Applications of machine learning in chemistry are often limited by the scarcity and expense of labeled data, restricting traditional supervised methods. In this work, we introduce a framework for molecular reasoning using general-purpose Large Language Models (LLMs) that operates without requiring labeled training data. Our method anchors chain-of-thought reasoning to the molecular structure by using unique atomic identifiers. First, the LLM performs a one-shot task to identify relevant fragments and their associated chemical labels or transformation classes. In an optional second step, this position-aware information is used in a few-shot task with provided class examples to predict the chemical transformation. We apply our framework to single-step retrosynthesis, a task where LLMs have previously underperformed. Across academic benchmarks and expert-validated drug discovery molecules, our work enables LLMs to achieve high success rates in identifying chemically plausible reaction sites ($\geq90\%$), named reaction classes ($\geq40\%$), and final reactants ($\geq74\%$). Beyond solving complex chemical tasks, our work also provides a method to generate theoretically grounded synthetic datasets by mapping chemical knowledge onto the molecular structure and thereby addressing data scarcity.

The concurrent work G2Gs presents a similar two-step framework, while our method is more general and scalable. We keep muted about G2Gs before its conference version is available since we have some concerns about it. This discussion will be included into our revised version. Atom mapping is optional for our method. The synthon approach can also work for reactions without provided atom mapping (L208-212).

The synthesis of complex natural products remains one of the grand challenges of organic chemistry. We present DeepRetro, a major advancement in computational retrosynthesis that enables the discovery of viable synthetic routes for complex molecules typically considered beyond the reach of existing retrosynthetic methods. DeepRetro is a novel, open-source framework that tightly integrates large language models (LLMs), traditional retrosynthetic engines, and expert human feedback in an iterative design loop. Prior approaches rely solely on template-based methods or unconstrained LLM outputs. In contrast, DeepRetro combines the precision of template-based methods with the generative flexibility of LLMs, controlled by rigorous chemical validity checks and enhanced by recursive refinement. This hybrid system dynamically explores and revises synthetic pathways, guided by both algorithmic checks and expert chemist feedback through an interactive user interface. While DeepRetro achieves strong performance on standard retrosynthesis benchmarks, its true strength lies in its ability to propose novel, viable pathways to highly complex natural products-targets that have historically eluded automated planning. Through detailed case studies, we illustrate how this approach enables new routes for total synthesis and facilitates human-machine collaboration in organic chemistry. Beyond retrosynthesis, DeepRetro represents a working model for how to leverage LLMs in scientific discovery. We provide a transparent account of the system's design, algorithms, and human-feedback loop, enabling broad adaptation across scientific domains. By releasing DeepRetro as an open-source tool, we aim to empower chemists to tackle increasingly ambitious synthetic targets, accelerating progress in drug discovery, materials design, and beyond.

Real-time cascade mitigation requires fast, complex operational decisions under uncertainty. In this work, we extend the influence graph into a Markov decision process model (MDP) for real-time mitigation of cascading outages in power transmission systems, accounting for uncertainties in generation, load, and initial contingencies. The MDP includes a do-nothing action to allow for conservative decision-making and is solved using reinforcement learning. We present a policy gradient learning algorithm initialized with a policy corresponding to the unmitigated case and designed to handle invalid actions. The proposed learning method converges faster than the conventional algorithm. Through careful reward design, we learn a policy that takes conservative actions without deteriorating system conditions. The model is validated on the IEEE 14-bus and IEEE 118-bus systems. The results show that proactive line disconnections can effectively reduce cascading risk, and certain lines consistently emerge as critical in mitigating cascade propagation.

As wireless communication technology progresses towards the sixth generation (6G), high-frequency millimeter-wave (mmWave) communication has emerged as a promising candidate for enabling vehicular networks. It offers high data rates and low-latency communication. However, obstacles such as buildings, trees, and other vehicles can cause signal attenuation and blockage, leading to communication failures that can result in fatal accidents or traffic congestion. Predicting blockages is crucial for ensuring reliable and efficient communications. Furthermore, the advent of 6G technology is anticipated to integrate advanced sensing capabilities, utilizing a variety of sensor types. These sensors, ranging from traditional RF sensors to cameras and Lidar sensors, are expected to provide access to rich multimodal data, thereby enriching communication systems with a wealth of additional contextual information. Leveraging this multimodal data becomes essential for making precise network management decisions, including the crucial task of blockage detection. In this paper, we propose a Deep Learning (DL)-based approach that combines Convolutional Neural Networks (CNNs) and customized Vision Transformers (ViTs) to effectively extract essential information from multimodal data and predict blockages in vehicular networks. Our method capitalizes on the synergistic strengths of CNNs and ViTs to extract features from time-series multimodal data, which include images and beam vectors. To capture temporal dependencies between the extracted features and the blockage state at future time steps, we employ a Gated Recurrent Unit (GRU)-based architecture. Our results show that the proposed approach achieves high accuracy and outperforms state-of-the-art solutions, achieving more than $95\%$ accurate predictions.

