LLM-generated reviews for scientific papers are gaining considerable traction and are even being officially piloted by major conferences. We have to assume that not only reviewers are using LLM-assistance, but also that authors use LLMs to revise their papers before submitting. In this work, we perform empirical experiments on papers from the 2025 ACL Rolling Review (ARR) to evaluate LLM reviews from both the author and the reviewer perspective. First, we identify a limited alignment of LLM reviews with human ones. In the best-case scenario, the alignment is reasonable. However, we also find that LLM-human alignment varies substantially across prompts and models. Finally, we investigate the scenario in which the author uses an iterative draft-revise workflow to improve the submission according to the LLM review. We find that this "gaming" of LLM reviews can be effective in specific scenarios, leading to a statistically significant increase of overall scores for up to 35\% of papers. We publish our code: https://github.com/uhh-hcds/reviewarcade.
Natural Language Processing (NLP) has transformed various fields beyond linguistics by applying techniques originally developed for human language to the analysis of biological sequences. This review explores the application of NLP methods to biological sequence data, focusing on genomics, transcriptomics, and proteomics. We examine how various NLP methods, from classic approaches like word2vec to advanced models employing transformers and hyena operators, are being adapted to analyze DNA, RNA, protein sequences, and entire genomes. The review also examines tokenization strategies and model architectures, evaluating their strengths, limitations, and suitability for different biological tasks. We further cover recent advances in NLP applications for biological data, such as structure prediction, gene expression, and evolutionary analysis, highlighting the potential of these methods for extracting meaningful insights from large-scale genomic data. As language models continue to advance, their integration into bioinformatics holds immense promise for advancing our understanding of biological processes in all domains of life.
A computer Program Capable of performing at a human-expert level in a narrow problem domain area is called an expert system. Management of uncertainty is an intrinsically important issue in the design of expert systems because much of the information in the knowledge base of a typical expert system is imprecise, incomplete or not totally reliable. In this paper, the author present s the review of past work that has been carried out by various researchers based on development of expert systems for the diagnosis of cardiac disease
By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large Language Models (LLMs) without increasing the inference cost. However, the memory consumption due to the growing number of experts presents a challenge to the deployment of these models in many real world settings. Our empirical study reveals that some experts encode redundant knowledge during pre-training. We thus propose a method of grouping and pruning similar experts to improve the model's parameter efficiency. We validate the effectiveness of our method by pruning three state-of-the-art MoE architectures, including Mixtral, Deepseek-MoE, and Qwen. The evaluation shows that our method outperforms other model pruning methods on a range of natural language tasks. We will release our code to facilitate future research.
Proteomics is the large scale study of protein structure and function from biological systems through protein identification and quantification. "Shotgun proteomics" or "bottom-up proteomics" is the prevailing strategy, in which proteins are hydrolyzed into peptides that are analyzed by mass spectrometry. Proteomics studies can be applied to diverse studies ranging from simple protein identification to studies of proteoforms, protein-protein interactions, protein structural alterations, absolute and relative protein quantification, post-translational modifications, and protein stability. To enable this range of different experiments, there are diverse strategies for proteome analysis. The nuances of how proteomic workflows differ may be challenging to understand for new practitioners. Here, we provide a comprehensive overview of different proteomics methods to aid the novice and experienced researcher. We cover from biochemistry basics and protein extraction to biological interpretation and orthogonal validation. We expect this work to serve as a basic resource for new practitioners in the field of shotgun or bottom-up proteomics.
