Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal environments, reasoning becomes essential for enabling robust and adaptive behavior. Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning. As research advances, multimodal reasoning has rapidly evolved from modular, perception-driven pipelines to unified, language-centric frameworks that offer more coherent cross-modal understanding. While instruction tuning and reinforcement learning have improved model reasoning, significant challenges remain in omni-modal generalization, reasoning depth, and agentic behavior. To address these issues, we present a comprehensive and structured survey of multimodal reasoning research, organized around a four-stage developmental roadmap that reflects the field's shifting design philosophies and emerging capabilities. First, we review early efforts based on task-specific modules, where reasoning was implicitly embedded across stages of representation, alignment, and fusion. Next, we examine recent approaches that unify reasoning into multimodal LLMs, with advances such as Multimodal Chain-of-Thought (MCoT) and multimodal reinforcement learning enabling richer and more structured reasoning chains. Finally, drawing on empirical insights from challenging benchmarks and experimental cases of OpenAI O3 and O4-mini, we discuss the conceptual direction of native large multimodal reasoning models (N-LMRMs), which aim to support scalable, agentic, and adaptive reasoning and planning in complex, real-world environments.

Distributed learning and Edge AI necessitate efficient data processing, low-latency communication, decentralized model training, and stringent data privacy to facilitate real-time intelligence on edge devices while reducing dependency on centralized infrastructure and ensuring high model performance. In the context of global navigation satellite system (GNSS) applications, the primary objective is to accurately monitor and classify interferences that degrade system performance in distributed environments, thereby enhancing situational awareness. To achieve this, machine learning (ML) models can be deployed on low-resource devices, ensuring minimal communication latency and preserving data privacy. The key challenge is to compress ML models while maintaining high classification accuracy. In this paper, we propose variational autoencoders (VAEs) for disentanglement to extract essential latent features that enable accurate classification of interferences. We demonstrate that the disentanglement approach can be leveraged for both data compression and data augmentation by interpolating the lower-dimensional latent representations of signal power. To validate our approach, we evaluate three VAE variants - vanilla, factorized, and conditional generative - on four distinct datasets, including two collected in controlled indoor environments and two real-world highway datasets. Additionally, we conduct extensive hyperparameter searches to optimize performance. Our proposed VAE achieves a data compression rate ranging from 512 to 8,192 and achieves an accuracy up to 99.92%.

LiDAR representation learning aims to extract rich structural and semantic information from large-scale, readily available datasets, reducing reliance on costly human annotations. However, existing LiDAR representation strategies often overlook the inherent spatiotemporal cues in LiDAR sequences, limiting their effectiveness. In this work, we propose LiMA, a novel long-term image-to-LiDAR Memory Aggregation framework that explicitly captures longer range temporal correlations to enhance LiDAR representation learning. LiMA comprises three key components: 1) a Cross-View Aggregation module that aligns and fuses overlapping regions across neighboring camera views, constructing a more unified and redundancy-free memory bank; 2) a Long-Term Feature Propagation mechanism that efficiently aligns and integrates multi-frame image features, reinforcing temporal coherence during LiDAR representation learning; and 3) a Cross-Sequence Memory Alignment strategy that enforces consistency across driving sequences, improving generalization to unseen environments. LiMA maintains high pretraining efficiency and incurs no additional computational overhead during downstream tasks. Extensive experiments on mainstream LiDAR-based perception benchmarks demonstrate that LiMA significantly improves both LiDAR semantic segmentation and 3D object detection. We hope this work inspires more effective pretraining paradigms for autonomous driving. The code has be made publicly accessible for future research.

In the broader context of deep learning, Multimodal Large Language Models have achieved significant breakthroughs by leveraging powerful Large Language Models as a backbone to align different modalities into the language space. A prime exemplification is the development of Video Large Language Models (Video-LLMs). While numerous advancements have been proposed to enhance the video understanding capabilities of these models, they are predominantly trained on questions generated directly from video content. However, in real-world scenarios, users often pose questions that extend beyond the informational scope of the video, highlighting the need for Video-LLMs to assess the relevance of the question. We demonstrate that even the best-performing Video-LLMs fail to reject unfit questions-not necessarily due to a lack of video understanding, but because they have not been trained to identify and refuse such questions. To address this limitation, we propose alignment for answerability, a framework that equips Video-LLMs with the ability to evaluate the relevance of a question based on the input video and appropriately decline to answer when the question exceeds the scope of the video, as well as an evaluation framework with a comprehensive set of metrics designed to measure model behavior before and after alignment. Furthermore, we present a pipeline for creating a dataset specifically tailored for alignment for answerability, leveraging existing video-description paired datasets.

Transcranial magnetic stimulation (TMS) is a non-invasive and safe brain stimulation procedure with growing applications in clinical treatments and neuroscience research. However, achieving precise stimulation over prolonged sessions poses significant challenges. By integrating advanced robotics with conventional TMS, robot-assisted TMS (Robo-TMS) has emerged as a promising solution to enhance efficacy and streamline procedures. Despite growing interest, a comprehensive review from an engineering perspective has been notably absent. This paper systematically examines four critical aspects of Robo-TMS: hardware and integration, calibration and registration, neuronavigation systems, and control systems. We review state-of-the-art technologies in each area, identify current limitations, and propose future research directions. Our findings suggest that broader clinical adoption of Robo-TMS is currently limited by unverified clinical applicability, high operational complexity, and substantial implementation costs. Emerging technologies, including marker-less tracking, non-rigid registration, learning-based electric field (E-field) modelling, individualised magnetic resonance imaging (MRI) generation, robot-assisted multi-locus TMS (Robo-mTMS), and automated calibration and registration, present promising pathways to address these challenges.

