Model-free diffusion planners have shown great promise for robot motion planning, but practical robotic systems often require combining them with model-based optimization modules to enforce constraints, such as safety. Naively integrating these modules presents compatibility challenges when diffusion's multi-modal outputs behave adversarially to optimization-based modules. To address this, we introduce Joint Model-based Model-free Diffusion (JM2D), a novel generative modeling framework. JM2D formulates module integration as a joint sampling problem to maximize compatibility via an interaction potential, without additional training. Using importance sampling, JM2D guides modules outputs based only on evaluations of the interaction potential, thus handling non-differentiable objectives commonly arising from non-convex optimization modules. We evaluate JM2D via application to aligning diffusion planners with safety modules on offline RL and robot manipulation. JM2D significantly improves task performance compared to conventional safety filters without sacrificing safety. Further, we show that conditional generation is a special case of JM2D and elucidate key design choices by comparing with SOTA gradient-based and projection-based diffusion planners. More details at: https://jm2d-corl25.github.io/.
In the last decade, the Laser Interferometer Gravitational-Wave Observatory (LIGO) and the European Virgo observatory have opened a new observational window on the universe. These cavity-enhanced laser interferometers sense spacetime strain, generated by distant astrophysical events such as black hole mergers, to an RMS fluctuation of a few parts in $10^{21}$ over a multi-kilometer baseline. Optical advancements in laser wavefront control are key to advancing the sensitivity of current detectors and enabling a planned next-generation 40-km gravitational wave observatory in the United States, known as Cosmic Explorer. We report the first experimental demonstration of a new wavefront control technique for gravitational-wave detection, obtained from testing a full-scale prototype on a 40-kg LIGO mirror. Our results indicate that this design can meet the unique and challenging requirements of providing higher-order precision wavefront corrections at megawatt laser power levels, while introducing extremely low effective displacement noise into the interferometer. This new technology will have a direct and enabling impact on the observational science, expanding the gravitational-wave detection horizon to very early times in the universe, before the first stars formed, and enabling new tests of gravity, cosmology, and dense nuclear matter.
Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation without requiring 3D maps or pre-trained controllers. Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles. We address key limitations of previous methods by continuously predicting local trajectory using monocular depth and traversability estimation, and incorporating an auto-switching mechanism that falls back to a baseline controller when necessary. The system operates using foundational models, ensuring open-set applicability without the need for domain-specific fine-tuning. We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability. Our approach outperforms existing state-of-the-art methods, offering a more adaptable and effective solution for visual navigation in open-set environments. The source code is made publicly available: https://github.com/podgorki/TANGO.
This paper presents a feature-based Partially Observable Markov Decision Process (POMDP) framework for quantum network routing, combining belief-state planning with Graph Neural Networks (GNNs) to address partial observability, decoherence, and scalability challenges in dynamic quantum systems. Our approach encodes complex quantum network dynamics, including entanglement degradation and time-varying channel noise, into a low-dimensional feature space, enabling efficient belief updates and scalable policy learning. The core of our framework is a hybrid GNN-POMDP architecture that processes graph-structured representations of entangled links to learn routing policies, coupled with a noise-adaptive mechanism that fuses POMDP belief updates with GNN outputs for robust decision making. We provide a theoretical analysis establishing guarantees for belief convergence, policy improvement, and robustness to noise. Experiments on simulated quantum networks with up to 100 nodes demonstrate significant improvements in routing fidelity and entanglement delivery rates compared to state-of-the-art baselines, particularly under high decoherence and nonstationary conditions.