Expert domain writing, such as scientific writing, typically demands extensive domain knowledge. Although large language models (LLMs) show promising potential in this task, evaluating the quality of automatically generated scientific writing is a crucial open issue, as it requires knowledge of domain-specific criteria and the ability to discern expert preferences. Conventional automatic evaluation metrics and LLM-as-a-judge systems, primarily designed for mainstream NLP tasks, are insufficient to grasp expert preferences and domain-specific quality standards. To address this gap and support realistic human-AI collaborative writing, we focus on related work generation, one of the most challenging scientific tasks, as an exemplar. We propose GREP, a multi-turn evaluation framework that integrates classical related work evaluation criteria with expert-specific preferences. GREP decomposes the evaluation into smaller fine-grained dimensions. This localized evaluation is further augmented with contrastive examples to provide detailed contextual guidance for the evaluation dimensions. Empirical investigation reveals that GREP is able to assess the quality of related work sections in a m
Given the large number of publications in software engineering, frequent literature reviews are required to keep current on work in specific areas. One tedious work in literature reviews is to find relevant studies amongst thousands of non-relevant search results. In theory, expert systems can assist in finding relevant work but those systems have primarily been tested in simulations rather than in application to actual literature reviews. Hence, few researchers have faith in such expert systems. Accordingly, using a realistic case study, this paper assesses how well our state-of-the-art expert system can help with literature reviews. The assessed literature review aimed at identifying test case prioritization techniques for automated UI testing, specifically from 8,349 papers on IEEE Xplore. This corpus was studied with an expert system that incorporates an incrementally updated human-in-the-loop active learning tool. Using that expert system, in three hours, we found 242 relevant papers from which we identified 12 techniques representing the state-of-the-art in test case prioritization when source code information is not available. These results were then validated by six other g
This paper reviews the current progress in applying machine learning (ML) tools to solve NP-hard combinatorial optimization problems, with a focus on routing problems such as the traveling salesman problem (TSP) and the vehicle routing problem (VRP). Due to the inherent complexity of these problems, exact algorithms often require excessive computational time to find optimal solutions, while heuristics can only provide approximate solutions without guaranteeing optimality. With the recent success of machine learning models, there is a growing trend in proposing and implementing diverse ML techniques to enhance the resolution of these challenging routing problems. We propose a taxonomy categorizing ML-based routing methods into construction-based and improvement-based approaches, highlighting their applicability to various problem characteristics. This review aims to integrate traditional OR methods with state-of-the-art ML techniques, providing a structured framework to guide future research and address emerging VRP variants.
Taking the opportunity of the 20th anniversary of the word "proteomics", this young adult age is a good time to remember how proteomics came from enormous progress in protein separation and protein microanalysis techniques, and from the conjugation of these advances into a high performance and streamlined working setup. However, in the history of the almost three decades that encompass the first attempts to perform large scale analysis of proteins to the current high throughput proteomics that we can enjoy now, it is also interesting to underline and to recall how difficult the first decade was. Indeed when the word was cast, the battle was already won. This recollection is mostly devoted to the almost forgotten period where proteomics was being conceived and put to birth, as this collective scientific work will never appear when searched through the keyword "proteomics". BIOLOGICAL SIGNIFICANCE: The significance of this manuscript is to recall and review the two decades that separated the first attempts of performing large scale analysis of proteins from the solid technical corpus that existed when the word "proteomics" was coined twenty years ago. This recollection is made within
In the last ten years, the field of proteomics has expanded at a rapid rate. A range of exciting new technology has been developed and enthusiastically applied to an enormous variety of biological questions. However, the degree of stringency required in proteomic data generation and analysis appears to have been underestimated. As a result, there are likely to be numerous published findings that are of questionable quality, requiring further confirmation and/or validation. This manuscript outlines a number of key issues in proteomic research, including those associated with experimental design, differential display and biomarker discovery, protein identification and analytical incompleteness. In an effort to set a standard that reflects current thinking on the necessary and desirable characteristics of publishable manuscripts in the field, a minimal set of guidelines for proteomics research is then described. These guidelines will serve as a set of criteria which editors of PROTEOMICS will use for assessment of future submissions to the Journal.
