arXiv:2607.09297v1 Announce Type: new
Abstract: The problem of Optimal Power Flow (OPF) is central to the secure and economic operation of modern power systems. However, increasing renewable energy penetration, and decreasing system inertia pose significant challenges to conventional optimization-based OPF solvers. While machine learning approaches have demonstrated substantial computational speed-ups, purely data-driven methods often suffer from data dependency, limited generalization, and lack of guaranteed physical feasibility. This paper suggests a physics-informed neural network (PINN) framework for solving the OPF problem in renewable energy-dominated, low-inertia power systems. In contrast to conventional OPF formulations, the model explicitly incorporates a location-aware inertia constraint based on the concept of system inertia strength, which accounts for the electrical distance between generation units and disturbance locations. Simulation results on a 6 GW test system demonstrate high accuracy. The mean absolute error (MAE) for both the training and testing datasets is approximately 0.045% of the total system capacity. The findings demonstrate that the proposed PINN framework is capable of producing highly accurate OPF solutions while ensuring compliance with both physical laws and inertia-related constraints. Overall, the findings highlight the potential of physics-informed learning to enable secure, efficient, and computationally scalable OPF for future low-inertia power systems.
Science Journals
arXiv:2607.06654v2 Announce Type: replace-cross
Abstract: Penning ion traps as quantum platforms have primarily utilized global control and symmetric Dicke states for quantum simulation and sensing experiments. The introduction of local control greatly increases the power of the platform as a quantum simulator but is technically challenging due to the rapid rotation of the ion crystals. Here we use an ultraviolet-compatible spatial light modulator (SLM) to imprint programmable AC Stark shift patterns with different azimuthal symmetries and gradients that co-rotate with the ion crystals, demonstrating localized coherent control of single plane crystals with greater than 100 ions. Comparisons of the measured ion qubit populations with calculations from independent measurements of the applied AC Stark shift patterns show good agreement, validating the technique and providing a path, with a higher format SLM, for parallelizable, coherent individual ion addressing in Penning traps.
arXiv:2607.09584v1 Announce Type: new
Abstract: Battery-free RFID systems offer a scalable and maintenance-free approach to interaction. We present KnitID, a machine-knitted textile RFID antenna design that enables on-body authentication, localization, and interaction. Unlike prior antenna designs, KnitID achieves a compact antenna form factor (60mm by 8mm) by integrating magnet wire into the unique loop-over-loop structure of machine knitting. This structure reduces the size of conventional loop antennas by around 90\%, while also providing 30\% longer sensing ranges than standard dipole designs with similar size on the human body. The compact form factor creates new opportunities to embed multiple RFID tags across the human body, enriching backscatter signals and supporting a broader range of battery-free on-body interactions. To demonstrate this capability, we build an interactive sleeve to support wearer authentication, spatial localization, and interaction detection. Through technical evaluations, we show the feasibility of KnitID to provide diverse and battery-free interactions on knitted user interfaces.
arXiv:2411.17513v3 Announce Type: replace
Abstract: Modern deep-learning super-resolution (SR) techniques process images and videos independently of the underlying content and viewing conditions. However, the sensitivity of the human visual system (HVS) to image details changes depending on the underlying image characteristics, such as spatial frequency, luminance, color, contrast, or motion; as well viewing condition aspects such as ambient lighting and distance to the display. This observation suggests that computational resources spent on up-sampling images/videos may be wasted whenever a viewer cannot resolve the synthesized details i.e the resolution of details exceeds the resolving capability of human vision. Motivated by this observation, we propose a human vision inspired and architecture-agnostic approach for controlling SR techniques to deliver visually optimal results while limiting computational complexity. Its core is an explicit Human Visual Processing Framework (HVPF) that dynamically and locally guides SR methods according to human sensitivity to specific image details and viewing conditions. We demonstrate the application of our framework in combination with network branching to improve the computational efficiency of SR methods. Quantitative and qualitative evaluations, including user studies, demonstrate the effectiveness of our approach in reducing FLOPS by factors of 2$\times$ and greater, without sacrificing perceived quality.