Using inverse planning tools to create radiotherapy treatment plans is an iterative process, where clinical trade-offs are explored by changing the relative importance of different objectives and rerunning the optimizer until a desirable plan is found. We seek to optimize hundreds of radiosurgery treatment plans, corresponding to different weightings of objectives, fast enough to incorporate interactive Pareto navigation of clinical trade-offs into the clinical workflow. We apply the alternating direction method of multipliers (ADMM) to the linear-program formulation of the optimization problem used in Lightning. We implement both a CPU and a GPU version of ADMM in Matlab and compare them to Matlab's built-in, single-threaded dual-simplex solver. The ADMM implementation is adapted to the optimization procedure used in the clinical software, with a bespoke algorithm for maximizing overlap between low-dose points for different objective weights. The method is evaluated on a test dataset consisting of 20 cases from three different indications, with between one and nine targets and total target volumes ranging from 0.66 to 52 cm3, yielding speedups of 1.6-97 and 54-1500 times on CPU and GPU, respectively, compared to simplex. Plan quality was evaluated by rerunning the ADMM optimization 20 times, each with a different random seed, for each test case and for nine objective weightings per case. The resulting clinical metrics closely mimicked those obtained when rerunning the simplex solver, verifying the validity of the method. In conclusion, we show how ADMM can be adapted for radiosurgery plan optimization, allowing hundreds of high-quality Gamma Knife treatment plans to be created in under two minutes on a single GPU, also for very large cases.
This paper investigates the resilience of mobile communication networks during the extreme flooding that affected Rio Grande do Sul, Brazil, in May 2024. Based on regulatory data and technical insights from operators, the study identifies the leading causes of mobile network disruptions, primarily related to flooding and prolonged power outages. The results reveal the significant vulnerability of modern networks (4G/5G) during the event and the essential role played by legacy technologies (2G/3G) in sustaining basic connectivity under adverse conditions. The findings underscore the necessity of disaster-aware infrastructure planning, taking into account the ongoing significance of legacy systems, diversified power supply strategies, and resilient network designs to enhance service continuity during future crises.
The objective of this paper is to significantly reduce the manual workload required from medical professionals in complex 3D segmentation tasks that cannot be yet fully automated. For instance, in radiotherapy planning, organs at risk must be accurately identified in computed tomography (CT) or magnetic resonance imaging (MRI) scans to ensure they are spared from harmful radiation. Similarly, diagnosing age-related degenerative diseases such as sarcopenia, which involve progressive muscle volume loss and strength, is commonly based on muscular mass measurements often obtained from manual segmentation of medical volumes. To alleviate the manual-segmentation burden, this paper introduces an implicit shape prior to segment volumes from sparse slice manual annotations generalized to the multi-organ case, along with a simple framework for automatically selecting the most informative slices to guide and minimize the next interactions. The experimental validation shows the method's effectiveness on two medical use cases: assisted segmentation in the context of at risks organs for brain cancer patients, and acceleration of the creation of a new database with unseen muscle shapes for patients with sarcopenia.
Path planning in dynamic environments remains a core challenge in robotics, especially as autonomous systems are deployed in unpredictable spaces such as warehouses and public roads. While algorithms like Fast Marching Tree (FMT$^{*}$) offer asymptotically optimal solutions in static settings, their single-pass design prevents path revisions which are essential for real-time adaptation. On the other hand, full replanning is often too computationally expensive. This paper introduces FMT$^{x}$, an extension of the Fast Marching Tree algorithm that enables efficient and consistent replanning in dynamic environments. We revisit the neighbor selection rule of FMT$^{*}$ and demonstrate that a minimal change overcomes its single-pass limitation, enabling the algorithm to update cost-to-come values upon discovering better connections without sacrificing asymptotic optimality or computational efficiency. By maintaining a cost-ordered priority queue and applying a selective update condition that uses an expanding neighbor to identify and trigger the re-evaluation of any node with a potentially suboptimal path, FMT$^{x}$ ensures that suboptimal routes are efficiently repaired as the environment evolves. This targeted strategy preserves the inherent efficiency of FMT$^{*}$ while enabling robust adaptation to changes in obstacle configuration. FMT$^{x}$ is proven to recover an asymptotically optimal solution after environmental changes. Experimental results demonstrate that FMT$^{x}$ outperforms the influential replanner RRT$^{x}$, reacting more swiftly to dynamic events with lower computational overhead and thus offering a more effective solution for real-time robotic navigation in unpredictable worlds.