This review systematically examines the progression of the You Only Look Once (YOLO) object detection algorithms from YOLOv1 to the recently unveiled YOLOv12. Employing a reverse chronological analysis, this study examines the advancements introduced by YOLO algorithms, beginning with YOLOv12 and progressing through YOLO11 (or YOLOv11), YOLOv10, YOLOv9, YOLOv8, and subsequent versions to explore each version's contributions to enhancing speed, detection accuracy, and computational efficiency in real-time object detection. Additionally, this study reviews the alternative versions derived from YOLO architectural advancements of YOLO-NAS, YOLO-X, YOLO-R, DAMO-YOLO, and Gold-YOLO. Moreover, the study highlights the transformative impact of YOLO models across five critical application areas: autonomous vehicles and traffic safety, healthcare and medical imaging, industrial manufacturing, surveillance and security, and agriculture. By detailing the incremental technological advancements in subsequent YOLO versions, this review chronicles the evolution of YOLO, and discusses the challenges and limitations in each of the earlier versions. The evolution signifies a path towards integrating
Introduction: While the origin and evolution of proteins remain mysterious, advances in evolutionary genomics and systems biology are facilitating the historical exploration of the structure, function and organization of proteins and proteomes. Molecular chronologies are series of time events describing the history of biological systems and subsystems and the rise of biological innovations. Together with time-varying networks, these chronologies provide a window into the past. Areas covered: Here, we review molecular chronologies and networks built with modern methods of phylogeny reconstruction. We discuss how chronologies of structural domain families uncover the explosive emergence of metabolism, the late rise of translation, the co-evolution of ribosomal proteins and rRNA, and the late development of the ribosomal exit tunnel; events that coincided with a tendency to shorten folding time. Evolving networks described the early emergence of domains and a late big bang of domain combinations. Expert opinion: Two processes, folding and recruitment appear central to the evolutionary progression. The former increases protein persistence. The later fosters diversity. Chronologically,
Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility, adaptability, dynamism, faster training, information sharing, and model compression. Hypernets have shown promising results in a variety of deep learning problems, including continual learning, causal inference, transfer learning, weight pruning, uncertainty quantification, zero-shot learning, natural language processing, and reinforcement learning. Despite their success across different problem settings, there is currently no comprehensive review available to inform researchers about the latest developments and to assist in utilizing hypernets. To fill this gap, we review the progress in hypernets. We present an illustrative example of training deep neural networks using hypernets and propose categorizing hypernets based on five design criteria: inputs, outputs, variability of inputs and outputs, and the architecture of hypernets. We also review applications of hypernets across different deep learning problem settings, followed by a discussion of general
The departure of subject-matter experts from industrial organizations results in the irreversible loss of tacit knowledge that is rarely captured through conventional documentation practices. This paper proposes Expert Mind, an experimental system that leverages Retrieval-Augmented Generation (RAG), large language models (LLMs), and multimodal capture techniques to preserve, structure, and make queryable the deep expertise of organizational knowledge holders. Drawing on the specific context of the energy sector, where decades of operational experience risk being lost to an aging workforce, we describe the system architecture, processing pipeline, ethical framework, and evaluation methodology. The proposed system addresses the knowledge elicitation problem through structured interviews, think-aloud sessions, and text corpus ingestion, which are subsequently embedded into a vector store and queried through a conversational interface. Preliminary design considerations suggest Expert Mind can significantly reduce knowledge transfer latency and improve onboarding efficiency. Ethical dimensions including informed consent, intellectual property, and the right to erasure are addressed as f
Context is an important factor in computer vision as it offers valuable information to clarify and analyze visual data. Utilizing the contextual information inherent in an image or a video can improve the precision and effectiveness of object detectors. For example, where recognizing an isolated object might be challenging, context information can improve comprehension of the scene. This study explores the impact of various context-based approaches to object detection. Initially, we investigate the role of context in object detection and survey it from several perspectives. We then review and discuss the most recent context-based object detection approaches and compare them. Finally, we conclude by addressing research questions and identifying gaps for further studies. More than 265 publications are included in this survey, covering different aspects of context in different categories of object detection, including general object detection, video object detection, small object detection, camouflaged object detection, zero-shot, one-shot, and few-shot object detection. This literature review presents a comprehensive overview of the latest advancements in context-based object detecti
Two-dimensional gel electrophoresis has been instrumental in the birth and developments of proteomics, although it is no longer the exclusive separation tool used in the field of proteomics. In this review, a historical perspective is made, starting from the days where two-dimensional gels were used and the word proteomics did not even exist. The events that have led to the birth of proteomics are also recalled, ending with a description of the now well-known limitations of two-dimensional gels in proteomics. However, the often-underestimated advantages of two-dimensional gels are also underlined, leading to a description of how and when to use two-dimensional gels for the best in a proteomics approach. Taking support of these advantages (robustness, resolution, and ability to separate entire, intact proteins), possible future applications of this technique in proteomics are also mentioned.