arXiv:2607.09037v1 Announce Type: new
Abstract: A synchrotron injection scheme for the SuperKEKB electron high-energy ring (HER) was implemented and experimentally evaluated as the first attempt with a top-up injection during beam collisions. The lattice at the HER injection point was configured to provide a large horizontal dispersion of -1.6 m, and the injection beam energy was accordingly set to +0.6% above the ring energy. Since the beam extraction system is located near the injection point, the optics design was constrained to ensure compatibility with its requirements. A systematic tuning procedure of the injection parameters has been established with turn-by-turn BPMs(TbT-BPMs) in the ring, by which the betatron amplitude of the injected beam was successfully removed. Using optimized ring optics, synchrotron injection into the HER was successfully demonstrated, followed by the establishment of stable collisions and the production of luminosity.
arXiv:2501.11794v2 Announce Type: replace
Abstract: Cross-chain settlement must preserve safety across heterogeneous ledgers while tolerating delayed computation, Byzantine participants, and adversarial transaction issuance. This paper presents SPID-Chain, an adapter-compatible settlement architecture for escrow-backed fungible transfers across programmable blockchains. SPID-Chain maintains settlement state through persistent Polar-coded fragments, validates candidate state transitions using hidden linear verification checks, and records certified transfers in a weighted directed acyclic graph (DAG). The design separates native-chain finality from cross-chain settlement: source-chain finality establishes an immutable reservation, whereas weighted DAG confirmation determines when the corresponding destination credit becomes executable. We derive an exact recovery-time distribution for heterogeneous coded workers, a verification-soundness bound for Byzantine responses, and an exact weighted-quorum condition for conflicting-block safety. These components are coupled in a cross-layer stability theorem showing how the coded-validation completion probability determines the effective honest issuance rate and, consequently, the stable adversarial-load region of the settlement DAG. We further establish an end-to-end settlement guarantee covering balance non-negativity, asset conservation, conflict exclusion, replay protection, coded-state consistency, and finite expected lock-to-release latency under the stated liveness conditions. Prototype-assisted simulations indicate that coded validation reduces sensitivity to stragglers, improves validation and confirmation throughput under heterogeneous delays, and produces the predicted transition between stable and unstable DAG operation. The resulting framework provides a verifiable and analytically grounded settlement layer without modifying the native consensus protocol of participating chains.
arXiv:2607.09059v1 Announce Type: new
Abstract: We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints. ARCANA decomposes each task into iterative perception, hypothesis generation, symbolic execution, and reflective refinement. A perceptual grounding agent builds object centric scene graphs from raw grids, a latent program policy proposes diverse DSL programs, a symbolic executor verifies candidates on demonstrations, and a reflective agent synthesizes failure driven feedback for the next turn. These agents communicate through a shared differentiable blackboard and are scheduled by a learned meta controller. The design combines structured program search with adaptive multi turn correction, improving reasoning efficiency and solution quality on challenging abstract transformation tasks.
arXiv:2606.29858v2 Announce Type: replace
Abstract: Language model loss follows remarkably regular scaling laws over model and data size, yet it remains unclear why the aggregate loss should exhibit a power-law form. Existing explanations often attribute this regularity to a heavy-tailed spectrum of pattern difficulty in natural language, but this view has not been directly validated at token-level granularity in large-scale real-data training. We present a token-level framework that decomposes scaling laws into localized learning events of individual contextualized tokens. By fitting token loss trajectories with sigmoids, we show that token learning is concentrated in localized transitions, giving rise to a learning-time spectrum that dominates the scaling-law shape. Across more than one hundred pre-training runs on large and diverse real-language corpora with modern LLM architectures, scaling up to 6B parameters and 300B training tokens, the measured learning-time spectrum quantitatively reconstructs the validation loss derivative along the training-step $T$, data-scale $D$, and model-scale $M$ axes. We further show that the same signal is actionable: by reshaping the training distribution according to when tokens become learnable, we alter the optimization trajectory and achieve 11\% faster validation-loss reduction. These results provide direct empirical evidence that scaling laws are governed primarily by the distribution of token-level learning times, and that this distribution can be used not only to explain scaling behavior but also to improve training performance.