In this paper, we present our localization method called CLAP, Clustering to Localize Across $n$ Possibilities, which helped us win the RoboCup 2024 adult-sized autonomous humanoid soccer competition. Competition rules limited our sensor suite to stereo vision and an inertial sensor, similar to humans. In addition, our robot had to deal with varying lighting conditions, dynamic feature occlusions, noise from high-impact stepping, and mistaken features from bystanders and neighboring fields. Therefore, we needed an accurate, and most importantly robust localization algorithm that would be the foundation for our path-planning and game-strategy algorithms. CLAP achieves these requirements by clustering estimated states of our robot from pairs of field features to localize its global position and orientation. Correct state estimates naturally cluster together, while incorrect estimates spread apart, making CLAP resilient to noise and incorrect inputs. CLAP is paired with a particle filter and an extended Kalman filter to improve consistency and smoothness. Tests of CLAP with other landmark-based localization methods showed similar accuracy. However, tests with increased false positive feature detection showed that CLAP outperformed other methods in terms of robustness with very little divergence and velocity jumps. Our localization performed well in competition, allowing our robot to shoot faraway goals and narrowly defend our goal.
Recent advances in robotics have enabled the widespread deployment of autonomous robotic systems in complex operational environments, presenting both unprecedented opportunities and significant security problems. Traditional shepherding approaches based on fixed formations are often ineffective or risky in urban and obstacle-rich scenarios, especially when facing adversarial agents with unknown and adaptive behaviors. This paper addresses this challenge as an extended herding problem, where defensive robotic systems must safely guide adversarial agents with unknown strategies away from protected areas and into predetermined safe regions, while maintaining collision-free navigation in dynamic environments. We propose a hierarchical hybrid framework based on reach-avoid game theory and local motion planning, incorporating a virtual containment boundary and event-triggered pursuit mechanisms to enable scalable and robust multi-agent coordination. Simulation results demonstrate that the proposed approach achieves safe and efficient guidance of adversarial agents to designated regions.
Diffusion models offer powerful generative capabilities for robot trajectory planning, yet their practical deployment on robots is hindered by a critical bottleneck: a reliance on imitation learning from expert demonstrations. This paradigm is often impractical for specialized robots where data is scarce and creates an inefficient, theoretically suboptimal training pipeline. To overcome this, we introduce PegasusFlow, a hierarchical rolling-denoising framework that enables direct and parallel sampling of trajectory score gradients from environmental interaction, completely bypassing the need for expert data. Our core innovation is a novel sampling algorithm, Weighted Basis Function Optimization (WBFO), which leverages spline basis representations to achieve superior sample efficiency and faster convergence compared to traditional methods like MPPI. The framework is embedded within a scalable, asynchronous parallel simulation architecture that supports massively parallel rollouts for efficient data collection. Extensive experiments on trajectory optimization and robotic navigation tasks demonstrate that our approach, particularly Action-Value WBFO (AVWBFO) combined with a reinforcement learning warm-start, significantly outperforms baselines. In a challenging barrier-crossing task, our method achieved a 100% success rate and was 18% faster than the next-best method, validating its effectiveness for complex terrain locomotion planning. https://masteryip.github.io/pegasusflow.github.io/
This paper presents a planning strategy for the deployment of smart electromagnetic entities (SEEs) to enhance the wireless coverage and the Quality-of-Service (QoS) in large urban areas. The integration of different technological solutions such as integrated access-and-backhaul nodes (IABs), smart repeaters (SRs), and electromagnetic skins (EMSs) is here addressed to enable an effective and efficient implementation of the concept of Smart Electromagnetic Environment (SEME). By combining the features of such heterogeneous SEEs and optimizing their number, positions, orientations, and configuration, the electromagnetic (EM) coverage in a set of Regions-of-Interest (RoIs) of outdoor scenarios is recovered and/or enhanced subject to installation costs and energy consumption requirements. Numerical validations from real-world scenarios are reported to assess the effectiveness of the proposed planning scheme as well as to show the potentialities of an heterogeneous deployment of SEMEs.
