The US Physics community completed the Snowmass planning process in 2022, culminating in the HEPAP Particle Physics Project Prioritization Panel (P5) publishing its summary report at the end of 2023. Building on this, the US Magnet Development Program, a national accelerator magnet R&D program established by DOE-OHEP in 2016, has updated its strategic plan to align with the 2023 P5 report, resulting in this roadmap document.
Efficient planning in high-dimensional spaces, such as those involving deformable objects, requires computationally tractable yet sufficiently expressive dynamics models. This paper introduces a method that automatically generates task-specific, spatially adaptive dynamics models by learning which regions of the object require high-resolution modeling to achieve good task performance for a given planning query. Task performance depends on the complex interplay between the dynamics model, world dynamics, control, and task requirements. Our proposed diffusion-based model generator predicts per-region model resolutions based on start and goal pointclouds that define the planning query. To efficiently collect the data for learning this mapping, a two-stage process optimizes resolution using predictive dynamics as a prior before directly optimizing using closed-loop performance. On a tree-manipulation task, our method doubles planning speed with only a small decrease in task performance over using a full-resolution model. This approach informs a path towards using previous planning and control data to generate computationally efficient yet sufficiently expressive dynamics models for new tasks.
We present a new application of model checking which achieves real-time multi-step planning and obstacle avoidance on a real autonomous robot. We have developed a small, purpose-built model checking algorithm which generates plans in situ based on "core" knowledge and attention as found in biological agents. This is achieved in real-time using no pre-computed data on a low-powered device. Our approach is based on chaining temporary control systems which are spawned to counteract disturbances in the local environment that disrupt an autonomous agent from its preferred action (or resting state). A novel discretization of 2D LiDAR data sensitive to bounded variations in the local environment is used. Multi-step planning using model checking by forward depth-first search is applied to cul-de-sac and playground scenarios. Both empirical results and informal proofs of two fundamental properties of our approach demonstrate that model checking can be used to create efficient multi-step plans for local obstacle avoidance, improving on the performance of a reactive agent which can only plan one step. Our approach is an instructional case study for the development of safe, reliable and explainable planning in the context of autonomous vehicles.
We introduce our new program to develop two-dimensional MEMS arrays of individually addressable micro-mirrors (''Micro-Mirror Devices'', MMDs) specifically optimized for astronomy, multi-slit spectroscopy in particular. After reviewing the main characteristics and performance of the currently available options, Micro Shutter Arrays by NASA/Goddard and Digital Micromirror Devices by Texas Instruments, we present our planned first generation/baseline devices with 30 micron x 30 miron pixel size arranged in a 1K x 1K format with tilt angle 15 degrees. Our goal is to bring to maturity a technology capable of delivering arrays of 2K x 2K element of 100 micron x 100 micron, buttable on two sides to achieve even larger formats. In additions to MEMS design, we will develop the associated device packaging and electronic control circuitry leveraging on the extensive expertise gained in the last 30+ years by leading experts from digital imaging industry.
Optimal path planning requires finding a series of feasible states from the starting point to the goal to optimize objectives. Popular path planning algorithms, such as Effort Informed Trees (EIT*), employ effort heuristics to guide the search. Effective heuristics are accurate and computationally efficient, but achieving both can be challenging due to their conflicting nature. This paper proposes Direction Informed Trees (DIT*), a sampling-based planner that focuses on optimizing the search direction for each edge, resulting in goal bias during exploration. We define edges as generalized vectors and integrate similarity indexes to establish a directional filter that selects the nearest neighbors and estimates direction costs. The estimated direction cost heuristics are utilized in edge evaluation. This strategy allows the exploration to share directional information efficiently. DIT* convergence faster than existing single-query, sampling-based planners on tested problems in R^4 to R^16 and has been demonstrated in real-world environments with various planning tasks. A video showcasing our experimental results is available at: https://youtu.be/2SX6QT2NOek
Purposeful behavior in robotic assistants requires the integration of multiple components and technological advances. Often, the problem is reduced to recognizing explicit prompts, which limits autonomy, or is oversimplified through assumptions such as near-perfect information. We argue that a critical gap remains unaddressed -- specifically, the challenge of reasoning about the uncertain outcomes and perception errors inherent to human intention recognition. In response, we present a framework designed to be resilient to uncertainty and sensor noise, integrating real-time sensor data with a combination of planners. Centered around an intention-recognition POMDP, our approach addresses cooperative planning and acting under uncertainty. Our integrated framework has been successfully tested on a physical robot with promising results.
