The autonomy and adaptability of (Lethal) Autonomous Weapons Systems, (L)AWS in short, promise unprecedented operational capabilities, but they also introduce profound risks that challenge the principles of control, accountability, and stability in international security. This report outlines the key technological risks associated with (L)AWS deployment, emphasizing their unpredictability, lack of transparency, and operational unreliability, which can lead to severe unintended consequences. Key Takeaways: 1. Proposed advantages of (L)AWS can only be achieved through objectification and classification, but a range of systematic risks limit the reliability and predictability of classifying algorithms. 2. These systematic risks include the black-box nature of AI decision-making, susceptibility to reward hacking, goal misgeneralization and potential for emergent behaviors that escape human control. 3. (L)AWS could act in ways that are not just unexpected but also uncontrollable, undermining mission objectives and potentially escalating conflicts. 4. Even rigorously tested systems may behave unpredictably and harmfully in real-world conditions, jeopardizing both strategic stability and humanitarian principles.

Simulation frameworks play a pivotal role in the safe development of robotic applications. However, often different components of an envisioned robotic system are best simulated in different environments/simulators. This poses a significant challenge in simulating the entire project into a single integrated robotic framework. Specifically, for partially-open or closed-source simulators, often two core limitations arise. i) Actors in the scene other than the designated robots cannot be controlled during runtime via interfaces such as ROS and ii) retrieving real-time state information (such as pose, velocity etc.) of objects in the scene is prevented. In this work, we address these limitations and describe our solution for the use case of integrating aerial drones simulated by the powerful simulator Sphinx (provided by Parrot Drone) into the Gazebo simulator. We achieve this by means of a mirrored instance of a drone that is included into existing Gazebo-based environments. A promising application of our integrated simulation environment is the task of target tracking that is common in aerial multi-robot scenarios. Therefore, to demonstrate the effectiveness our our integrated simulation, we also implement a model predictive controller (MPC) that outperforms the default PID-based controller framework provided with the Parrot's popular Anafi drone in various dynamic tracking scenarios thus enhancing the utility of the overall system. We test our solution by including the Anafi drone in an existing Gazebo-based simulation and evaluate the performance of the MPC through rigorous testing in simulated and real-world tracking experiments against a customized PID controller baseline. Source code is published on https://github.com/robot-perception-group/anafi_sim.

We introduce Agent Process Reward Models (AgentPRM), a simple and scalable framework for training LLM agents to continually improve through interactions. AgentPRM follows a lightweight actor-critic paradigm, using Monte Carlo rollouts to compute reward targets and optimize policies. It requires minimal modifications to existing RLHF pipelines, making it easy to integrate at scale. Beyond AgentPRM, we propose InversePRM, which learns process rewards directly from demonstrations without explicit outcome supervision. We also explore key challenges and opportunities, including exploration, process reward shaping, and model-predictive reasoning. We evaluate on ALFWorld benchmark, show that small 3B models trained with AgentPRM and InversePRM outperform strong GPT-4o baselines, and analyze test-time scaling, reward hacking, and more.

In this book, written in Portuguese, we discuss what ill-posed problems are and how the regularization method is used to solve them. In the form of questions and answers, we reflect on the origins and future of regularization, relating the similarities and differences of its meaning in different areas, including inverse problems, statistics, machine learning, and deep learning.

Across many domains of science, stochastic models are an essential tool to understand the mechanisms underlying empirically observed data. Models can be of different levels of detail and accuracy, with models of high-fidelity (i.e., high accuracy) to the phenomena under study being often preferable. However, inferring parameters of high-fidelity models via simulation-based inference is challenging, especially when the simulator is computationally expensive. We introduce MF-NPE, a multifidelity approach to neural posterior estimation that leverages inexpensive low-fidelity simulations to infer parameters of high-fidelity simulators within a limited simulation budget. MF-NPE performs neural posterior estimation with limited high-fidelity resources by virtue of transfer learning, with the ability to prioritize individual observations using active learning. On one statistical task with analytical ground-truth and two real-world tasks, MF-NPE shows comparable performance to current approaches while requiring up to two orders of magnitude fewer high-fidelity simulations. Overall, MF-NPE opens new opportunities to perform efficient Bayesian inference on computationally expensive simulators.

Long-term time series forecasting is critical in domains such as finance, economics, and energy, where accurate and reliable predictions over extended horizons drive strategic decision-making. Despite the progress in machine learning-based models, the impact of temporal noise in extended lookback windows remains underexplored, often degrading model performance and computational efficiency. In this paper, we propose a novel framework that addresses these challenges by integrating the Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) to perform noise reduction and extract robust long-term features. These transformations enable the separation of meaningful temporal patterns from noise in both the time and frequency domains. To complement this, we introduce a lightweight low-rank linear prediction layer that not only reduces the influence of residual noise but also improves memory efficiency. Our approach demonstrates competitive robustness to noisy input, significantly reduces computational complexity, and achieves competitive or state-of-the-art forecasting performance across diverse benchmark datasets. Extensive experiments reveal that the proposed framework is particularly effective in scenarios with high noise levels or irregular patterns, making it well suited for real-world forecasting tasks. The code is available in https://github.com/forgee-master/HADL.