Eye tracking (ET) can help to understand visual attention and cognitive processes in interactive environments. This study presents a comprehensive eye-tracking analysis framework of the Inhibitory Control Game, named the ReStroop game, which is an educational intervention aimed at improving inhibitory control skills in children through a recycling-themed sorting task, for educational assessment that processes raw gaze data through unified algorithms for fixation detection, performance evaluation, and personalized intervention planning. The system employs dual-threshold eye movement detection (I-VT and advanced clustering), comprehensive Area of Interest (AOI) analysis, and evidence-based risk assessment to transform gaze patterns into actionable educational insights. We evaluated this framework across three difficulty levels and revealed critical attention deficits, including low task relevance, elevated attention scatter, and compromised processing efficiency. The multi-dimensional risk assessment identified high to moderate risk levels, triggering personalized interventions including focus training, attention regulation support, and environmental modifications. The system successfully distinguishes between adaptive learning and cognitive overload, providing early warning indicators for educational intervention. Results demonstrate the system's effectiveness in objective attention assessment, early risk identification, and the generation of evidence-based recommendations for students, teachers, and specialists, supporting data-driven educational decision-making and personalized learning approaches.
We address the problem of policy selection in contextual stochastic optimization (CSO), where covariates are available as contextual information and decisions must satisfy hard feasibility constraints. In many CSO settings, multiple candidate policies--arising from different modeling paradigms--exhibit heterogeneous performance across the covariate space, with no single policy uniformly dominating. We propose Prescribe-then-Select (PS), a modular framework that first constructs a library of feasible candidate policies and then learns a meta-policy to select the best policy for the observed covariates. We implement the meta-policy using ensembles of Optimal Policy Trees trained via cross-validation on the training set, making policy choice entirely data-driven. Across two benchmark CSO problems--single-stage newsvendor and two-stage shipment planning--PS consistently outperforms the best single policy in heterogeneous regimes of the covariate space and converges to the dominant policy when such heterogeneity is absent. All the code to reproduce the results can be found at https://anonymous.4open.science/r/Prescribe-then-Select-TMLR.
Multi-arm motion planning is fundamental for enabling arms to complete complex long-horizon tasks in shared spaces efficiently but current methods struggle with scalability due to exponential state-space growth and reliance on large training datasets for learned models. Inspired by Multi-Agent Path Finding (MAPF), which decomposes planning into single-agent problems coupled with collision resolution, we propose a novel diffusion-guided multi-arm planner (DG-MAP) that enhances scalability of learning-based models while reducing their reliance on massive multi-arm datasets. Recognizing that collisions are primarily pairwise, we train two conditional diffusion models, one to generate feasible single-arm trajectories, and a second, to model the dual-arm dynamics required for effective pairwise collision resolution. By integrating these specialized generative models within a MAPF-inspired structured decomposition, our planner efficiently scales to larger number of arms. Evaluations against alternative learning-based methods across various team sizes demonstrate our method's effectiveness and practical applicability. Project website can be found at https://diff-mapf-mers.csail.mit.edu
Safe navigation is essential for autonomous systems operating in hazardous environments, especially when multiple agents must coordinate using just visual inputs over extended time horizons. Traditional planning methods excel at solving long-horizon tasks but rely on predefined distance metrics, while safe Reinforcement Learning (RL) can learn complex behaviors using high-dimensional inputs yet struggles with multi-agent, goal-conditioned scenarios. Recent work combined these paradigms by leveraging goal-conditioned RL (GCRL) to build an intermediate graph from replay buffer states, pruning unsafe edges, and using Conflict-Based Search (CBS) for multi-agent path planning. Although effective, this graph-pruning approach can be overly conservative, limiting mission efficiency by precluding missions that must traverse high-risk regions. To address this limitation, we propose RB-CBS, a novel extension to CBS that dynamically allocates and adjusts user-specified risk bound ($\Delta$) across agents to flexibly trade off safety and speed. Our improved planner ensures that each agent receives a local risk budget ($\delta$) enabling more efficient navigation while still respecting overall safety constraints. Experimental results demonstrate that this iterative risk-allocation framework yields superior performance in complex environments, allowing multiple agents to find collision-free paths within the user-specified $\Delta$.