Neutral hydrogen (HI) 21-cm Intensity Mapping (IM) holds the potential to map the large-scale structures in the Universe over a wide redshift range $(z \lesssim 5.5)$, measure cosmological parameters, and shed light on the nature of dark energy. In addition, the signal is also sensitive to how the HI is distributed among the dark matter haloes, this being quantified through the HIHM relation, which relates the HI mass to the halo mass. In this work, we investigate whether measurements of the 21-cm power spectrum (PS) and bispectrum (BS) at large scales can be used to estimate the HIHM relation, which quantifies the HI distribution at small scales. As a proof of concept, we consider the simulated 21-cm IM signal at $z=1$. We find that the measured 21-cm PS and BS at large scales $(k \le k_{ul} = 0.32 \, {\rm Mpc}^{-1})$ are well modeled using perturbation theory, with only two free parameters namely $[\Omega_{\rm HI} b_1]$ and $\gamma = b_2/b_1$. Combining the measured 21-cm PS and BS with an independent measurement of $\Omega_{\rm HI} $, we show that it is possible to estimate the three parameters that quantify the HIHM relation. We expect observational estimates of the HIHM relation to shed light on galaxy formation and the evolution of the ISM. Our preliminary analysis ignores redshift space distortion and the system noise in IM observations, which we plan to address in future work.
Interpreting kinematic graphs remains a significant challenge in physics education. The MissionMotion Project addresses this issue by providing a gamified physical-computational environment combining low-cost sensors, physical activity, computational thinking, and real-time visualization of motion graphs. This paper presents the design, development, and implementation of the project, with a particular focus on the pilot phase conducted with high school students in Uruguay. During this phase, we primarily used the MEEGA+ questionnaire to evaluate the gaming experience, usability, and motivation of the participants. Our analysis of the results shows high levels of satisfaction, perceived learning, and engagement, supporting the proposal's viability. Finally, we plan to conduct a large-scale conceptual evaluation to analyze how the proposal impacts understanding of kinematic graphs using standardized assessment tools.
Accurate detection and segmentation of cancerous lesions from computed tomography (CT) scans is essential for automated treatment planning and cancer treatment response assessment. Transformer-based models with self-supervised pretraining can produce reliably accurate segmentation from in-distribution (ID) data but degrade when applied to out-of-distribution (OOD) datasets. We address this challenge with RF-Deep, a random forest classifier that utilizes deep features from a pretrained transformer encoder of the segmentation model to detect OOD scans and enhance segmentation reliability. The segmentation model comprises a Swin Transformer encoder, pretrained with masked image modeling (SimMIM) on 10,432 unlabeled 3D CT scans covering cancerous and non-cancerous conditions, with a convolution decoder, trained to segment lung cancers in 317 3D scans. Independent testing was performed on 603 3D CT public datasets that included one ID dataset and four OOD datasets comprising chest CTs with pulmonary embolism (PE) and COVID-19, and abdominal CTs with kidney cancers and healthy volunteers. RF-Deep detected OOD cases with a FPR95 of 18.26%, 27.66%, and less than 0.1% on PE, COVID-19, and abdominal CTs, consistently outperforming established OOD approaches. The RF-Deep classifier provides a simple and effective approach to enhance reliability of cancer segmentation in ID and OOD scenarios.
