Similar to conventional video generation, current deep learning-based weather prediction frameworks often lack explicit physical constraints, leading to unphysical outputs that limit their reliability for operational forecasting. Among various physical processes requiring proper representation, radiation plays a fundamental role as it drives Earth's weather and climate systems. However, accurate simulation of radiative transfer processes remains challenging for traditional numerical weather prediction (NWP) models due to their inherent complexity and high computational costs. Here, we propose FuXi-RTM, a hybrid physics-guided deep learning framework designed to enhance weather forecast accuracy while enforcing physical consistency. FuXi-RTM integrates a primary forecasting model (FuXi) with a fixed deep learning-based radiative transfer model (DLRTM) surrogate that efficiently replaces conventional radiation parameterization schemes. This represents the first deep learning-based weather forecasting framework to explicitly incorporate physical process modeling. Evaluated over a comprehensive 5-year dataset, FuXi-RTM outperforms its unconstrained counterpart in 88.51% of 3320 variable and lead time combinations, with improvements in radiative flux predictions. By incorporating additional physical processes, FuXi-RTM paves the way for next-generation weather forecasting systems that are both accurate and physically consistent.

Recent developments in deep reinforcement learning have been very successful in learning complex, previously intractable problems. Sample efficiency and local optimality, however, remain significant challenges. To address these challenges, novelty-driven exploration strategies have emerged and shown promising potential. Unfortunately, no single algorithm outperforms all others in all tasks and most of them struggle with tasks with high-dimensional and complex observations. In this work, we propose Adventurer, a novelty-driven exploration algorithm that is based on Bidirectional Generative Adversarial Networks (BiGAN), where BiGAN is trained to estimate state novelty. Intuitively, a generator that has been trained on the distribution of visited states should only be able to generate a state coming from the distribution of visited states. As a result, novel states using the generator to reconstruct input states from certain latent representations would lead to larger reconstruction errors. We show that BiGAN performs well in estimating state novelty for complex observations. This novelty estimation method can be combined with intrinsic-reward-based exploration. Our empirical results show that Adventurer produces competitive results on a range of popular benchmark tasks, including continuous robotic manipulation tasks (e.g. Mujoco robotics) and high-dimensional image-based tasks (e.g. Atari games).

A robust control strategy for autonomous vehicles can improve system stability, enhance riding comfort, and prevent driving accidents. This paper presents a novel interpolation tube-based constrained iterative linear quadratic regulator (itube-CILQR) algorithm for autonomous computer-vision-based vehicle lane-keeping. The goal of the algorithm is to enhance robustness during high-speed cornering on tight turns. The advantages of itube-CILQR over the standard tube-approach include reduced system conservatism and increased computational speed. Numerical and vision-based experiments were conducted to examine the feasibility of the proposed algorithm. The proposed itube-CILQR algorithm is better suited to vehicle lane-keeping than variational CILQR-based methods and model predictive control (MPC) approaches using a classical interior-point solver. Specifically, in evaluation experiments, itube-CILQR achieved an average runtime of 3.16 ms to generate a control signal to guide a self-driving vehicle; itube-MPC typically required a 4.67-times longer computation time to complete the same task. Moreover, the influence of conservatism on system behavior was investigated by exploring the interpolation variable trajectories derived from the proposed itube-CILQR algorithm during lane-keeping maneuvers.

Efficient and reliable operation of Concentrated Solar Power (CSP) plants is essential for meeting the growing demand for sustainable energy. However, high-temperature solar receivers face severe operational risks, such as freezing, deformation, and corrosion, resulting in costly downtime and maintenance. To monitor CSP plants, cameras mounted on solar receivers record infrared images at irregular intervals ranging from one to five minutes throughout the day. Anomalous images can be detected by thresholding an anomaly score, where the threshold is chosen to optimize metrics such as the F1-score on a validation set. This work proposes a framework for generating more reliable decision thresholds with finite-sample coverage guarantees on any chosen risk function. Our framework also incorporates an abstention mechanism, allowing high-risk predictions to be deferred to domain experts. Second, we propose a density forecasting method to estimate the likelihood of an observed image given a sequence of previously observed images, using this likelihood as its anomaly score. Third, we analyze the deployment results of our framework across multiple training scenarios over several months for two CSP plants. This analysis provides valuable insights to our industry partner for optimizing maintenance operations. Finally, given the confidential nature of our dataset, we provide an extended simulated dataset, leveraging recent advancements in generative modeling to create diverse thermal images that simulate multiple CSP plants. Our code is publicly available.

