Fully automated self-driving laboratories are promising to enable high-throughput and large-scale scientific discovery by reducing repetitive labour. However, effective automation requires deep integration of laboratory knowledge, which is often unstructured, multimodal, and difficult to incorporate into current AI systems. This paper introduces the k-agents framework, designed to support experimentalists in organizing laboratory knowledge and automating experiments with agents. Our framework employs large language model-based agents to encapsulate laboratory knowledge including available laboratory operations and methods for analyzing experiment results. To automate experiments, we introduce execution agents that break multi-step experimental procedures into state machines, interact with other agents to execute each step and analyze the experiment results. The analyzed results are then utilized to drive state transitions, enabling closed-loop feedback control. To demonstrate its capabilities, we applied the agents to calibrate and operate a superconducting quantum processor, where they autonomously planned and executed experiments for hours, successfully producing and characterizing entangled quantum states at the level achieved by human scientists. Our knowledge-based agent system opens up new possibilities for managing laboratory knowledge and accelerating scientific discovery.

This paper introduces a novel approach to detect and address faulty or corrupted external sensors in the context of inertial navigation by leveraging a switching Kalman Filter combined with parameter augmentation. Instead of discarding the corrupted data, the proposed method retains and processes it, running multiple observation models simultaneously and evaluating their likelihoods to accurately identify the true state of the system. We demonstrate the effectiveness of this approach to both identify the moment that a sensor becomes faulty and to correct for the resulting sensor behavior to maintain accurate estimates. We demonstrate our approach on an application of balloon navigation in the atmosphere and shuttle reentry. The results show that our method can accurately recover the true system state even in the presence of significant sensor bias, thereby improving the robustness and reliability of state estimation systems under challenging conditions. We also provide a statistical analysis of problem settings to determine when and where our method is most accurate and where it fails.

This paper introduces lateral thinking to implement System-2 reasoning capabilities in AI systems, focusing on anticipatory and causal reasoning under uncertainty. We present a framework for systematic generation and modeling of lateral thinking queries and evaluation datasets. We introduce Streaming Agentic Lateral Thinking (SALT), a multi-agent framework designed to process complex, low-specificity queries in streaming data environments. SALT implements lateral thinking-inspired System-2 reasoning through a dynamic communication structure between specialized agents. Our key insight is that lateral information flow across long-distance agent interactions, combined with fine-grained belief management, yields richer information contexts and enhanced reasoning. Preliminary quantitative and qualitative evaluations indicate SALT's potential to outperform single-agent systems in handling complex lateral reasoning tasks in a streaming environment.

In 1988, we launched the Best of What's New Awards. The original list highlighted "the very things that make our lives more comfortable, more rewarding, more exciting, and more fun," to quote then-Publisher Grant A. Burnett. Now, in 2024, we continue our decades-old tradition of honoring big ideas. We even see hints of our original honorees in this year's list: Sea-Doo and Ford made both lists, 36 years apart. We're proud to bring you promising innovations--from things that make life at home easier to literal out-of-this-world explorations. This is the Best of What's New 2024. Had you asked me at the beginning of 2024 what our best gadgets list would look like, I'd have guessed it would be filled with quirky AI-driven devices like the rabbit R1 or the Humane Ai Pin. "Now with AI" is a phrase that has dominated consumer electronics in the 2020s. These devices promised unadulterated access to the power of neural networks in ways that would seamlessly integrate into our lives without relying on phones or smart fridges. Then, the devices came out. The software is slow and buggy, and the hardware is clunky. Maybe the stand-alone AI device will still have its year, and we'll look back and chuckle at these humble beginnings. In reality, 2024's big breakthrough came from Apple in the form of its long-rumored Vision Pro headset. The device has its own hurdles to clear, but after just a few minutes of using it, it was clear that it's something different, important, and honestly pretty amazing. The list also includes Sony's innovative pro-grade camera, the most accessible drone we've ever used, and a no-fun phone--no fun in a good way, of course. Credible rumors of Apple's VR bounced around the gadget blogs and tech sites for nearly a decade. It was consumer tech's sasquatch in that people claimed to have seen it, but no one knew if it even existed. Then, the Vision Pro emerged from the proverbial forest in February with a surprising design and a massive 3,500 price tag. It also came toting a new R-series chip and a dedicated OS meant for spatial computing.

Getting caught out in the rain might soon be a thing of the past thanks to a powerful new AI weather forecaster. Google DeepMind has unveiled an AI-powered weather model called GenCast which it claims is faster and more accurate than traditional forecasts. Compared to the top-performing supercomputer Google's GenCast model was more accurate across 99.8 per cent of predictions up to 15 days in advance. According to Google, this will not only help commuters decide whether to bring an umbrella but also spot natural disasters like Typhoons before it is too late. Normally, weather agencies like the Met Office predict the weather by using huge supercomputers to crunch the complex maths which simulates the climate.