In a doctor-patient dialogue, the primary objective of physicians is to diagnose patients and propose a treatment plan. Medical doctors guide these conversations through targeted questioning to efficiently gather the information required to provide the best possible outcomes for patients. To the best of our knowledge, this is the first work that studies physician intent trajectories in doctor-patient dialogues. We use the `Ambient Clinical Intelligence Benchmark' (Aci-bench) dataset for our study. We collaborate with medical professionals to develop a fine-grained taxonomy of physician intents based on the SOAP framework (Subjective, Objective, Assessment, and Plan). We then conduct a large-scale annotation effort to label over 5000 doctor-patient turns with the help of a large number of medical experts recruited using Prolific, a popular crowd-sourcing platform. This large labeled dataset is an important resource contribution that we use for benchmarking the state-of-the-art generative and encoder models for medical intent classification tasks. Our findings show that our models understand the general structure of medical dialogues with high accuracy, but often fail to identify transitions between SOAP categories. We also report for the first time common trajectories in medical dialogue structures that provide valuable insights for designing `differential diagnosis' systems. Finally, we extensively study the impact of intent filtering for medical dialogue summarization and observe a significant boost in performance. We make the codes and data, including annotation guidelines, publicly available at https://github.com/DATEXIS/medical-intent-classification.
We introduce TROOP, a tree-based Riccati optimistic online planner, that is designed to generate near-optimal control laws for discrete-time switched linear systems with switched quadratic costs. The key challenge that we address is balancing computational resources against control performance, which is important as constructing near-optimal inputs often requires substantial amount of computations. TROOP addresses this trade-off by adopting an online best-first search strategy inspired by A*, allowing for efficient estimates of the optimal value function. The control laws obtained guarantee both near-optimality and stability properties for the closed-loop system. These properties depend on the planning depth, which determines how far into the future the algorithm explores and is closely related to the amount of computations. TROOP thus strikes a balance between computational efficiency and control performance, which is illustrated by numerical simulations on an example.
Multi-stage stochastic optimization is a well-known quantitative tool for decision-making under uncertainty. It is broadly used in financial and investment planning, inventory control, and also natural disaster risk management. Theoretical solutions of multi-stage stochastic programs can be found explicitly only in very exceptional cases due to their variational form and interdependency of uncertainty in time. Nevertheless, numerical solutions are often inaccurate, as they rely on Monte-Carlo sampling, which requires the Law of Large Numbers to hold for the approximation quality. In this article, we introduce a new approximation scheme, which computes and groups together stage-wise optimal quantizers of conditional Fr\'echet distributions for optimal weighting of value functions in the dynamic programming. We consider optimality of scenario quantization methods in the sense of minimal Kantorovich-Wasserstein distance at each stage of the scenario tree. By this, we bound the approximation error with convergence guarantees. We also provide global solution guarantees under convexity and monotonicity conditions on the value function. We apply the developed methods to the governmental budget allocation problem for risk management of flood events in Austria. For this, we propose an extremely efficient way to approximate optimal quantizers for conditional Fr\'echet distributions. Our approach allows to enhance the overall efficiency of dynamic programming via the use of different parameter estimation methods for different groups of quantizers. The groups are distinguished by a particular risk threshold and are able to differentiate between higher- and lower-impact flood events.
Ground motion models (GMMs) predict how strongly the ground will shake during an earthquake. They are essential for structural analysis, seismic design, and seismic risk assessment studies. Traditional machine learning (ML) approaches are popular to develop GMMs, due to large earthquake databases worldwide. However, they operate as "black boxes," which are hard to interpret and trust, limiting their use in high-stake decisions. Additionally, these databases suffer from significant data imbalances: fewer large, critically damaging records near the fault compared to abundant, less severely damaging distant records. These two limitations are addressed in this work by developing a transparent ML architecture using the HazBinLoss function. Each input (e.g., magnitude, distance, their interaction term, etc.) is processed separately and added linearly to obtain the output, resulting in exact contribution of each term. The HazBinLoss function assigns higher weights to critical near-field large magnitude records and lower weights to less-critical far-field smaller magnitude records, during training to prevent underprediction of the most damaging scenarios. Our model captures known seismological principles and achieves comparable performance with established GMMs while maintaining transparency. This framework enables broader adoption of ML-based approaches for risk assessment studies and disaster planning.
