantic granularity in retrieval and gives rise to the hubness phenomenon.To address this limitation, we propose a Hyperbolic Retrieval-Augmented Generation (HyRAG) framework designed to enhance the generalization capabilities of GFMs. Specifically, the introduced Hyperbolic Knowledge Indexing module retains the tree-like hierarchies of the external knowledge base by modeling them within hyperbolic space. The Multi-granularity Retrieval module then provides GFMs with the global semantic anchors and local semantic nuances through coarse-grained and fine-grained knowledge retrieval, respectively. Finally, the Dual-path Fusion module achieves effective knowledge integration for graph tasks at both the feature and structural levels. Experiments on multiple graph benchmarks demonstrate significant improvements in the zero-shot setting, highlighting the generalization of our method for robust GFMs inference.
arXiv:2606.04975v1 Announce Type: new
Abstract: The growing complexity of modern energy systems has led to the adoption of Smart Grid (SG) that use advanced communication technologies to facilitate efficient, reliable, secure, and sustainable energy operation and management. Unlike existing surveys that often treat grid and communication domains separately, this work rigorously quantifies service requirements for high-complexity emerging scenarios. It provides a comprehensive overview of SG architecture that integrates digital communication infrastructure with distributed energy resources (DERs), microgrids, energy storage systems, and cybersecurity frameworks. Furthermore, emerging SG use cases such as smart distributed voltage control, real-time fault detection and self-healing, smart and autonomous monitoring, and predictive maintenance are identified, and more importantly, service performance requirements associated with these use cases have been quantified. Additionally, key capabilities and emerging SG enablers of fifth-generation (5G) and sixth-generation (6G) networks are described. These capabilities and enablers include network slicing, edge computing, spectrum management, artificial intelligence (AI) driven optimization, digital twins, and Open-Radio Access Network (O-RAN). Finally, the paper discusses open challenges and future research directions for designing scalable, intelligent, and secure next-generation SG systems.
arXiv:2606.05058v1 Announce Type: new
Abstract: Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in isolation, and multi-modal, multi-task learning for CAD is hindered by the absence of a unified benchmark. To address this gap, we introduce UniCAD, a comprehensive benchmark for multi-modal CAD learning that covers point-to-CAD reconstruction, text/image-to-CAD generation, and CAD question answering across diverse input modalities. Alongside the benchmark, we present UniCAD-MLLM, a universal multi-modal large language model that ingests text, images, sketches, and point clouds and performs these heterogeneous tasks in an end-to-end fashion within a single framework. Extensive experiments on the UniCAD and Fusion360 benchmarks demonstrate that UniCAD-MLLM achieves state-of-the-art performance across all tasks, outperforming existing task-specific and multi-task baselines. We will release the dataset, code, and pretrained models to accelerate future research.