The current paper investigates the influences of AI innovation, GDP growth, renewable energy utilization, the digital economy, and industrialization on CO2 emissions in the USA from 1990 to 2022, incorporating the ARDL methodology. The outcomes observe that AI innovation, renewable energy usage, and the digital economy reduce CO2 emissions, while GDP expansion and industrialization intensify ecosystem damage. Unit root tests (ADF, PP, and DF-GLS) reveal heterogeneous integration levels amongst components, ensuring robustness in the ARDL analysis. Complementary methods (FMOLS, DOLS, and CCR) validate the results, enhancing their reliability. Pairwise Granger causality assessments identify strong unidirectional connections within CO2 emissions and AI innovation, as well as the digital economy, underscoring their significant roles in ecological sustainability. This research highlights the requirement for strategic actions to nurture equitable growth, including advancements in AI technology, green energy adoption, and environmentally conscious industrial development, to improve environmental quality in the United States.

With the growing practical interest in vision-based tasks for autonomous systems, the need for efficient and complex methods becomes increasingly larger. In the rush to develop new methods with the aim to outperform the current state of the art, an analysis of the underlying theory is often neglected and simply replaced with empirical evaluations in simulated or real-world experiments. While such methods might yield favorable performance in practice, they are often less well understood, which prevents them from being applied in safety-critical systems. The goal of this work is to design an algorithm for the Next Best View (NBV) problem in the context of active object reconstruction, for which we can provide qualitative performance guarantees with respect to true optimality. To the best of our knowledge, no previous work in this field addresses such an analysis for their proposed methods. Based on existing work on Gaussian process optimization, we rigorously derive sublinear bounds for the cumulative regret of our algorithm, which guarantees near-optimality. Complementing this, we evaluate the performance of our algorithm empirically within our simulation framework. We further provide additional insights through an extensive study of potential objective functions and analyze the differences to the results of related work.

--We introduce CoinFT, a capacitive 6-axis force / torque (F / T) sensor that is compact, light, low-cost, and robust with an average mean-squared error of 0.11 N for force and 0.84 mNm for moment when the input ranges from 0 10 N and 0 4 N in normal and shear directions, respectively. CoinFT is a stack of two rigid PCBs with comb-shaped electrodes connected by an array of silicone rubber pillars. The microcontroller interrogates the electrodes in different subsets in order to enhance sensitivity for measuring 6-axis F / T . The combination of desirable features of CoinFT enables various contact-rich robot interactions at a scale, across different embodiment domains including drones, robot end-effectors, and wearable haptic devices. We demonstrate the utility of CoinFT on drones by performing an attitude-based force control to perform tasks that require careful contact force modulation. RECISE force and torque measurement is vital for robots to perform contact-rich tasks safely and effectively. Tasks such as table wiping [1], assembly [2], or palpating soft tissue [3] require the application of force and torque within a specific range--sufficient to complete the task but not so excessive as to cause damage or waste energy. Depending on the application and interaction type, robots performing contact-rich tasks come in various forms, including robotic arms [4], grippers [5], drones [6], and wearable devices [7]. Therefore, equipping these diverse robotic platforms with sensors that can accurately measure force and torque is essential. Extensive research has been dedicated to developing 6-axis force / torque (F / T) sensors using various transduction methods [8]. Commercially available sensors also exist, such as the Gamma (A TI Industries), and 6-axis F / T sensors from MinebeaMitsumi or ReSense.

Large Language Models (LLMs) have made significant advances in various code-related tasks, particularly in generating source code from natural language descriptions (Zhao et al. (2023); Chang et al. (2024)). Their effectiveness is primarily driven by their extensive number of model parameters, the use of large and diverse datasets, and the immense computational resources employed during training (Kaplan et al. (2020)). These models are typically trained on vast corpora sourced from the web. LLMs are capable of capturing intricate patterns, linguistic subtleties, and semantic relationships. A wide range of models are available for code generation. There are general-purpose models like ChatGPT (Ouyang et al. (2022)), GPT -4 (Achiam et al. (2023)), and LLaMA (Touvron et al. (2023a)) which are designed for a broad range of applications, as well as specialized models such as StarCoder, Code LLaMA (Roziere et al. (2023)), DeepSeek-Coder, and Code Gemma that are optimized for code-related tasks. The integration of code generation with the latest advances in LLM technology is now an essential tool for many businesses, as well as an essential target for LLM developers as programming languages are considered to be different dialects of natural language (Athiwaratkun et al. (2022)).