Predictive Process Monitoring (PPM) aims to train models that forecast upcoming events in process executions. These predictions support early bottleneck detection, improved scheduling, proactive interventions, and timely communication with stakeholders. While existing research adopts a control-flow perspective, we investigate next-activity prediction from a resource-centric viewpoint, which offers additional benefits such as improved work organization, workload balancing, and capacity forecasting. Although resource information has been shown to enhance tasks such as process performance analysis, its role in next-activity prediction remains unexplored. In this study, we evaluate four prediction models and three encoding strategies across four real-life datasets. Compared to the baseline, our results show that LightGBM and Transformer models perform best with an encoding based on 2-gram activity transitions, while Random Forest benefits most from an encoding that combines 2-gram transitions and activity repetition features. This combined encoding also achieves the highest average accuracy. This resource-centric approach could enable smarter resource allocation, strategic workforce planning, and personalized employee support by analyzing individual behavior rather than case-level progression. The findings underscore the potential of resource-centric next-activity prediction, opening up new venues for research on PPM.
Efficient and safe navigation of Unmanned Aerial Vehicles (UAVs) is critical for various applications, including combat support, package delivery and Search and Rescue Operations. This paper introduces the Tangent Intersection Guidance (TIG) algorithm, an advanced approach for UAV path planning in both static and dynamic environments. The algorithm uses the elliptic tangent intersection method to generate feasible paths. It generates two sub-paths for each threat, selects the optimal route based on a heuristic rule, and iteratively refines the path until the target is reached. Considering the UAV kinematic and dynamic constraints, a modified smoothing technique based on quadratic B\'ezier curves is adopted to generate a smooth and efficient route. Experimental results show that the TIG algorithm can generate the shortest path in less time, starting from 0.01 seconds, with fewer turning angles compared to A*, PRM, RRT*, Tangent Graph, and Static APPATT algorithms in static environments. Furthermore, in completely unknown and partially known environments, TIG demonstrates efficient real-time path planning capabilities for collision avoidance, outperforming APF and Dynamic APPATT algorithms.
We present AniME, a director-oriented multi-agent system for automated long-form anime production, covering the full workflow from a story to the final video. The director agent keeps a global memory for the whole workflow, and coordinates several downstream specialized agents. By integrating customized Model Context Protocol (MCP) with downstream model instruction, the specialized agent adaptively selects control conditions for diverse sub-tasks. AniME produces cinematic animation with consistent characters and synchronized audio visual elements, offering a scalable solution for AI-driven anime creation.
We present a Sequential Mobile Manipulation Planning (SMMP) framework that can solve long-horizon multi-step mobile manipulation tasks with coordinated whole-body motion, even when interacting with articulated objects. By abstracting environmental structures as kinematic models and integrating them with the robot's kinematics, we construct an Augmented Configuration Apace (A-Space) that unifies the previously separate task constraints for navigation and manipulation, while accounting for the joint reachability of the robot base, arm, and manipulated objects. This integration facilitates efficient planning within a tri-level framework: a task planner generates symbolic action sequences to model the evolution of A-Space, an optimization-based motion planner computes continuous trajectories within A-Space to achieve desired configurations for both the robot and scene elements, and an intermediate plan refinement stage selects action goals that ensure long-horizon feasibility. Our simulation studies first confirm that planning in A-Space achieves an 84.6\% higher task success rate compared to baseline methods. Validation on real robotic systems demonstrates fluid mobile manipulation involving (i) seven types of rigid and articulated objects across 17 distinct contexts, and (ii) long-horizon tasks of up to 14 sequential steps. Our results highlight the significance of modeling scene kinematics into planning entities, rather than encoding task-specific constraints, offering a scalable and generalizable approach to complex robotic manipulation.