arXiv:2606.31513v2 Announce Type: replace
Abstract: Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections -- a severely ill-posed problem. Existing methods operate in pixel space, where the nonlinear sRGB formation model entangles the two layers and limits generalization. We observe that pretrained VAE latent spaces exhibit substantially lower coherence between image layers compared to pixel space, providing a more favorable working space for decomposition. Building on this finding, we propose \textbf{PRISM} (Pretrained-latent Reflection Image Separation Model), which reinterprets SIRR as a latent linear separation problem. Under an approximate additive formulation in latent space, PRISM learns a flow matching velocity field on a pretrained FLUX backbone that recovers both transmission and reflection in a single forward pass. To enforce robust disentanglement, we introduce a Latent Composition Consistency (LCC) strategy that constructs synthetic mixtures by swapping reflection latents across samples and enforces consistent decomposition via a cycle loss. We further propose a Layer Contrastive Separation (LCS) loss that promotes semantic separation between layers through patch-level contrastive learning, without requiring explicit reflection targets. Experiments on six benchmarks demonstrate that PRISM consistently outperforms state-of-the-art methods by significant margins, with strong generalization to in-the-wild images.
arXiv:2607.09336v1 Announce Type: new
Abstract: Diffusion-based trajectory planners have shown strong performance in offline reinforcement learning, but their iterative denoising process often incurs high inference cost. Consistency-based planners reduce the number of sampling steps, yet they typically rely on a two-stage teacher--student distillation pipeline that increases training cost and may introduce instability. We propose Shortcut Trajectory Planning (STP), an offline model-based reinforcement learning framework that incorporates shortcut models as efficient trajectory generators. STP trains a conditional shortcut trajectory model in a single stage, supports adjustable one-step and few-step inference through step-size conditioning, and selects candidate plans using a critic augmented with feasibility-aware correction. Across standard D4RL benchmarks, including locomotion, navigation, manipulation, and dexterous control tasks, STP achieves strong performance while simplifying the training pipeline for fast generative planning.
arXiv:2502.00138v3 Announce Type: replace
Abstract: In open multi-agent agent systems that cross organisational boundaries, agent actions must be regulated by complex policies. Consider medical data processing systems, which must observe generic laws (e.g., EU data protection regulations) and also specific participants' resource conditions (e.g., Bob consents to sharing his X-Rays with EU hospitals). Presently, we address the implementation of these systems as distributed software. Solutions to key sub-problems are available: existing policy languages capture the necessary normative concepts and formalise the computational representation and reasoning about policies, and existing distributed algorithms and protocols coordinate agents' changing actions and policies. But which policies and protocols are useful in application?
With the JustAct framework, we characterise a class of multi-agent systems where actors justify their actions with sufficient policy information collected from dynamic policy statements and agreements. We prove key properties of these systems, e.g., any decision that an action is permitted now cannot be refuted later, regardless of any added statements or updated agreements. We study a particular instance of the framework by specifying (in Rocq) and implementing (in Rust) a particular policy language and runtime system for mediating agent communications. We demonstrate and assess JustAct via a case study of this implementation: we reproduce the usage scenarios of Brane, an existing policy-regulated, inter-domain, medical data processing system.
