This paper introduces DIM-WAM, a memory-augmented world-action model that integrates multi-scale historical context, local future dynamics, and global task progress, significantly improving success rates in long-horizon robot manipulation tasks. On RMBench, average success increases from 28.4% to 69.8%, and on real-world Franka tasks, stage success rises from 70.7% to 91.5%.

A new framework, CWI, decouples motion capture data for upper and lower body to improve whole-body coordination in humanoid robots. It achieves stable locomotion and versatile manipulation without full-body MoCap equipment.

A new method injects a 3D point representation directly into the action head of VLA models, achieving large improvements in spatial and task generalization with a simple two-layer MLP.

This paper presents Parallel ARC (P-ARC), a parallel variant of the Adaptive Robot Coordination (ARC) approach to multi-robot motion planning (MRMP). P-ARC proposes a parallel variant for each of the three main stages in ARC: initial individual solutions, conflict detection, and conflict resolution, exploiting the independence created by ARC's decomposition of the MRMP problem. Additionally, we employ an OR-parallel multi-start strategy to both ARC and P-ARC, creating a hybrid parallel strategy OR-P-ARC. We evaluate the impact of the different parallel strategies for ARC using a set of scaling 2D mobile and planar manipulator scenarios with up to 128 robots to control for conflicts and work distribution across the stages of ARC. Additionally, we demonstrate planning time speedups approach…

This paper presents an automation framework for robotic radiation source localization (RSL) using physics-informed machine learning (PIML). It enables precise source estimation without requiring the robot to approach the source, reducing radiation damage risk. Physics-inspired tensors handle gamma-ray attenuation from unknown obstacles, and parallel model computation improves robustness. Evaluated via high-fidelity Monte Carlo simulations and physical experiments, the method also incorporates continuous learning for real-world deployment.

A hybrid simulation framework couples a high-fidelity quadrotor model with a physics solver to train an RL policy that, deployed zero-shot on hardware, reduces landing error by 50% and throw duration by 30%. Visual-based policies achieve comparable accuracy.

SceneBot is a unified motion-tracking framework for humanoids that handles free-space locomotion, terrain traversal, and whole-body manipulation. By conditioning a single policy on both reference motions and per-link contact labels, it explicitly defines expected environmental interactions. To address the lack of annotated interaction data, the authors propose a hindsight scene reconstruction approach that infers scene-interaction graphs from retargeted human motion. Trained on 7.5 hours of reconstructed contact-rich data, SceneBot generalizes to unseen motions and environments, enabling complex long-horizon tasks like carrying a box upstairs. It is the first general framework to seamlessly unify free-space and contact-rich behaviors.

Existing fiducial markers are mostly single-scale and designed for terrestrial robotics, leaving the camera's field of view at close range during critical proximity and docking phases. This paper presents AstraTag, a fiducial marker based on a square Spidron pattern with recursive self-similar structure enabling multi-scale detection, 48-bit identification encoded with Generalized Reed-Solomon code, and Thin-Plate Spline re-warp for curved surfaces. Benchmarked on spacecraft mockups, AstraTag achieves higher detection rate on curved surfaces than three-layer Fractal ArUco and AprilTag, offering a robust recursive-marker option for space robotics.

A new anytime multi-robot motion planning method, AO-ARC, achieves initial solution times on par with state-of-the-art feasibility solvers while converging faster and more reliably as the number of robots grows. It adapts the AO-x meta-algorithm by iteratively calling ARC on bounded instances, proving asymptotic optimality.

SCORE framework constrains RL in simulation to the support of a generative policy pretrained on real data, improving manipulation success rate from 37.8% to 89.9% without real-world training.

TTE is a learnable location encoder using Spherical Voronoi partitions to focus capacity on discriminative regions and global semantic tokens for sharing semantics across similar environments, achieving state-of-the-art on geospatial tasks.

This paper introduces Structured-Li-GS, a lightweight Gaussian Splatting pipeline that integrates LiDAR-inertial-visual SLAM. It achieves high-quality 3D reconstructions with fewer Gaussians by training on accurate, dense, colorized point clouds, without requiring Gaussian densification. Multiple loss functions guide the training, producing up-to-scale, high-fidelity results. Experiments on benchmark and in-house datasets surpass state-of-the-art methods.

TruEye is a novel model for fine-grained detection and localization of AI-generated or manipulated humans and scenes, distinguishing among five compositional categories of synthetic content. It runs over 100x faster than LLM-based competitors and outperforms state-of-the-art detectors on multiple datasets.

ReWorld is the first representation learning framework specifically designed for autonomous-driving world action models. It directly optimizes intermediate representations along three dimensions: future-predictive supervision on the generation module, cross-modal alignment and hard-negative supervision on the planning module. Experiments on nuScenes and NAVSIM show significant improvements in video generation quality and closed-loop planning performance, along with faster convergence.

Aloe-Vision introduces a family of open-source medical vision-language models trained on a large-scale quality-filtered dataset, achieving balanced performance and exposing vulnerabilities to adversarial inputs.