Navigation signs and maps, such as floor plans and street maps, are widely available and serve as ubiquitous aids for way-finding in human environments. Yet, they are rarely used by robot systems. This paper presents SignLoc, a global localization method that leverages navigation signs to localize the robot on publicly available maps -- specifically floor plans and OpenStreetMap (OSM) graphs -- without prior sensor-based mapping. SignLoc first extracts a navigation graph from the input map. It then employs a probabilistic observation model to match directional and locational cues from the detected signs to the graph, enabling robust topo-semantic localization within a Monte Carlo framework. We evaluated SignLoc in diverse large-scale environments: part of a university campus, a shopping mall, and a hospital complex. Experimental results show that SignLoc reliably localizes the robot after observing only one to two signs.
The LEGEND experiment is looking for the extremely rare neutrinoless double beta ($0\nu\beta\beta$) decay of $^{76}$Ge using isotopically-enriched high-purity germanium (HPGe) detectors. The detection of this process would imply that the neutrino is a Majorana particle and the total lepton number would not be conserved, which could be related to the cosmological asymmetry between matter and antimatter through leptogenesis. The long-term goal of the collaboration is LEGEND-1000: a 1-ton detector array planned to run for 10 years, with a projected half-life sensitivity exceeding $10^{28}$ years, fully covering the inverted neutrino mass hierarchy. A first search for the $0\nu\beta\beta$ decay has been carried out by LEGEND-200 building on the experience gained from GERDA and the MAJORANA DEMONSTRATOR. The experiment has been collecting physics data for a year at the Gran Sasso National Laboratory in Italy with 140 kg of HPGe detectors. With a total exposure of 61 kg yr, LEGEND-200 has achieved a background index of $5^{+3}_{-2}\times10^{-4}$ counts/(keV kg yr) in the $0\nu\beta\beta$ decay signal region from the highest performing detectors. After combining the results from GERDA, the MAJORANA Demonstrator and LEGEND-200, an exclusion sensitivity $ > 2.8\times10^{26}$ yr has been obtained at 90\% confidence level for the $0\nu\beta\beta$ decay half-life, with no evidence for a signal. A new observed lower limit of $T^{0\nu}_{1/2} > 1.9\times10^{26}$ yr at 90\% confidence level has been established.
Novelty heuristics aid heuristic search by exploring states that exhibit novel atoms. However, novelty heuristics are not symmetry invariant and hence may sometimes lead to redundant exploration. In this preliminary report, we propose to use Weisfeiler-Leman Features for planning (WLFs) in place of atoms for detecting novelty. WLFs are recently introduced features for learning domain-dependent heuristics for generalised planning problems. We explore an unsupervised usage of WLFs for synthesising lifted, domain-independent novelty heuristics that are invariant to symmetric states. Experiments on the classical International Planning Competition and Hard To Ground benchmark suites yield promising results for novelty heuristics synthesised from WLFs.
Weisfeiler-Leman Features (WLFs) are a recently introduced classical machine learning tool for learning to plan and search. They have been shown to be both theoretically and empirically superior to existing deep learning approaches for learning value functions for search in symbolic planning. In this paper, we introduce new WLF hyperparameters and study their various tradeoffs and effects. We utilise the efficiency of WLFs and run planning experiments on single core CPUs with a sample size of 1,000,000 to understand the effect of hyperparameters on training and planning. Our experimental analysis show that there is a robust and best set of hyperparameters for WLFs across the tested planning domains. We find that the best WLF hyperparameters for learning heuristic functions minimise execution time rather than maximise model expressivity. We further statistically analyse and observe no significant correlation between training and planning metrics.
We study the usage of language models (LMs) for planning over world models specified in the Planning Domain Definition Language (PDDL). We prompt LMs to generate Python programs that serve as generalised policies for solving PDDL problems from a given domain. Notably, our approach synthesises policies that are provably sound relative to the PDDL domain without reliance on external verifiers. We conduct experiments on competition benchmarks which show that our policies can solve more PDDL problems than PDDL planners and recent LM approaches within a fixed time and memory constraint. Our approach manifests in the LMPlan planner which can solve planning problems with several hundreds of relevant objects. Surprisingly, we observe that LMs used in our framework sometimes plan more effectively over PDDL problems written in meaningless symbols in place of natural language; e.g. rewriting (at dog kitchen) as (p2 o1 o3). This finding challenges hypotheses that LMs reason over word semantics and memorise solutions from its training corpus, and is worth further exploration.