arXiv:2502.02097v4 Announce Type: replace
Abstract: Vertebral Landmarks Localization in Dual-Energy X-ray Absorptiometry based Lateral Spine Imaging plays a critical role in evaluating spinal alignment, Vertebral Fracture Assessment, and facilitating intervertebral guide placement for Abdominal Aortic Calcification quantification. While lateral spine DXA scans offer advantages such as reduced cost and lower radiation exposure, its analysis remains challenging due to a low signal-to-noise ratio and imaging artifacts. Artificial Intelligence presents a promising approach for improving the precision and accuracy of VLL. In this study, we introduce a novel architecture that employs dual-resolution attention mechanisms to capture both fine-grained local details and broader contextual information. Our approach enhances feature integration by leveraging skip connections and decoder layers through dual-resolution self-attention and cross-attention mechanisms. This design improves the ability of the model to learn complex patterns, enabling precise vertebral corner localization while maintaining both local and global contextual awareness. We evaluated the proposed framework on DXA LSI images acquired from multiple machines and found that it outperforms recent state-of-the-art architectures for VLL, achieving a normalized mean error of 4.92 and a normalized median error of 2.35. The proposed framework, VerteNet, enables highly accurate VLL in DXA LSI images from diverse acquisition systems and demonstrates strong robustness to low signal-to-noise ratios, owing to its enhanced ability to capture both fine-grained local details and broader contextual information.
arXiv:2607.09616v1 Announce Type: new
Abstract: As chip complexity increases and time-to-market pressures grow, front-end design has become a critical bottleneck in chip development. Recently, Large Language Models (LLMs) have shown great potential in Electronic Design Automation (EDA). Beyond specification understanding, LLMs show the potential to serve as a unified intelligent interface for hardware description language (HDL) generation, testbench construction, and design space exploration. The rise of agentic AI, represented by pioneering systems such as OpenClaw, offers a strategic roadmap for the next generation EDA. From this perspective, this paper discusses the evolution of EDA from localized assistance to autonomous agentic execution. Then, we review representative advances of LLMs in front-end design, focusing on key tasks such as circuit and testbench generation from a shared specification, as well as design quality improvement in established workflows such as high-level synthesis. Finally, we discuss the key challenges and limitations of integrating LLMs into EDA, and outline future opportunities for advancing LLM-enabled front-end design, offering a systematic perspective for researchers interested in leveraging agentic AI technologies for EDA.
arXiv:2607.09648v1 Announce Type: new
Abstract: In this work, we present B-spline Policy (BSP), an action representation designed for accelerating robot manipulation policies. Rather than predicting discrete-time action chunks, BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points. This representation yields smooth, time-continuous trajectories that can be temporally scaled and executed by low-level controllers at higher frequencies and speeds. We show that B-spline-parameterized actions can be seamlessly integrated into standard policy learning pipelines by directly predicting B-spline parameters. Experiments on simulated and real-world tasks demonstrate that BSP significantly reduces task completion time, achieving substantial improvements over baseline methods while maintaining strong success rates. More results: https://b-spline-policy.github.io
arXiv:2607.09346v1 Announce Type: new
Abstract: A fixed boundary stellarator equilibrium capable of producing 3 GW of fusion power (1 GW-electric) is presented as the design basis for the GIGA fusion power plant being developed by Gauss Fusion GmbH. The stellarator concept provides a steady-state, transient free, low recirculating power approach to a fusion power plant, which builds on 50 years of progress in plasma physics. A set of requirements for a fixed boundary equilibrium were determined through application of 0.5 D modeling. Optimization of a modified Wendelstein 7-X (W7-X) equilibrium was performed to achieve these requirements including alpha power confinement greater than $85\%$, neoclassical effective ripple below 0.01, bootstrap current below 50 kA, and reduced turbulent heat fluxes. In order to fix the plasma volume of $1500~m^3$ during optimization, the VMEC code was modified to renormalize the boundary coefficient to the desired plasma volume. The STELLOPT stellarator optimization code was modified as well to include new bootstrap current targets, a new target for the radial electric field, and the capability to hold the magnetic field on axis at a fixed value. An intermediary conceptual design plasma and final evolved fixed boundary equilibria are compared to the original modified W7-X equilibrium. The final evolved equilibrium is shown to achieve all the necessary requirements for the GIGA fusion power plant through more detailed modeling of stability, fast ion confinement, and transport.
