Download pdf here.
Tuesday, 9 September 2025
| 8.00 – 9.00 | Registration | |||
| 9.00 – 10.30 | Tutorials | |||
| The Virtual Brain Spase Petkoski (Aix-Marseille University, France) | Dynamic Field Theory Gregor Schöner (Ruhr-Universität Bochum, Germany) | |||
| 10.30 – 11.00 | Coffee Break | |||
| 11.00 – 12.00 | Tutorials | |||
| The Virtual Brain Marmaduke Woodman (Aix-Marseille University, France) | Dynamic Field Theory Gregor Schöner (Ruhr-Universität Bochum, Germany) | |||
| 12.00 – 13.00 | Lunch | |||
| 13.00 – 15.00 | Tutorials | |||
| GFlownets Emmanuel Bengio (Valence Labs/Recursion, Canada) | Simulated Bayesian Inference Michael Deistler (Machine Learning in Science, University of Tübingen, Germany) | Brain Visual Decoding with Generative Models Weihao Xia (University of Cambridge, UK) Cengiz Öztireli (University of Cambridge, UK) | ||
| 15.00 – 15.30 | Coffee Break | |||
| 15:30 – 17.00 | Tutorials | |||
| GFlownets Emmanuel Bengio (Valence Labs/Recursion, Canada) | Simulation-based Bayesian Inference Michael Deistler (Machine Learning in Science, University of Tübingen, Germany) | Brain Visual Decoding with Generative Models Weihao Xia (University of Cambridge, UK) Cengiz Öztireli (University of Cambridge, UK) | ||
| 17.00 – 17.30 | Coffee Break | |||
| 17.30 – 18.00 | Opening and Welcome | |||
| Stefan Wermter (President of the European Neural Network Society) Juozas Augutis (Rector of Vytautas Magnus University) | ||||
| 18.00 – 19.00 | Opening Keynote Lecture on AI Extracting Causality | |||
| Causal Representations, World Models and Digital Twins Bernhard Schölkopf (Max Planck Institute for Intelligent Systems, Tübingen, Germany) | ||||
| 19.00 – 21.00 | Concert & Welcoming Reception at Vytautas Magnus University | |||
Wednesday, 10 September 2025
| 7.30 – 8.30 | Registration | |
| 8.30 – 9.00 | Opening and Welcome | |
| Viktor Jirsa (EBRAINS Chief Science Officer) Rimantas Benetis (Rector of Lithuanian University of Health Sciences, LSMU) Arimantas Tamašauskas (Director of Neuroscience Institute, LSMU) | ||
| 9.00 – 10.00 | Keynote Lecture on Neuroscience and Whole Brain Simulations | |
| Virtual Brain Twins for Health and Disease Viktor Jirsa (Aix-Marseille University, France) | ||
| 10.00 – 10.30 | Coffee Break | |
| 10.30 – 12.00 | Invited Talks EBRAINS Morning Session | |
| 10.30 – 11.15 | Teacher Propagation Through Space, Time and the Brain Mihai Petrovici (NeuroTMA Lab, University of Bern, Switzerland) | |
| 11.15 – 12:00 | Engineering Brain Activity Patterns for Therapeutics Mehmet Fatih Yanik (ETH Zurich, Switzerland, remote) | |
| 12.00 – 13.00 | Lunch | |
| 13.00 – 15.00 | Public Keynote Lecture & Panel Discussion | |
| 13.00 – 14.00 | Public Keynote Lecture on Ethics in AI & Neuroscience Neuroscience and AI for a Flourishing Life Christiane Woopen (University of Bonn, Germany) | |
| 14.00 – 15.00 | Public Panel Discussion Where does AI lead to? Opportunities and Risks Bernhard Schölkopf, Christiane Woopen, Viktor Jirsa, Gintare Dziugaite, Yoshua Bengio (remote) | |
| 15.00 – 15.30 | Coffee Break | |
| 15.30 – 17.00 | Invited talks AI Afternoon Session | |
| 15.30 – 16.00 | Building Mechanistic Models of Neural Computations with Simulation-based Machine Learning Michael Deistler (Machine Learning in Science, University of Tübingen, Germany) | |
| 16.00 – 16.30 | Scalable Strategies for AI Oversight of AI – Progress, Pitfalls and Path Forward Ameya Pandurang Prabh (Tübingen AI Center, University of Tübingen, Germany) | |
| 16.30 – 17.00 | Embodied Reasoning in the Physical World Ignas Budvytis (University of Cambridge, UK) | |