Heterogeneous multi-robot system deployment offers a For example, consider Figure 1 where two unmanned ground variety of advantages including improved versatility, scalability, vehicles (UGVs) and one unmanned aerial vehicle (UAV) are and adaptability over homogeneous systems. As robotic exploring an environment and may discover tasks at undisclosed technology has advanced over the last few decades making locations. During disconnection, the UAV maintains robots smaller, more capable, and affordable, demand for a set of possible (belief) states for UGV 1 and UGV 2 and multi-robot research has grown. Appropriate coordination of also a set of (empathy) states that UGV 1 and UGV 2 might these heterogeneous systems can improve the effectiveness of believe about the UAV. The UAV finds a task that requires safety critical missions such as surveillance, exploration, and a UGV and plans to communicate with UGV 2. After the rescue operations by incorporating the capabilities of each UAV travels to UGV 2's first belief state, it finds that UGV robot. However, the complexity of the solution for a heterogeneous 2 is not present. So, the UAV reasons that UGV 2 might be system can exponentially expand over long periods at the second belief state, successfully communicates, and of disconnectivity, especially in uncertain environments.

Accurate segmentation of pulmonary airways and vessels is crucial for the diagnosis and treatment of pulmonary diseases. However, current deep learning approaches suffer from disconnectivity issues that hinder their clinical usefulness. To address this challenge, we propose a post-processing approach that leverages a data-driven method to repair the topology of disconnected pulmonary tubular structures. Our approach formulates the problem as a keypoint detection task, where a neural network is trained to predict keypoints that can bridge disconnected components. We use a training data synthesis pipeline that generates disconnected data from complete pulmonary structures. Moreover, the new Pulmonary Tree Repairing (PTR) dataset is publicly available, which comprises 800 complete 3D models of pulmonary airways, arteries, and veins, as well as the synthetic disconnected data.

Thus, we introduce Multi-robot systems (MRS) have the potential to assist a coordinated epistemic prediction and planning method in many safety-critical applications such as search and rescue, in which a robot propagates a finite set of belief states military intelligence and surveillance, and inspection representing possible states of other agents in the system and operations where it may be hazardous and costly to deploy empathy states representing a finite set of possible states from humans. Looking to the state-of-the-art, we note that most other agents' perspectives. Subsequently, using epistemic MRS research assumes constant communication between planning, we can formulate a consensus strategy such that robots [1]-[3]. However, within the aforementioned application every distributed belief in the system achieves consensus. For space, long-range communication is often unreliable example, consider Figure 1 where two robots are canvassing or unavailable. Humans adequately cope with such problems, an environment. During disconnection, Robot 1 maintains a performing these tasks collaboratively by extrapolating and set of possible (belief) states for Robot 2 and also a set of empathizing with what other actors might believe if the local (empathy) states that Robot 2 might believe about Robot 1. plan must change at run-time. This subconscious process can Once Robot 2 experiences a failure, it tracks another state be modally represented as epistemic planning, computing in its empathy set. We reason that though Robot 1 holds a and reasoning about multiple predictions and actions while false belief about Robot 2's state, there exists an epistemic accounting for a priori beliefs, current observations, and strategy that can allow robot 1 to find robot 2 (i.e., updating other actors' sensing and mobility capabilities.

In this special issue we are reprinting our top stories of the past year. This article first appeared on Nautilus in our "Universality" issue in April, 2021. It all started with an odd pile of shells: a pile that, upon closer inspection, fell apart like a flower losing its petals, introducing a burned-out nature documentarian named Craig Foster--and, in time, the world--to the octopus hiding cleverly inside. Known simply as "her," she would become the star of My Octopus Teacher, the Oscar-nominated Netflix documentary and surprise pandemic hit that told the story of Foster's unlikely relationship with that eight-armed mollusk. Released in September 2020, it arrived at the perfect moment. Audiences exhausted by lockdowns and unrelenting 2020-ness were primed for escape into the undersea fantasia of South Africa's kelp forests, where Foster met her. Best-selling books like The Soul of an Octopus and Other Minds: The Octopus, the Sea, and the Deep Origins of Consciousness had whetted public curiosity about these uncannily intelligent creatures with whom humans last shared a common ancestor 600 million years ago. Yet while most writing about octopuses emphasizes their ostensibly alien, unknowable nature,1 and serious, science-minded nature documentaries elevate concern about biodiversity over sentiment for a single animal, My Octopus Teacher defied convention. It embraced Foster's feelings for the octopus, which over the course of a year evolved from curiosity to care--even to love. And though her own feelings were left for viewers to interpret, the film's indelible impression was of nature populated by species who are not only beautiful and exquisitely evolved and ecologically important, but highly sentient, too.