arXiv:2607.08775v1 Announce Type: new
Abstract: We study how to improve a frozen pretrained language model with a small amount of adaptive extra computation. A simple approach is to add additional refinement steps on top of the backbone hidden states, but fixed extra refinement can be wasteful: a one-step refinement head may be too weak, while forcing a second full-sequence refinement step everywhere can increase compute without improving transfer. We introduce HALO, a hybrid adaptive latent-refinement method that combines a coarse refinement stage with selective second-stage latent refinement on a subset of tokens chosen by token scoring and monotonic token halting. On the main public benchmark comparison built from MMLU-Pro and GPQA-Diamond, HALO achieves the best overall average among the paper-facing methods, outperforming the frozen backbone, fixed-1, and fixed-2. Internal analysis further shows that HALO reaches nearly the same token-accuracy level as fixed-2 while using fewer average applied refine steps than fixed-1 and far fewer than fixed-2. These results suggest that the key advantage is not simply more refinement, but a better allocation of refinement: HALO achieves the strongest paper-facing result while also using less measured controller compute than either fixed baseline.
arXiv:2405.00914v4 Announce Type: replace-cross
Abstract: We present in this paper novel accelerated fully first-order methods in \emph{Bilevel Optimization} (BLO). Firstly, for BLO under the assumption that the lower-level functions admit the typical strong convexity assumption, the \emph{(Perturbed) Restarted Accelerated Fully First-order methods for Bilevel Approximation} (\texttt{PRAF${}^2$BA}) algorithm leveraging \emph{fully} first-order oracles is proposed, whereas the algorithm for finding approximate first-order and second-order stationary points with state-of-the-art oracle query complexities in solving complex optimization tasks. Secondly, applying as a special case of BLO the \emph{nonconvex-strongly-convex} (NCSC) minimax optimization, \texttt{PRAF${}^2$BA} rediscovers \emph{perturbed restarted accelerated gradient descent ascent} (\texttt{PRAGDA}) that achieves the state-of-the-art complexity for finding approximate second-order stationary points. Additionally, we investigate the challenge of finding stationary points of the hyper-objective function in BLO when lower-level functions lack the typical strong convexity assumption, where we identify several regularity conditions of the lower-level problems that ensure tractability and present hardness results indicating the intractability of BLO for general convex lower-level functions. Under these regularity conditions we propose the \emph{Inexact Gradient-Free Method} (\texttt{IGFM}), utilizing the \emph{Switching Gradient Method} (\texttt{SGM}) as an efficient sub-routine to find an approximate stationary point of the hyper-objective in polynomial time. Empirical studies for real-world problems are provided to further validate the outperformance of our proposed algorithms.
arXiv:2504.18902v3 Announce Type: replace
Abstract: In the forthcoming era of 6G networks, characterized by unprecedented data rates, ultra-low latency, and ubiquitous connectivity, effective management of Virtualized Network Functions (VNFs) is essential. VNFs are software-based counterparts of traditional hardware devices that facilitate flexible and scalable service provisioning. Service Function Chains (SFCs), structured as ordered sequences of VNFs, are pivotal in delivering complex network services. Nevertheless, splitting an SFC into multiple segments that are deployed across different network domains or infrastructure locations presents substantial challenges due to the potential heterogeneity of domain characteristic along with quality of service (QoS) constraints and limited visibility of network state. Conventional optimization methods have limited scalability, while existing data-driven approaches struggle to balance efficiency with capturing VNF inter-dependencies in SFCs. To overcome these limitations, we introduce a Transformer-empowered actor-critic framework specifically designed for sequence-aware SFC partitioning. By utilizing the self-attention mechanism, our approach effectively models complex inter-dependencies between VNFs, facilitating coordinated and parallel decision-making processes. Furthermore, to improve training stability and convergence we introduce an $\epsilon$-LoPe exploration strategy as well as Asymptotic Return Normalization. Comprehensive simulation results demonstrate that the proposed methodology outperforms existing state-of-the-art solutions in terms of long-term service acceptance rates, resource utilization, and scalability while achieving fast inference.