Recent years have seen rapid increases in intermittent renewable generation, requiring novel battery energy storage systems (BESS) solutions. One recent trend is the emergence of large grid-connected batteries, that can be controlled to provide multiple storage and flexibility services, using a stacked revenue model. Another emerging development is renewable energy communities (REC), in which prosumers invest in their own renewable generation capacity, but also requiring battery storage for flexibility. In this paper, we study settings in which energy communities rent battery capacity from a battery operator through a battery-as-a-service (BaaS) model. We present a methodology for determining the sizing and pricing of battery capacity that can be rented, such that it provides economic benefits to both the community and the battery operator that participates in the energy market. We examine how sizes and prices vary across a number of different scenarios for different types of tariffs (flat, dynamic) and competing energy market uses. Second, we conduct a systematic study of linear optimization models for battery control when deployed to provide flexibility to energy communities. We show that existing approaches for battery control with daily time windows have a number of important limitations in practical deployments, and we propose a number of regularization functions in the optimization to address them. Finally, we investigate the proposed method using real generation, demand, tariffs, and battery data, based on a practical case study from a large battery operator in the Netherlands. For the settings in our case study, we find that a community of 200 houses with a 330 kW wind turbine can save up to 12,874 euros per year by renting just 280 kWh of battery capacity (after subtracting battery rental costs), with the methodology applicable to a wide variety of settings and tariff types.

Large language models (LLMs) are powerful artificial intelligence (AI) tools transforming how research is conducted. However, their use in research has been met with skepticism, due to concerns about hallucinations, biases and potential harms to research. These emphasize the importance of clearly understanding the strengths and weaknesses of LLMs to ensure their effective and responsible use. Here, we present a roadmap for integrating LLMs into cross-disciplinary research, where effective communication, knowledge transfer and collaboration across diverse fields are essential but often challenging. We examine the capabilities and limitations of LLMs and provide a detailed computational biology case study (on modeling HIV rebound dynamics) demonstrating how iterative interactions with an LLM (ChatGPT) can facilitate interdisciplinary collaboration and research. We argue that LLMs are best used as augmentative tools within a human-in-the-loop framework. Looking forward, we envisage that the responsible use of LLMs will enhance innovative cross-disciplinary research and substantially accelerate scientific discoveries.

This paper systematically reviews recent advances in artificial intelligence (AI), with a particular focus on machine learning (ML), across the entire drug discovery pipeline. Due to the inherent complexity, escalating costs, prolonged timelines, and high failure rates of traditional drug discovery methods, there is a critical need to comprehensively understand how AI/ML can be effectively integrated throughout the full process. Currently available literature reviews often narrowly focus on specific phases or methodologies, neglecting the dependence between key stages such as target identification, hit screening, and lead optimization. To bridge this gap, our review provides a detailed and holistic analysis of AI/ML applications across these core phases, highlighting significant methodological advances and their impacts at each stage. We further illustrate the practical impact of these techniques through an in-depth case study focused on hyperuricemia, gout arthritis, and hyperuricemic nephropathy, highlighting real-world successes in molecular target identification and therapeutic candidate discovery. Additionally, we discuss significant challenges facing AI/ML in drug discovery and outline promising future research directions. Ultimately, this review serves as an essential orientation for researchers aiming to leverage AI/ML to overcome existing bottlenecks and accelerate drug discovery.

The recent mainstream adoption of large language model (LLM) technology is enabling novel applications in the form of chatbots and virtual assistants across many domains. With the aim of grounding LLMs in trusted domains and avoiding the problem of hallucinations, retrieval-augmented generation (RAG) has emerged as a viable solution. In order to deploy sustainable RAG systems in low-resource settings, achieving high retrieval accuracy is not only a usability requirement but also a cost-saving strategy. Through empirical evaluations on a Kinyarwanda-language dataset, we find that the most limiting factors in achieving high retrieval accuracy are limited language coverage and inadequate sub-word tokenization in pre-trained language models. We propose a new retriever model, KinyaColBERT, which integrates two key concepts: late word-level interactions between queries and documents, and a morphology-based tokenization coupled with two-tier transformer encoding. This methodology results in lexically grounded contextual embeddings that are both fine-grained and self-contained. Our evaluation results indicate that KinyaColBERT outperforms strong baselines and leading commercial text embedding APIs on a Kinyarwanda agricultural retrieval benchmark. By adopting this retrieval strategy, we believe that practitioners in other low-resource settings can not only achieve reliable RAG systems but also deploy solutions that are more cost-effective.

A recent trend in the mathematical optimization literature is to embed trained machine learning predictors into a larger optimization model. The m ost common application is for a practitioner to train a machine learning predictor as a sur rogate for a more complicated subsystem that cannot be directly embedded into an optimiza tion model, for example, because it does not have an algebraic form or because it is non -differentiable. L opez-Flores et al. (2024) provide a review of the field.