Variational quantum algorithms (VQAs) have emerged as a leading paradigm in near-term quantum computing, yet their performance can be hindered by the so-called barren plateau problem, where gradients vanish exponentially with system size or circuit depth. While most existing VQA research employs simple Gaussian or zero-initialization schemes, classical deep learning has long benefited from sophisticated weight initialization strategies such as Xavier, He, and orthogonal initialization to improve gradient flow and expedite convergence. In this work, we systematically investigate whether these classical methods can mitigate barren plateaus in quantum circuits. We first review each initialization's theoretical grounding and outline how to adapt the notions from neural networks to VQAs. We then conduct extensive numerical experiments on various circuit architectures and optimization tasks. Our findings indicate that while the initial heuristics, inspired by classical initialization, yield moderate improvements in certain experiments, their overall benefits remain marginal. By outlining a preliminary exploration plan in this paper, we aim to offer the research community a broader perspective and accessible demonstrations. Furthermore, we propose future research directions that may be further refined by leveraging the insights gained from this work.
In humanitarian and emergency scenarios, the use of biometrics can dramatically improve the efficiency of operations, but it poses risks for the data subjects, which are exacerbated in contexts of vulnerability. To address this, we present a mobile biometric system implementing a biometric template protection (BTP) scheme suitable for these scenarios. After rigorously formulating the functional, operational, and security and privacy requirements of these contexts, we perform a broad comparative analysis of the BTP landscape. PolyProtect, a method designed to operate on neural network face embeddings, is identified as the most suitable method due to its effectiveness, modularity, and lightweight computational burden. We evaluate PolyProtect in terms of verification and identification accuracy, irreversibility, and unlinkability, when this BTP method is applied to face embeddings extracted using EdgeFace, a novel state-of-the-art efficient feature extractor, on a real-world face dataset from a humanitarian field project in Ethiopia. Moreover, as PolyProtect promises to be modality-independent, we extend its evaluation to fingerprints. To the best of our knowledge, this is the first time that PolyProtect has been evaluated for the identification scenario and for fingerprint biometrics. Our experimental results are promising, and we plan to release our code
The research and development of intelligent automation solutions is a ground-breaking point for the factory of the future. A promising and challenging mission is the use of autonomous robot systems to automate tasks in the field of maintenance. For this purpose, the robot system must be able to plan autonomously the different manipulation tasks and the corresponding paths. Basic requirements are the development of algorithms with a low computational complexity and the possibility to deal with environmental uncertainties. In this work, an approach is presented, which is especially suited to solve the problem of maintenance automation. For this purpose, offline data from CAD is combined with online data from an RGBD vision system via a probabilistic filter, to compensate uncertainties from offline data. For planning the different tasks, a method is explained, which use a symbolic description, founded on a novel sampling-based method to compute the disassembly space. For path planning we use global state-of-the art algorithms with a method that allows the adaption of the exploration stepsize in order to reduce the planning time. Every method is experimentally validated and discussed.
Automating complex tasks using robotic systems requires skills for planning, control and execution. This paper proposes a complete robotic system for maintenance automation, which can automate disassembly and assembly operations under environmental uncertainties (e.g. deviations between prior plan information). The cognition of the robotic system is based on a planning approach (using CAD and RGBD data) and includes a method to interpret a symbolic plan and transform it to a set of executable robot instructions. The complete system is experimentally evaluated using real-world applications. This work shows the first step to transfer these theoretical results into a practical robotic solution.
