Communications 2025

934 papers
Communications 2025 published 932 papers, with a strong focus on the intersection of machine learning and the biological sciences. Key research directions included recovering biological signals from sparse transcriptomics, developing protein language models for sequence representation, and utilizing Euclidean equivariant representations for molecular geometry. Clinical applications were also a major theme, specifically regarding the grounding of large language models in authoritative evidence to enhance reliability and the longitudinal modeling of brain development and disease trajectories. Methodological trends highlighted the management of stochastic instability in large language model reasoning and advancements in deep learning for live cell imaging restoration. The year's contributions spanned diverse applications, such as temporal hypergraph convolutional networks for EEG emotion recognition, video anomaly detection using multi-scale feature fusion, and studies linking sensory perception to boredom in individuals with ADHD. Prolific authors for this edition included Minh–Triet Tran, Quanying Liu, and Pablo Rivas. Other research addressed image aesthetic quality assessment through generative prompts and real estate market prediction using entropy clustering and sentiment-based frameworks.

Top Research Directions

Research directions most represented by Communications 2025 papers.

Overcoming Data Sparsity in Single Cell Sequencing 5
The Generalizability Gap Between Healthy and Clinical Brains 3
Contextual Embeddings from Protein Language Models 3
Remodeling Protein Active Sites Through Targeted Mutagenesis 3
Grounding Language Models with External Knowledge Retrieval 3
The Longitudinal Validation Gap in Developmental Science 3
Computing Minimum Energy Paths in Molecular Systems 2
Hierarchical Bayesian Parameter Estimation through Partial Pooling 2
Mitigating Off-Target Risks in Precision Genome Editing 2
The Mechanics of Digital Self Discrepancy Anxiety 2
Cross-Species Generalization of Biological Deep Learning Models 2
The Information Cost of Discretizing Continuous Data 2
Real-Time Processing for High-Throughput Scientific Sensors 2
Alternative Binders and Industrial Waste Upcycling in Concrete 2
Bridging the Spatial Scale Mismatch in Climate Projections 2

Top Authors

AuthorPapers
Quanying Liu7
Pablo Rivas6
Thanh Duc Ngo4
Azmine Toushik Wasi3
Chunhua Yang3
Dongnan Liu3
Jionglong Su3
Kang Liu3
Leilei Sun3
Mingli Song3
Tongyu Zhu3
Xueqin Wang3
Buzhou Tang2
Catie Chang2
Charlotte Deane2
Christopher Li Hsian Chen2
Chuang Liu2
Daniel Dajun Zeng2
Daniel Haeufle2
Daoqiang Zhang2

Impactful Papers

Papers from Communications 2025 that shaped research clusters.

Influential

Papers

Title
Distributed Deep Reinforcement Learning Based Deterministic Task Offloading in End-Edge-Cloud Collaborative Computing Networks
Distributed Resource Management Mechanism Based on Deep Reinforcement Learning
Districting Methods for Water Distribution Networks
DLP-FR: Learning Predictable Degradation for Robust Blind Face Restoration
DLRF-Net: A Decomposition-Driven Network for Low-Rank Infrared and Visible Image Fusion
DNP: Deep Neural Predictor Attack for Black-Box Scene Text Recognition
Doctor AI: A Hybrid Model for Clinical Ocular Disease Classification
Does AI Write More Accurately in Japanese Than Humans? A Comparison of Human and AI Speech Levels and Speech-Level Shifts in Japanese Compositions
Do High Metrics Equal Enhanced Cognitive Performance? Exploring Objective and Subjective Assessments in Digital Human Quality
Domain-enhanced dual-branch model for efficient and interpretable accident anticipation
Driver Action Recognition Based on Dynamic Adaptive Transformer
Dual Contrastive Incomplete Multi-view Clustering with Clustering-Oriented Guidance
Dual-Modal Structural Decoupling with Semantic Relation Distillation for Text-Based Person Search
Dual-Space Structure Preservation with Non-Homogeneous Fusion for Incomplete Multi-view Multi-label Classification
Dual-Stream Iterative Semantic-Aware Mechanism for Sign Language Translation
Dual-View Aware Smart Contract Vulnerability Detection for Ethereum
DuCoMo: Dual Counters in Model-Based Offline Reinforcement Learning
Dynamic Adversarial Training for Jailbreak Robustness: A Security Enhancement Scheme for LLMs
Dynamic developmental signatures of facial expression processing differ by emotion
Dynamic Evolution Analysis of Network Public Opinion in Emergencies from the Perspective of Information Ecology
Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
Dynamic Modeling and Motion Control of a Thruster-Assisted Bipedal Robot
Dynamic Period Perception and Multi-graph Integration for Temporal Knowledge Graph Completion
EasIPA: Enhancing LLM’s Ability to Select APIs for IPA
Ecological shift in a remote alpine lake in inland Asia induced by European air pollutants
Economy and Explainability with Non-separable Wavelet-Based CNN Experiments
EduChat: A Large Language Model-Based Conversational Agent for Intelligent Education
EEG neural indicator of temporal integration in the human auditory brain with clinical implications
Effective Social Media Strategies for Engaging Younger Audiences: Best Practices for Luxury Brands Targeting Millennials and Gen Z
Effects of Personalized Generative AI on Student Creativity: Evidence from Creative Performance, Self-efficacy, and Attention Allocation
Efficient Conditional Diffusion Model for Accurate Pedestrian Trajectory Prediction
Efficient Cross-Layer Coordinated Buffer Management in Datacenter Networks
Efficient Image Similarity Search with Quadtrees
Efficiently preparing chiral states via fermionic cooling on bosonic quantum hardware
Efficient Multi-task Inferencing: Model Merging with Gromov-Wasserstein Feature Alignment
EIDA: Explicit and Implicit-Space Self-supervised Learning for Visual Emotion Adaptation
Emotion-Driven Interaction Design in Regional Public Brand Apps- Enhancing User Experience Through Emotional Engagement
Empirical Study on Translating Toxic Sentences with Large Language Model vs. Machine Translation
EmuGuard: An Active Defense System for ICS Emulation
Enabling multirotor UAVs to perch, land and detach with standard propeller guards
Encoding and decoding illegal wildlife trade networks reveals key airport characteristics and undetected hotspots
Energy efficiency and carbon savings via a body grid
Energy Optimized Piecewise Polynomial Approximation Utilizing Modern Machine Learning Optimizers
Engineering virus-like particles for safe and versatile modeling of SARS-CoV-2 host interaction and immune escape
Enhanced genome editing with a Streptococcus equinus Cas9
Enhanced large language models for effective screening of depression and anxiety
Enhanced Prediction of Post-Myocardial Infarction Complications: Dual-Modality Analysis with Optimized Flow Cytometry Preprocessing and Feature Visualization
Enhanced RT-DETR for Aerial Traffic Object Detection
Enhanced Temporal Knowledge Graph Forecasting with Historical and Non-Historical Contrastive Learning
Enhancing Critical Thinking in Education by Means of a Socratic Chatbot

« prev Page 7/19 next »