Interactive trajectory planning in autonomous driving must balance safety, efficiency, and scalability under heterogeneous driving behaviors. Existing methods often face high computational cost or rely on external safety critics. To address this, we propose an Interaction-Enriched Unified Potential Field (IUPF) framework that fuses style-dependent benefit and risk fields through a physics-inspired variational model, grounded in mean field game theory. The approach captures conservative, aggressive, and cooperative behaviors without additional safety modules, and employs stochastic differential equations to guarantee Nash equilibrium with exponential convergence. Simulations on lane changing and overtaking scenarios show that IUPF ensures safe distances, generates smooth and efficient trajectories, and outperforms traditional optimization and game-theoretic baselines in both adaptability and computational efficiency.
Federated Learning (FL) is a novel, multidisciplinary Machine Learning paradigm where multiple clients, such as mobile devices, collaborate to solve machine learning problems. Initially introduced in Kone{\v{c}}n{\'y} et al. (2016a,b); McMahan et al. (2017), FL has gained further attention through its inclusion in the National AI Research and Development Strategic Plan (2023 Update) of the United States (Science and on Artificial Intelligence, 2023). The FL training process is inherently decentralized and often takes place in less controlled settings compared to data centers, posing unique challenges distinct from those in fully controlled environments. In this thesis, we identify five key challenges in Federated Learning and propose novel approaches to address them. These challenges arise from the heterogeneity of data and devices, communication issues, and privacy concerns for clients in FL training. Moreover, even well-established theoretical advances in FL require diverse forms of practical implementation to enhance their real-world applicability. Our contributions advance FL algorithms and systems, bridging theoretical advancements and practical implementations. More broadly, our work serves as a guide for researchers navigating the complexities of translating theoretical methods into efficient real-world implementations and software. Additionally, it offers insights into the reverse process of adapting practical implementation aspects back into theoretical algorithm design. This reverse process is particularly intriguing, as the practical perspective compels us to examine the underlying mechanics and flexibilities of algorithms more deeply, often uncovering new dimensions of the algorithms under study.
I present spherical (https://github.com/m-samland/spherical), a software package and database designed for the ESO VLT/SPHERE high-contrast imager. SPHERE has produced the world's largest archive of direct imaging observations of exoplanets and circumstellar disks, but its heterogeneous metadata and fragmented reduction tools make end-to-end analysis labor-intensive. spherical addresses this by combining (1) a curated, regularly updated, and searchable database of all SPHERE observations, cross-matched with stellar properties and observing conditions, and (2) a Python-based, script-driven pipeline for the Integral Field Spectrograph (IFS). The database, archived on Zenodo (https://doi.org/10.5281/zenodo.15147730) and reproducible from the ESO archive, currently includes about 6000 IRDIS dual-band imaging, about 1000 IRDIS polarimetric, and about 4500 IFS sequences, with additional modes (ZIMPOL, IRDIS-LSS, SAM) planned. The pipeline automates raw data retrieval, calibration, and IFS reduction with the adapted open-source CHARIS instrument pipeline, followed by astrometric and photometric calibration and post-processing with TRAP for companion detection and spectral extraction. spherical lowers the barrier from raw files to science-ready products, enabling homogeneous population studies, atmospheric characterization of companions, and efficient survey follow-up, while remaining interoperable with community tools such as VIP, pyKLIP, and IRDAP.