Offline Reinforcement Learning (RL) presents a promising paradigm for training autonomous vehicle (AV) planning policies from large-scale, real-world driving logs. However, the extreme data imbalance in these logs, where mundane scenarios vastly outnumber rare "long-tail" events, leads to brittle and unsafe policies when using standard uniform data sampling. In this work, we address this challenge through a systematic, large-scale comparative study of data curation strategies designed to focus the learning process on information-rich samples. We investigate six distinct criticality weighting schemes which are categorized into three families: heuristic-based, uncertainty-based, and behavior-based. These are evaluated at two temporal scales, the individual timestep and the complete scenario. We train seven goal-conditioned Conservative Q-Learning (CQL) agents with a state-of-the-art, attention-based architecture and evaluate them in the high-fidelity Waymax simulator. Our results demonstrate that all data curation methods significantly outperform the baseline. Notably, data-driven curation using model uncertainty as a signal achieves the most significant safety improvements, reducing the collision rate by nearly three-fold (from 16.0% to 5.5%). Furthermore, we identify a clear trade-off where timestep-level weighting excels at reactive safety while scenario-level weighting improves long-horizon planning. Our work provides a comprehensive framework for data curation in Offline RL and underscores that intelligent, non-uniform sampling is a critical component for building safe and reliable autonomous agents.
Many Vision-Language-Action (VLA) models are built upon an internal world model trained via direct next-frame prediction ($v_t \rightarrow v_{t+1}$). This paradigm, however, presents a fundamental challenge: it \textbf{conflates} the task of predicting physical motion with that of rendering static appearance, forcing a single mechanism to handle both. This inherent coupling often leads to physically implausible forecasts and inefficient policy learning. To address this limitation, we introduce the \textbf{Visual Chain of Thought (Visual CoT)}, a framework that disentangles these processes by compelling the model to first reason about \textbf{motion dynamics} before generating the future frame's \textbf{visual appearance}. We instantiate this principle by proposing \textbf{FlowVLA}, an autoregressive Transformer that explicitly materializes this reasoning process as ``$v_t \rightarrow f_t \rightarrow v_{t+1}$'', where $f_t$ is an intermediate optical flow prediction. By forcing the model to first commit to a motion plan ($f_t$), FlowVLA learns disentangled dynamics, resulting in more coherent visual predictions and significantly more efficient policy learning. Experiments on challenging robotics manipulation benchmarks demonstrate that FlowVLA achieves state-of-the-art performance with substantially improved sample efficiency, pointing toward a more principled foundation for world modeling in VLAs. Project page: https://irpn-lab.github.io/FlowVLA/
Accurate prediction of urban wind flow is essential for urban planning, pedestrian safety, and environmental management. Yet, it remains challenging due to uncertain boundary conditions and the high cost of conventional CFD simulations. This paper presents the use of the modular and efficient uncertainty quantification (UQ) framework OpenLB-UQ for urban wind flow simulations. We specifically use the lattice Boltzmann method (LBM) coupled with a stochastic collocation (SC) approach based on generalized polynomial chaos (gPC). The framework introduces a relative-error noise model for inflow wind speeds based on real measurements. The model is propagated through a non-intrusive SC LBM pipeline using sparse-grid quadrature. Key quantities of interest, including mean flow fields, standard deviations, and vertical profiles with confidence intervals, are efficiently computed without altering the underlying deterministic solver. We demonstrate this on a real urban scenario, highlighting how uncertainty localizes in complex flow regions such as wakes and shear layers. The results show that the SC LBM approach provides accurate, uncertainty-aware predictions with significant computational efficiency, making OpenLB-UQ a practical tool for real-time urban wind analysis.
Robot swarms require cohesive collective behaviour to address diverse challenges, including shape formation and decision-making. Existing approaches often treat consensus in discrete and continuous decision spaces as distinct problems. We present DANCeRS, a unified, distributed algorithm leveraging Gaussian Belief Propagation (GBP) to achieve consensus in both domains. By representing a swarm as a factor graph our method ensures scalability and robustness in dynamic environments, relying on purely peer-to-peer message passing. We demonstrate the effectiveness of our general framework through two applications where agents in a swarm must achieve consensus on global behaviour whilst relying on local communication. In the first, robots must perform path planning and collision avoidance to create shape formations. In the second, we show how the same framework can be used by a group of robots to form a consensus over a set of discrete decisions. Experimental results highlight our method's scalability and efficiency compared to recent approaches to these problems making it a promising solution for multi-robot systems requiring distributed consensus. We encourage the reader to see the supplementary video demo.