Every scientific discovery starts with an idea inspired by prior work, interdisciplinary concepts, and emerging challenges. Recent advancements in large language models (LLMs) trained on scientific corpora have driven interest in AI-supported idea generation. However, generating context-aware, high-quality, and innovative ideas remains challenging. We introduce SCI-IDEA, a framework that uses LLM prompting strategies and Aha Moment detection for iterative idea refinement. SCI-IDEA extracts essential facets from research publications, assessing generated ideas on novelty, excitement, feasibility, and effectiveness. Comprehensive experiments validate SCI-IDEA's effectiveness, achieving average scores of 6.84, 6.86, 6.89, and 6.84 (on a 1-10 scale) across novelty, excitement, feasibility, and effectiveness, respectively. Evaluations employed GPT-4o, GPT-4.5, DeepSeek-32B (each under 2-shot prompting), and DeepSeek-70B (3-shot prompting), with token-level embeddings used for Aha Moment detection. Similarly, it achieves scores of 6.87, 6.86, 6.83, and 6.87 using GPT-4o under 5-shot prompting, GPT-4.5 under 3-shot prompting, DeepSeek-32B under zero-shot chain-of-thought prompting, and DeepSeek-70B under 5-shot prompting with sentence-level embeddings. We also address ethical considerations such as intellectual credit, potential misuse, and balancing human creativity with AI-driven ideation. Our results highlight SCI-IDEA's potential to facilitate the structured and flexible exploration of context-aware scientific ideas, supporting innovation while maintaining ethical standards.

--This study addresses the technical bottlenecks in handling long text and the "hallucination" issue caused by insufficient short text information in remote sensing vision-language foundation models (VLFM). We propose a novel vision-language foundation model, LRSCLIP, and a multimodal dataset, LRS2M. The main contributions are as follows: (1) By integrating multi-source remote sensing data and adopting a large language model labeling strategy, we construct the LRS2M dataset, which contains 2 million image-text pairs, providing both short and long texts for the first time, thus solving the problem of semantic granularity limitations in existing datasets; (2) The design of the LRSCLIP architecture based on Long-CLIP's KPS module, which extends CLIP's text processing capacity and achieves fine-grained cross-modal feature alignment through a dual-text loss weighting mechanism. Experimental results show that LRSCLIP improves retrieval accuracy by 10%-20% over the Long-CLIP baseline in the zero-shot long-text cross-modal retrieval task. For the zero-shot short-text cross-modal retrieval task, LRSCLIP achieves improvements over the current best model, GeoRSCLIP, with increases of 0.17%, 0.67%, and 0.92% in T ext to Image R@1, Image to T ext R@1, and mR on RSITMD, respectively, and 0.04%, 2.93%, and 1.28% on RSICD. This work provides a new benchmark model and data support for remote sensing multimodal learning. ECENT years have seen significant progress in foundation models (FM) within the fields of computer vision (CV) and natural language processing (NLP) [1] [2] [3] [4] [5] [6] [7] [8]. This research was funded by the National Key R&D Program of China under grant number 2021YFB3900504. Weizhi Chen, Kai Li are with Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China, and also with School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China. Jingbo Chen, Y upeng Deng, Jiansheng Chen, Zhihao Xi, Diyou Liu, Y u Meng are with Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China. Y uman Feng is with the School of Information Network Security, People's Public Security University of China, Beijing 100038, China. Unlike models designed for specific task objectives, VLFM learns joint representations of massive image-text pairs in upstream tasks and then transfers this knowledge to various downstream tasks, demonstrating exceptional performance. Several outstanding VLFM models have already emerged, such as CLIP [10], BLIP [11] [12], and MaskVLM [13]. Meanwhile, researchers have begun exploring the application potential of VLFM in the remote sensing domain. However, VLFM often faces issues related to the long-tail effect (where a small number of classes dominate while the rest have fewer samples), making direct application to remote sensing tasks challenging [14].