Patient-specific computational models of the heart are powerful tools for cardiovascular research and medicine, with demonstrated applications in treatment planning, device evaluation, and surgical decision-making. Yet constructing such models is inherently difficult, reflecting the extraordinary complexity of the heart itself. Numerous considerations are required, including reconstructing the anatomy from medical images, representing myocardial mesostructure, capturing material behavior, defining model geometry and boundary conditions, coupling multiple physics, and selecting numerical methods. Many of these choices involve a tradeoff between physiological fidelity and modeling complexity. In this review, we summarize recent advances and unresolved questions in each of these areas, with particular emphasis on cardiac tissue mechanics. We argue that clarifying which complexities are essential, and which can be safely simplified, will be key to enabling clinical translation of these models.
Many robotic manipulation tasks require sensing and responding to force signals such as torque to assess whether the task has been successfully completed and to enable closed-loop control. However, current Vision-Language-Action (VLA) models lack the ability to integrate such subtle physical feedback. In this work, we explore Torque-aware VLA models, aiming to bridge this gap by systematically studying the design space for incorporating torque signals into existing VLA architectures. We identify and evaluate several strategies, leading to three key findings. First, introducing torque adapters into the decoder consistently outperforms inserting them into the encoder.Third, inspired by joint prediction and planning paradigms in autonomous driving, we propose predicting torque as an auxiliary output, which further improves performance. This strategy encourages the model to build a physically grounded internal representation of interaction dynamics. Extensive quantitative and qualitative experiments across contact-rich manipulation benchmarks validate our findings.
In heterogeneous multi-task learning, tasks not only exhibit diverse observation and action spaces but also vary substantially in intrinsic difficulty. While conventional multi-task world models like UniZero excel in single-task settings, we find that when handling large-scale heterogeneous environments, gradient conflicts and the loss of model plasticity often constrain their sample and computational efficiency. In this work, we address these challenges from two perspectives: the single learning iteration and the overall learning process. First, we investigate the impact of key design spaces on extending UniZero to multi-task planning. We find that a Mixture-of-Experts (MoE) architecture provides the most substantial performance gains by mitigating gradient conflicts, leading to our proposed model, \textit{ScaleZero}. Second, to dynamically balance the computational load across the learning process, we introduce an online, LoRA-based \textit{dynamic parameter scaling} (DPS) strategy. This strategy progressively integrates LoRA adapters in response to task-specific progress, enabling adaptive knowledge retention and parameter expansion. Empirical evaluations on standard benchmarks such as Atari, DMControl (DMC), and Jericho demonstrate that ScaleZero, relying exclusively on online reinforcement learning with one model, attains performance on par with specialized single-task baselines. Furthermore, when augmented with our dynamic parameter scaling strategy, our method achieves competitive performance while requiring only 80\% of the single-task environment interaction steps. These findings underscore the potential of ScaleZero for effective large-scale multi-task learning. Our code is available at \textcolor{magenta}{https://github.com/opendilab/LightZero}.
Characterization of uncooperative Resident Space Objects (RSO) play a crucial role in On-Orbit Servicing (OOS) and Active Debris Removal (ADR) missions to assess the geometry and motion properties. To address the challenges of reconstructing tumbling uncooperative targets, this study evaluates the performance of existing state-of-the-art 3D reconstruction algorithms for dynamic scenes, focusing on their ability to generate geometrically accurate models with high-fidelity. To support our evaluation, we developed a simulation environment using Isaac Sim to generate physics-accurate 2D image sequences of tumbling satellite under realistic orbital lighting conditions. Our preliminary results on static scenes using Neuralangelo demonstrate promising reconstruction quality. The generated 3D meshes closely match the original CAD models with minimal errors and artifacts when compared using Cloud Compare (CC). The reconstructed models were able to capture critical fine details for mission planning. This provides a baseline for our ongoing evaluation of dynamic scene reconstruction.