Large Language Models (LLMs) employ three popular training approaches: Masked Language Models (MLM), Causal Language Models (CLM), and Sequence-to-Sequence Models (seq2seq). However, each approach has its strengths and limitations, and faces challenges in addressing specific tasks that require controllable and bidirectional generation, such as drug optimization. To address this challenge, inspired by the biological processes of growth and evolution, which involve the expansion, shrinking, and mutation of sequences, we introduce ControllableGPT. This initiative represents the first effort to combine the advantages of MLM, CLM, and seq2seq into a single unified, controllable GPT framework. It enables the precise management of specific locations and ranges within a sequence, allowing for expansion, reduction, or mutation over chosen or random lengths, while maintaining the integrity of any specified positions or subsequences. In this work, we designed ControllableGPT for drug optimization from the ground up, which included proposing the Causally Masked Seq2seq (CMS) objective, developing the training corpus, introducing a novel pre-training approach, and devising a unique generation process. We demonstrate the effectiveness and controllability of ControllableGPT by conducting experiments on drug optimization tasks for both viral and cancer benchmarks, surpassing competing baselines.

Approximating a probability distribution using a set of particles is a fundamental problem in machine learning and statistics, with applications including clustering and quantization. Formally, we seek a finite weighted mixture of Dirac measures that best approximates the target distribution. While much existing work relies on the Wasserstein distance to quantify approximation errors, maximum mean discrepancy (MMD) has received comparatively less attention, especially when allowing for variable particle weights. We study the quantization problem from the perspective of minimizing MMD via gradient flow in the Wasserstein-Fisher-Rao (WFR) geometry. This gradient flow yields an ODE system from which we further derive a fixed-point algorithm called mean shift interacting particles (MSIP). We show that MSIP extends the (non-interacting) mean shift algorithm, widely used for identifying modes in kernel density estimates. Moreover, we show that MSIP can be interpreted as preconditioned gradient descent, and that it acts as a relaxation of Lloyd's algorithm for clustering. Our numerical experiments demonstrate that MSIP and the WFR ODEs outperform other algorithms for quantization of multi-modal and high-dimensional targets.

Soft machines are poised to deliver significant real-world impact, with soft robotics emerging as a key sub-discipline. This field integrates biological inspiration, materials science, and embodied intelligence to create bio-robotic hybrids, blurring the boundary between engineered systems and biology. Over the past 15 years, research in fluidically controlled soft robots has led to commercialised systems that leverage "softness" to improve human-machine interaction or to handle delicate objects. However, translating laboratory advancements into scalable applications remains challenging due to difficulties in prototyping and manufacturing ultra-flexible materials, as well as the absence of standardised design processes. Here we show that the Flex Printer, an open-source, low-cost FDM platform, enables reliable printing of ultra-flexible soft robots with embedded fluidic logic. By employing an innovative upside-down print orientation, the system significantly expands the range of printable geometries. We demonstrate how this approach allows robots to autonomously walk off the print bed immediately after fabrication - a milestone achievement in soft robotics. This work provides a foundation for standardisation and scalable manufacturing, critical for accelerating the field's impact. More broadly, by lowering barriers to entry, this platform has the potential to democratise soft robotics research and facilitate the development of new applications. We invite the community to contribute to the shared development of this technology to drive the next wave of breakthroughs in soft robotics.

Efficient GPU kernels are crucial for building performant machine learning architectures, but writing them is a time-consuming challenge that requires significant expertise; therefore, we explore using language models (LMs) to automate kernel generation. We introduce KernelBench, an open-source framework for evaluating LMs' ability to write fast and correct kernels on a suite of 250 carefully selected PyTorch ML workloads. KernelBench represents a real-world engineering environment and making progress on the introduced benchmark directly translates to faster practical kernels. We introduce a new evaluation metric fast_p, which measures the percentage of generated kernels that are functionally correct and offer a speedup greater than an adjustable threshold p over baseline. Our experiments across various state-of-the-art models and test-time methods show that frontier reasoning models perform the best out of the box but still fall short overall, matching the PyTorch baseline in less than 20% of the cases. While we show that results can improve by leveraging execution and profiling feedback during iterative refinement, KernelBench remains a challenging benchmark, with its difficulty increasing as we raise speedup threshold p.