Generative models can now produce photorealistic synthetic data which is virtually indistinguishable from the real data used to train it. This is a significant evolution over previous models which could produce reasonable facsimiles of the training data, but ones which could be visually distinguished from the training data by human evaluation. Recent work on OOD detection has raised doubts that generative model likelihoods are optimal OOD detectors due to issues involving likelihood misestimation, entropy in the generative process, and typicality. We speculate that generative OOD detectors also failed because their models focused on the pixels rather than the semantic content of the data, leading to failures in near-OOD cases where the pixels may be similar but the information content is significantly different. We hypothesize that estimating typical sets using self-supervised learners leads to better OOD detectors. We introduce a novel approach that leverages representation learning, and informative summary statistics based on manifold estimation, to address all of the aforementioned issues. Our method outperforms other unsupervised approaches and achieves state-of-the art performance on well-established challenging benchmarks, and new synthetic data detection tasks.

Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large space of trajectories. For settings where the dynamical system of interest follows a Brownian motion with known drift, the question of conditioning the process to reach a given endpoint or desired rare event is definitively answered by Doob's h-transform. However, the naive estimation of this transform is infeasible, as it requires simulating sufficiently many forward trajectories to estimate rare event probabilities. In this work, we propose a variational formulation of Doob's h-transform as an optimization problem over trajectories between a given initial point and the desired ending point. To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design. Our approach significantly reduces the search space over trajectories and avoids expensive trajectory simulation and inefficient importance sampling estimators which are required in existing methods. We demonstrate the ability of our method to find feasible transition paths on real-world molecular simulation and protein folding tasks.

One of the main properties of any intelligent system is that it has the capacity to learn. This holds for biological systems, ranging from bacteria and fungi to plants and animals [17, 21, 42, 50], as well as for engineered systems designed by artificial intelligence (AI) researchers [59, 29, 9]. Modern intelligent systems, such as those used in machine learning, typically rely on gradient descent for learning by minimizing error gradients [32, 65, 49]. While gradient-based methods have driven significant advances in AI [29], their reliance on exact gradients, centralized updates, and complex information pathways limits their applicability in biological and neuromorphic systems In contrast, biological learning likely relies on different mechanisms, as organisms often lack the exact gradient information and centralized control that gradient descent requires [31, 68]. Neuromorphic computing, inspired by these principles, aims to replicate the distributed, energyefficient learning of biological systems [38, 40]. However, integrating traditional gradient-based methods into neuromorphic hardware has proven challenging, highlighting a critical gap: the need for gradient-free learning mechanisms that exclusively rely on operations that are local in space and time [24, 12]. To address this, alternative learning principles to gradient descent have been proposed for both rate-based [45, 7, 51, 5, 67] and spike-based models [36, 4, 22, 46]. A class of methods that leverages inherent noise present in biological systems to facilitate learning is perturbation-based methods [57, 69, 66], which adjust the system's parameters based on noise effects and global reinforcement signals, offering gradient-free, local learning suitable for biological or neuromorphic

Distance functions are crucial in robotics for representing spatial relationships between the robot and the environment. It provides an implicit representation of continuous and differentiable shapes, which can seamlessly be combined with control, optimization, and learning techniques. While standard distance fields rely on the Euclidean metric, many robotic tasks inherently involve non-Euclidean structures. To this end, we generalize the use of Euclidean distance fields to more general metric spaces by solving a Riemannian eikonal equation, a first-order partial differential equation, whose solution defines a distance field and its associated gradient flow on the manifold, enabling the computation of geodesics and globally length-minimizing paths. We show that this \emph{geodesic distance field} can also be exploited in the robot configuration space. To realize this concept, we exploit physics-informed neural networks to solve the eikonal equation for high-dimensional spaces, which provides a flexible and scalable representation without the need for discretization. Furthermore, a variant of our neural eikonal solver is introduced, which enables the gradient flow to march across both task and configuration spaces. As an example of application, we validate the proposed approach in an energy-aware motion generation task. This is achieved by considering a manifold defined by a Riemannian metric in configuration space, effectively taking the property of the robot's dynamics into account. Our approach produces minimal-energy trajectories for a 7-axis Franka robot by iteratively tracking geodesics through gradient flow backpropagation.

Flow Matching (FM) is a recent framework for generative modeling that has achieved state-of-the-art performance across various domains, including image, video, audio, speech, and biological structures. This guide offers a comprehensive and self-contained review of FM, covering its mathematical foundations, design choices, and extensions. By also providing a PyTorch package featuring relevant examples (e.g., image and text generation), this work aims to serve as a resource for both novice and experienced researchers interested in understanding, applying and further developing FM.