Stroke is the second most frequent cause of death world wide with an annual mortality of around 5.5 million. Recurrence rates of stroke are between 5 and 25% in the first year. As mortality rates for relapses are extraordinarily high (40%) it is of utmost importance to reduce the recurrence rates. We address this issue by detecting patients at risk of stroke recurrence at an early stage in order to enable appropriate therapy planning. To this end we collected 3D intracranial CTA image data and recorded concomitant heart diseases, the age and the gender of stroke patients between 2010 and 2024. We trained single- and multimodal deep learning based neural networks for binary relapse detection (Task 1) and for relapse free survival (RFS) time prediction together with a subsequent classification (Task 2). The separation of relapse from non-relapse patients (Task 1) could be solved with tabular data (AUC on test dataset: 0.84). However, for the main task, the regression (Task 2), our multimodal XSRD-net processed the modalities vision:tabular with 0.68:0.32 according to modality contribution measures. The c-index with respect to relapses for the multimodal model reached 0.68, and the AUC is 0.71 for the test dataset. Final, deeper interpretability analysis results could highlight a link between both heart diseases (tabular) and carotid arteries (vision) for the detection of relapses and the prediction of the RFS time. This is a central outcome that we strive to strengthen with ongoing data collection and model retraining.
Neurosymbolic AI (NeSy) aims to integrate the statistical strengths of neural networks with the interpretability and structure of symbolic reasoning. However, current NeSy frameworks like DeepProbLog enforce a fixed flow where symbolic reasoning always follows neural processing. This restricts their ability to model complex dependencies, especially in irregular data structures such as graphs. In this work, we introduce DeepGraphLog, a novel NeSy framework that extends ProbLog with Graph Neural Predicates. DeepGraphLog enables multi-layer neural-symbolic reasoning, allowing neural and symbolic components to be layered in arbitrary order. In contrast to DeepProbLog, which cannot handle symbolic reasoning via neural methods, DeepGraphLog treats symbolic representations as graphs, enabling them to be processed by Graph Neural Networks (GNNs). We showcase the capabilities of DeepGraphLog on tasks in planning, knowledge graph completion with distant supervision, and GNN expressivity. Our results demonstrate that DeepGraphLog effectively captures complex relational dependencies, overcoming key limitations of existing NeSy systems. By broadening the applicability of neurosymbolic AI to graph-structured domains, DeepGraphLog offers a more expressive and flexible framework for neural-symbolic integration.
Efficient exploration of unknown environments is crucial for autonomous robots, especially in confined and large-scale scenarios with limited communication. To address this challenge, we propose a collaborative exploration framework for a marsupial ground-aerial robot team that leverages the complementary capabilities of both platforms. The framework employs a graph-based path planning algorithm to guide exploration and deploy the aerial robot in areas where its expected gain significantly exceeds that of the ground robot, such as large open spaces or regions inaccessible to the ground platform, thereby maximizing coverage and efficiency. To facilitate large-scale spatial information sharing, we introduce a bandwidth-efficient, task-driven map compression strategy. This method enables each robot to reconstruct resolution-specific volumetric maps while preserving exploration-critical details, even at high compression rates. By selectively compressing and sharing key data, communication overhead is minimized, ensuring effective map integration for collaborative path planning. Simulation and real-world experiments validate the proposed approach, demonstrating its effectiveness in improving exploration efficiency while significantly reducing data transmission.