arXiv:2607.09348v1 Announce Type: new
Abstract: Causal discovery from unstructured data is a challenging yet underexplored task in high-expertise domains such as healthcare, finance, and education. Existing methods typically leverage the general knowledge of large language models (LLMs) to identify causal factors from unstructured data and annotate them into structured data for causal graph construction. However, they remain limited by two key challenges (CHs): (CH1) insufficient identification of latent factors, which are implicit in the data yet essential for causal discovery, due to the lack of domain-specific knowledge; and (CH2) unreliable factor annotation, caused by the lack of domain-grounded reasoning, which propagates errors to the resulting causal graphs. To address these challenges, we introduce a novel Domain Knowledge-enhanced Causal Discovery framework (DKCD) for causal discovery from unstructured data in high-expertise domains with three interconnected components: (1) Knowledge Mining: It retrieves relevant domain knowledge based on observable factors to support subsequent causal reasoning. (2) Knowledge-guided Causal Reasoning: Reasoning with relevant knowledge, it discovers latent causal factors to address CH1 and generates key causal clues for more accurate data annotation to address CH2. (3) Causal Structure Discovery: It constructs the final causal graphs based on a more complete factor set and accurate annotations. Experiments on two domain-specific datasets show that DKCD significantly improves both causal factor identification and causal graph construction.
arXiv:2505.15987v5 Announce Type: replace
Abstract: We study identifiability of stochastic differential equations (SDE) under multiple interventions. Our results give the first provable bounds for unique recovery of SDE parameters given samples from their stationary distributions. We give tight bounds on the number of necessary interventions for linear SDEs, and upper bounds for nonlinear SDEs in the small noise regime. We experimentally validate the recovery of true parameters in synthetic data, and motivated by our theoretical results, demonstrate the advantage of parameterizations with learnable activation functions in application to gene regulatory dynamics.
arXiv:2602.07759v2 Announce Type: replace
Abstract: Recent advances in marine seismic acquisition and processing have substantially improved the separation of free-surface ghost wavefields. Building upon these developments, this study proposes a propagation-based framework in which separated ghost wavefields are treated as physically meaningful components that can be constructively utilised as additional observations. Starting from a finite inverse expansion of the ghost operator, a recursive formulation is derived and implemented through adaptive predictive decomposition. The formulation is subsequently extended to multidimensional wavefields through wavefield extrapolation, survey sinking, and reciprocity, allowing decomposition into components associated with real and mirrored sources and receivers. The separated wavefields are restored to a common acquisition geometry by survey sinking and combined through wavefield superposition, forming a preprocessing module that can be incorporated into conventional marine seismic processing workflows. Field-data examples acquired using a conventional shallow-towed airgun survey demonstrate improvements in reflector continuity, signal-to-noise ratio, and partial recovery of ghost-related spectral notches. The proposed framework therefore provides a processing-based complement to conventional ghost decomposition technologies and suggests a unified approach in which acquisition geometry and ghost processing are jointly optimised to maximise the information content of marine seismic observations.
arXiv:2607.03857v2 Announce Type: replace
Abstract: Function-Correcting Codes (FCCs) are a class of codes designed to protect the evaluation of a specific function of a message against channel errors at a higher level than the level of protection for the message, while requiring significantly less redundancy than conventional error-correcting codes. In this paper, we study function-correcting codes under the sum-rank metric, which is a natural generalization of both the Hamming metric and the rank-metric and also we derive general upper and lower bounds on the optimal redundancy of FCCs in the sum-rank metric. In particular, we establish a Plotkin-like bound for irregular-distance codes in sum-rank metric. Furthermore, we present explicit construction of function-correcting sum-rank metric codes (FCSRCs) for locally binary functions with optimal redundancy.