Expert finding is an information retrieval task that is concerned with the search for the most knowledgeable people with respect to a specific topic, and the search is based on documents that describe people's activities. The task involves taking a user query as input and returning a list of people who are sorted by their level of expertise with respect to the user query. Despite recent interest in the area, the current state-of-the-art techniques lack in principled approaches for optimally combining different sources of evidence. This article proposes two frameworks for combining multiple estimators of expertise. These estimators are derived from textual contents, from graph-structure of the citation patterns for the community of experts, and from profile information about the experts. More specifically, this article explores the use of supervised learning to rank methods, as well as rank aggregation approaches, for combing all of the estimators of expertise. Several supervised learning algorithms, which are representative of the pointwise, pairwise and listwise approaches, were tested, and various state-of-the-art data fusion techniques were also explored for the rank aggregation
Single-cell proteomics (SCP) is transforming our understanding of biological complexity by shifting from bulk proteomics, where signals are averaged over thousands of cells, to the proteome analysis of individual cells. This granular perspective reveals distinct cell states, population heterogeneity, and the underpinnings of disease pathogenesis that bulk approaches may obscure. However, SCP demands exceptional sensitivity, precise cell handling, and robust data processing to overcome the inherent challenges of analyzing picogram-level protein samples without amplification. Recent innovations in sample preparation, separations, data acquisition strategies, and specialized mass spectrometry instrumentation have substantially improved proteome coverage and throughput. Approaches that integrate complementary omics, streamline multi-step sample processing, and automate workflows through microfluidics and specialized platforms promise to further push SCP boundaries. Advances in computational methods, especially for data normalization and imputation, address the pervasive issue of missing values, enabling more reliable downstream biological interpretations. Despite these strides, higher
Automated planning is a prominent area of Artificial Intelligence, and an important component for intelligent autonomous agents. A cornerstone of domain-independent planning is the separation between planning logic, i.e. the automated reasoning side, and the knowledge model, that encodes a formal representation of domain knowledge needed to reason upon a given problem to synthesise a solution plan. Such a separation enables the use of reformulation techniques, which transform how a model is represented in order to improve the efficiency of plan generation. Over the past decades, significant research effort has been devoted to the design of reformulation techniques. In this paper, we present a systematic review of the large body of work on reformulation techniques for classical planning, aiming to provide a holistic view of the field and to foster future research in the area. As a tangible outcome, we provide a qualitative comparison of the existing classes of techniques, that can help researchers gain an overview of their strengths and weaknesses.
Spatial proteomics enables single-cell-resolution characterization of protein expression within tissue architecture, playing a critical role in understanding tumor microenvironments and guiding precision medicine. However, current analysis workflows remain fragmented, requiring expert manual orchestration of heterogeneous tools and limiting research scalability and reproducibility. We present SP-Mind, the first autonomous AI agent designed to unify the spatial proteomics analysis pipeline, from raw multiplexed tissue imaging to downstream phenotype discovery. Equipped with expert-curated biological analysis skills and specialized computational tools, SP-Mind converts natural-language queries into end-to-end analytical workflows without task-specific fine-tuning. To rigorously evaluate its capabilities, we introduce SP-Bench, a comprehensive benchmark spanning diverse tissue types, comprising 102 tasks across 18 distinct categories. Through extensive evaluation on SP-Bench and established downstream tasks, SP-Mind achieves state-of-the-art performance compared to existing open-source biomedical agent baselines.