In robots task and motion planning (TAMP), it is crucial to sample within the robot's configuration space to meet task-level global constraints and enhance the efficiency of subsequent motion planning. Due to the complexity of joint configuration sampling under multi-level constraints, traditional methods often lack efficiency. This paper introduces the principle of RobKiNet, a kinematics-informed neural network, for end-to-end sampling within the Continuous Feasible Set (CFS) under multiple constraints in configuration space, establishing its Optimization Expectation Model. Comparisons with traditional sampling and learning-based approaches reveal that RobKiNet's kinematic knowledge infusion enhances training efficiency by ensuring stable and accurate gradient optimization.Visualizations and quantitative analyses in a 2-DOF space validate its theoretical efficiency, while its application on a 9-DOF autonomous mobile manipulator robot(AMMR) demonstrates superior whole-body and decoupled control, excelling in battery disassembly tasks. RobKiNet outperforms deep reinforcement learning with a training speed 74.29 times faster and a sampling accuracy of up to 99.25%, achieving a 97.33% task completion rate in real-world scenarios.
K2-Think is a reasoning system that achieves state-of-the-art performance with a 32B parameter model, matching or surpassing much larger models like GPT-OSS 120B and DeepSeek v3.1. Built on the Qwen2.5 base model, our system shows that smaller models can compete at the highest levels by combining advanced post-training and test-time computation techniques. The approach is based on six key technical pillars: Long Chain-of-thought Supervised Finetuning, Reinforcement Learning with Verifiable Rewards (RLVR), Agentic planning prior to reasoning, Test-time Scaling, Speculative Decoding, and Inference-optimized Hardware, all using publicly available open-source datasets. K2-Think excels in mathematical reasoning, achieving state-of-the-art scores on public benchmarks for open-source models, while also performing strongly in other areas such as Code and Science. Our results confirm that a more parameter-efficient model like K2-Think 32B can compete with state-of-the-art systems through an integrated post-training recipe that includes long chain-of-thought training and strategic inference-time enhancements, making open-source reasoning systems more accessible and affordable. K2-Think is freely available at k2think.ai, offering best-in-class inference speeds of over 2,000 tokens per second per request via the Cerebras Wafer-Scale Engine.
Clinical trials with time-to-event endpoints, such as overall survival (OS) or progression-free survival (PFS), are fundamental for evaluating new treatments, particularly in immuno-oncology. However, modern therapies, such as immunotherapies and targeted treatments, often exhibit delayed effects that challenge traditional trial designs. These delayed effects violate the proportional hazards assumption, which underpins standard statistical methods like the Cox proportional hazards model and the log-rank test. Careful planning is essential to ensure trials are appropriately designed to account for the timing and magnitude of these effects. Without this planning, interim analyses may lead to premature trial termination if the treatment effect is underestimated early in the study. We present an adaptive trial design framework that incorporates prior distributions, elicited from experts, for delayed treatment effects. By addressing the uncertainty surrounding delayed treatment effects, our approach enhances trial efficiency and robustness, minimizing the risk of premature termination and improving the detection of treatment benefits over time. We present an example illustrating how interim analyses, informed by prior distributions, can guide early stopping decisions. To facilitate the implementation of our framework, we have developed free, open-source software that enables researchers to integrate prior distributions into trial planning and decision-making. This software provides a flexible, accessible tool for designing trials that more accurately evaluate modern therapies through adaptive trial designs.
We study the shipper-side design of large-scale inbound transportation networks, motivated by Renault's global supply chain. We introduce the Shipper Transportation Design Problem, which integrates consolidation, routing, and regularity constraints, and propose a tailored Iterated Local Search (ILS) metaheuristic. The algorithm combines large-neighborhood search with MILP-based perturbations and exploits bundle-specific decompositions and giant container bounds to obtain scalable lower bounds and effective benchmarks. Computational experiments on real industrial data show that the ILS achieves an average gap of 7.9% to the best available lower bound on world-scale instances with more than 700,000 commodities and 1,200,000 arcs, delivering solutions showing a potential of 23.2% cost reduction compared to the Renault-based benchmark. To our knowledge, this is the first approach to solve shipper-side transportation design problems at such scale. Our analysis further yields managerial insights: accurate bin-packing models are essential for realistic consolidation, highly regular plans offer the best balance between cost and operational stability, and outsourcing is only attractive in low-volume contexts, while large-scale networks benefit from in-house planning.