arXiv:2506.10915v2 Announce Type: replace
Abstract: Text-to-video generation has significantly enriched content creation and holds the potential to evolve into powerful world simulators. However, modeling the vast spatiotemporal space remains computationally demanding, particularly when employing Transformers, which incur quadratic complexity in sequence processing and thus limit practical applications. Recent advancements in linear-time sequence modeling, particularly the Mamba architecture, offer a more efficient alternative. Nevertheless, its plain design limits its direct applicability to multimodal and spatiotemporal video generation tasks. To address these challenges, we introduce M4V, a multimodal Mamba framework for efficient text-to-video generation. Specifically, a MultiModal diffusion Mamba (MM-DiM) block is designed within the framework to enable seamless integration of multimodal information and spatiotemporal modeling. In detail, we introduce a novel multimodal token re-composition design, which employs a bidirectional scheme for multimodal information integration through simple token arrangement, along with visual registers to enhance spatialtemporal consistency. As a result, the MM-DiM blocks in M4V reduce FLOPs by 45% compared with the attention-based alternative when generating videos at 768x1280 resolution. Additionally, several training strategies are explored in this work to provide a better understanding of training text-to-video models using only publicly available datasets. Extensive experiments on text-to-video benchmarks demonstrate M4V's ability to produce high-quality videos while significantly lowering computational costs. Project page: https://huangjch526.github.io/M4V_project/.
arXiv:2506.11936v2 Announce Type: replace
Abstract: Traditional rheological tools are often limited in characterizing soft materials under ultra-high strain-rate loading conditions (> 1000 s^-1) due to constraints in spatiotemporal resolution, loading rate, and invasiveness. Recently, inertial microcavitation rheometry (IMR), which utilizes laser-induced inertial cavitation (LIC) to dynamically deform surrounding materials, has emerged as a powerful experimental mechanics technique for probing nonlinear viscoelastic properties under extreme loading conditions. However, conventional IMR relies on computationally expensive iterative inverse fitting procedures, limiting its scalability and real-time applicability. Here, we introduce a new AI-enhanced experimental mechanics framework, called Bubble Dynamics Transformer (BDT), that integrates physics-based cavitation simulations with Transformer neural network architectures to achieve rapid inverse characterization of soft material viscoelasticity from experimentally measured bubble dynamics. The proposed framework directly predicts viscoelastic material parameters from time-resolved bubble radius evolution curves without iterative optimization. The BDT is trained using synthetic datasets generated from physics-based Keller--Miksis cavitation simulations and validated using experimental laser-induced cavitation data obtained from hydrogels and viscous polymer solutions. The proposed AI-driven framework demonstrates excellent agreement with our previous IMR while substantially accelerating constitutive parameter inference. Experimental demonstrations further reveal the capability of the framework to characterize rate-dependent material behavior across a wide range of soft materials, from viscous liquids to various viscoelastic hydrogels, at ultra-high strain rates.
arXiv:2506.22228v2 Announce Type: replace-cross
Abstract: Single-cell sequencing is revolutionizing biology by enabling detailed investigations of cell-state transitions. Many biological processes unfold along continuous trajectories, yet it remains challenging to extract smooth, low-dimensional representations from inherently noisy, high-dimensional single-cell data. Neighbor embedding (NE) algorithms, such as t-SNE and UMAP, are widely used to embed high-dimensional single-cell data into low dimensions. But they often introduce undesirable distortions, resulting in misleading interpretations. Existing evaluation methods for NE algorithms primarily focus on separating discrete cell types rather than capturing continuous cell-state transitions, while dynamic modeling approaches rely on strong assumptions about cellular processes and specialized data. To address these challenges, we build on the Predictability-Computability-Stability (PCS) framework for reliable and reproducible data-driven discoveries. First, we systematically evaluate popular NE algorithms through empirical analysis, simulation, and theory, and reveal their key shortcomings, such as artifacts and instability. We then introduce NESS, a principled and interpretable machine learning approach to improve NE representations by leveraging algorithmic stability and to enable robust inference of smooth biological structures. NESS offers useful concepts, quantitative stability metrics, and efficient computational workflows to uncover developmental trajectories and cell-state transitions in single-cell data. Finally, we apply NESS to six single-cell datasets, spanning pluripotent stem cell differentiation, organoid development, and multiple tissue-specific lineage trajectories. Across these diverse contexts, NESS consistently yields useful biological insights, such as identification of transitional and stable cell states and quantification of transcriptional dynamics during development.