Plus: Meta has taken down a group dedicated to tracking ICE officers' movements An emerging field of science is seeking to use cell analysis to predict what kind of a person an embryo might eventually become. Some parents turn to these tests to avoid passing on devastating genetic disorders that run in their families. A much smaller group, driven by dreams of Ivy League diplomas or attractive, well-behaved offspring, are willing to pay tens of thousands of dollars to optimize for intelligence, appearance, and personality. But customers of the companies emerging to provide it to the public may not be getting what they're paying for. This story is from our forthcoming print issue, which is all about the body. Plus, you'll also receive a free digital report on nuclear power.

Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hidden information within seemingly benign generations. In this paper, we evaluate the steganography capabilities in frontier LLMs to better understand the risk they pose. We focus on two types of steganography: passing encoded messages and performing encoded reasoning. We find that current models are unable to encode short messages in their outputs without a monitor noticing under standard affordances. They can succeed, however, if given additional affordances like using an unmonitored scratchpad and coordinating on what encoding scheme to use. We additionally find early signs that models can perform basic encoded reasoning in a simple state-tracking problem. This includes some ability to reason with their own and pre-defined schemes, including encoding schemes such as Hexadecimal. Despite this, they can rarely hide reasoning subtly within a cover task to fool a monitor. Overall, our results indicate that current LLMs exhibit nascent steganographic capabilities. While these capabilities are likely insufficient to bypass well-designed monitors at present, this could change in the future.

Driving simulation plays a crucial role in developing reliable driving agents by providing controlled, evaluative environments. To enable meaningful assessments, a high-quality driving simulator must satisfy several key requirements: multi-modal sensing capabilities (e.g., camera and LiDAR) with realistic scene rendering to minimize observational discrepancies; closed-loop evaluation to support free-form trajectory behaviors; highly diverse traffic scenarios for thorough evaluation; multi-agent cooperation to capture interaction dynamics; and high computational efficiency to ensure affordability and scalability. However, existing simulators and benchmarks fail to comprehensively meet these fundamental criteria. To bridge this gap, this paper introduces RealEngine, a novel driving simulation framework that holistically integrates 3D scene reconstruction and novel view synthesis techniques to achieve realistic and flexible closed-loop simulation in the driving context. By leveraging real-world multi-modal sensor data, RealEngine reconstructs background scenes and foreground traffic participants separately, allowing for highly diverse and realistic traffic scenarios through flexible scene composition. This synergistic fusion of scene reconstruction and view synthesis enables photorealistic rendering across multiple sensor modalities, ensuring both perceptual fidelity and geometric accuracy. Building upon this environment, RealEngine supports three essential driving simulation categories: non-reactive simulation, safety testing, and multi-agent interaction, collectively forming a reliable and comprehensive benchmark for evaluating the real-world performance of driving agents.

Unmanned Aerial Vehicles (UAVs) are increasingly being utilized in various private and commercial applications, e.g., traffic control, parcel delivery, and Search and Rescue (SAR) missions. Machine Learning (ML) methods used in UAV-Assisted Sensor Networks (UASNETs) and, especially, in Deep Reinforcement Learning (DRL) face challenges such as complex and lengthy model training, gaps between simulation and reality, and low sampling efficiency, which conflict with the urgency of emergencies, such as SAR missions. In this paper, an In-Context Learning (ICL)-Data Collection Scheduling (ICLDC) system is proposed as an alternative to DRL in emergencies. The UAV collects sensory data and transmits it to a Large Language Model (LLM), which creates a task description in natural language. From this description, the UAV receives a data collection schedule that must be executed. A verifier ensures safe UAV operations by evaluating the schedules generated by the LLM and overriding unsafe schedules based on predefined rules. The system continuously adapts by incorporating feedback into the task descriptions and using this for future decisions. This method is tested against jailbreaking attacks, where the task description is manipulated to undermine network performance, highlighting the vulnerability of LLMs to such attacks. The proposed ICLDC significantly reduces cumulative packet loss compared to both the DQN and Maximum Channel Gain baselines. ICLDC presents a promising direction for intelligent scheduling and control in UASNETs.

The increasing number of satellites and orbital debris has made space congestion a critical issue, threatening satellite safety and sustainability. Challenges such as collision avoidance, station-keeping, and orbital maneuvering require advanced techniques to handle dynamic uncertainties and multi-agent interactions. Reinforcement learning (RL) has shown promise in this domain, enabling adaptive, autonomous policies for space operations; however, many existing RL frameworks rely on custom-built environments developed from scratch, which often use simplified models and require significant time to implement and validate the orbital dynamics, limiting their ability to fully capture real-world complexities. To address this, we introduce OrbitZoo, a versatile multi-agent RL environment built on a high-fidelity industry standard library, that enables realistic data generation, supports scenarios like collision avoidance and cooperative maneuvers, and ensures robust and accurate orbital dynamics. The environment is validated against a real satellite constellation, Starlink, achieving a Mean Absolute Percentage Error (MAPE) of 0.16% compared to real-world data. This validation ensures reliability for generating high-fidelity simulations and enabling autonomous and independent satellite operations.

Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion methods and VLMs in the field of robot vision. For semantic scene understanding tasks, we categorize fusion approaches into encoder-decoder frameworks, attention-based architectures, and graph neural networks. Meanwhile, we also analyze the architectural characteristics and practical implementations of these fusion strategies in key tasks such as simultaneous localization and mapping (SLAM), 3D object detection, navigation, and manipulation. We compare the evolutionary paths and applicability of VLMs based on large language models (LLMs) with traditional multimodal fusion methods.Additionally, we conduct an in-depth analysis of commonly used datasets, evaluating their applicability and challenges in real-world robotic scenarios. Building on this analysis, we identify key challenges in current research, including cross-modal alignment, efficient fusion, real-time deployment, and domain adaptation. We propose future directions such as self-supervised learning for robust multimodal representations, structured spatial memory and environment modeling to enhance spatial intelligence, and the integration of adversarial robustness and human feedback mechanisms to enable ethically aligned system deployment. Through a comprehensive review, comparative analysis, and forward-looking discussion, we provide a valuable reference for advancing multimodal perception and interaction in robotic vision. A comprehensive list of studies in this survey is available at https://github.com/Xiaofeng-Han-Res/MF-RV.

Accurate and scalable machine-learned inter-atomic potentials (MLIPs) are essential for molecular simulations ranging from drug discovery to new material design. Current state-of-the-art models enforce roto-translational symmetries through equivariant neural network architectures, a hard-wired inductive bias that can often lead to reduced flexibility, computational efficiency, and scalability. In this work, we introduce TransIP: Transformer-based Inter-Atomic Potentials, a novel training paradigm for interatomic potentials achieving symmetry compliance without explicit architectural constraints. Our approach guides a generic non-equivariant Transformer-based model to learn SO(3)-equivariance by optimizing its representations in the embedding space. Trained on the recent Open Molecules (OMol25) collection, a large and diverse molecular dataset built specifically for MLIPs and covering different types of molecules (including small organics, biomolecular fragments, and electrolyte-like species), TransIP effectively learns symmetry in its latent space, providing low equivariance error. Further, compared to a data augmentation baseline, TransIP achieves 40% to 60% improvement in performance across varying OMol25 dataset sizes. More broadly, our work shows that learned equivariance can be a powerful and efficient alternative to augmentation-based MLIP models.

Forecasting urban phenomena such as housing prices and public health indicators requires the effective integration of various geospatial data. Current methods primarily utilize task-specific models, while recent foundation models for spatial representations often support only limited modalities and lack multimodal fusion capabilities. To overcome these challenges, we present UrbanFusion, a Geo-Foundation Model (GeoFM) that features Stochastic Multimodal Fusion (SMF). The framework employs modality-specific encoders to process different types of inputs, including street view imagery, remote sensing data, cartographic maps, and points of interest (POIs) data. These multimodal inputs are integrated via a Transformer-based fusion module that learns unified representations. An extensive evaluation across 41 tasks in 56 cities worldwide demonstrates UrbanFusion's strong generalization and predictive performance compared to state-of-the-art GeoAI models. Specifically, it 1) outperforms prior foundation models on location-encoding, 2) allows multimodal input during inference, and 3) generalizes well to regions unseen during training. UrbanFusion can flexibly utilize any subset of available modalities for a given location during both pretraining and inference, enabling broad applicability across diverse data availability scenarios. All source code is available at https://github.com/DominikM198/UrbanFusion.

Machine learning solvers for partial differential equations (PDEs) have attracted growing interest. However, most existing approaches, such as neural network solvers, rely on stochastic training, which is inefficient and typically requires a great many training epochs. Gaussian process (GP)/kernel-based solvers, while mathematical principled, suffer from scalability issues when handling large numbers of collocation points often needed for challenging or higher-dimensional PDEs. To overcome these limitations, we propose TGPS, a tensor-GP-based solver that models factor functions along each input dimension using one-dimensional GPs and combines them via tensor decomposition to approximate the full solution. This design reduces the task to learning a collection of one-dimensional GPs, substantially lowering computational complexity, and enabling scalability to massive collocation sets. For efficient nonlinear PDE solving, we use a partial freezing strategy and Newton's method to linerize the nonlinear terms. We then develop an alternating least squares (ALS) approach that admits closed-form updates, thereby substantially enhancing the training efficiency. We establish theoretical guarantees on the expressivity of our model, together with convergence proof and error analysis under standard regularity assumptions. Experiments on several benchmark PDEs demonstrate that our method achieves superior accuracy and efficiency compared to existing approaches.

Abstract--Spiking Neural Networks are attracting increased attention as a more energy-efficient alternative to traditional Artificial Neural Networks for edge computing. Neuromorphic computing can significantly reduce energy requirements. Here, we present a complete pipeline: efficient event-based training of SNNs with synaptic delays on GPUs and deployment on Intel's Loihi 2 neuromorphic chip. We evaluate our approach on keyword recognition tasks using the Spiking Heidelberg Digits and Spiking Speech Commands datasets, demonstrating that our algorithm can enhance classification accuracy compared to architectures without delays. Our benchmarking indicates almost no accuracy loss between GPU and Loihi 2 implementations, while classification on Loihi 2 is up to 18 faster and uses 250 less energy than on an NVIDIA Jetson Orin Nano.