| 17.00 – 19.00 | Poster Sessions & Coffee | |
| Poster Session 1 | Poster Session 2 | |
| 20.00 – 22.00 | Gala Dinner at Science Island, Kaunas, Lithuania | |
Thursday, 11 September 2025
| 8.00 – 9.00 | Registration | ||||||||
| 9.00 – 11. 00 | Keynote Lectures on AI | ||||||||
| 9.00 – 10.00 | AI and Generative Models Emmanuel Bengio (Valence Labs/Recursion, Canada) | ||||||||
| 10.00 – 11.00 | On Memorization and Unlearning Gintare Dziugaite (DeepMind, USA) | ||||||||
| 11.00 – 11.30 | Coffee Break | ||||||||
| 11:30 – 13.00 | Parallel Sessions & Workshop | ||||||||
| Parallel Session 1 Federated, Graph, and Edge Intelligence | Parallel Session 2 Scientific and Physics- Informed Machine Learning | Workshop 1 AI in Drug Discovery Igor Tetko (Helmholtz Munich, Germany) | |||||||
| 13.00 – 14.00 | Lunch | ||||||||
| 14.00 – 15:30 | Parallel Sessions & Workshop | ||||||||
| Parallel Session 3 Spiking and Neuromorphic Intelligence | Parallel Session 4 Reinforcement Learning and Control Systems | Workshop 2 AI in Drug Discovery Igor Tetko (Helmholtz Munich, Germany) | Workshop 3 Graph Neural Networks | ||||||
| 15.30 – 16.00 | Coffee Break | ||||||||
| 16.00 – 17.00 | Parallel Sessions | ||||||||
| Parallel Session 5 Robustness, Generalization, and Out – of-Distribution Learning | Parallel Session 6 Symbolic Reasoning, Explainability, and Structured Systems | Parallel Session 7 Foundations and Advances in Neural Network Architectures | Workshop 4 Graph Neural Networks | ||||||
| 17.00 – 18.00 | Keynote Lecture on AI | ||||||||
| A Journey through Efficient Deep Learning on Graphs Alessio Micheli (University of Pisa, Italy) | |||||||||
| 18.00 – 19.00 | European Neural Network Society ENNS General Assembly Meeting* Best Paper Award | ||||||||
| 20.00 | Sport Evening at Zalgirio Arena, Kaunas, Lithuania | ||||||||
Friday, 12 September 2025
| 9.00 – 10.00 | Registration | |
| 10.00 – 12.00 | Workshops | |
| 3rd International Workshop on Reservoir Computing Domenico Tortorella (University of Pisa, Italy) | Special Session on Neurorobotics Kristina Malinovska (Comenius University in Bratislava, Slovakia) | |
| 12.00 – 13.00 | Lunch Break | |
| 13.00 – 15.00 | Workshops | |
| 3rd International Workshop on Reservoir Computing Domenico Tortorella (University of Pisa, Italy) | Special Session on Neurorobotics Kristina Malinovska (Comenius University in Bratislava, Slovakia) | |
| 15.00 – 16.00 | Closing Remarks and Farewell | |
Presentations:
| Session | Paper Title |
| Federated, Graph, and Edge Intelligence | Enhancing Graph Neural Networks with Mixup-Based Knowledge Distillation |
| Federated, Graph, and Edge Intelligence | Accelerating Spatiotemporal Learning with minConvRNNs |
| Foundations and Advances in Neural Network Architectures | Unrolled Neural Adaptive Alternating Gradient Descent for NMF |
| Foundations and Advances in Neural Network Architectures | The Power of Max Pooling Layer |
| Foundations and Advances in Neural Network Architectures | MTL-SIMNAS: Task Similarity-Driven Neural Architecture Search for Enhanced Multi-Task Learning. |
| Foundations and Advances in Neural Network Architectures | Classification of large data sets by neural networks: A probabilistic viewpoint |
| Foundations and Advances in Neural Network Architectures | An Enhanced Dual-Stream Architecture \\ for State-of-the-Art \\ Artist and Style Classification |
| Foundations and Advances in Neural Network Architectures | Regularised Loss Function for Goal Recognition as a Deep Learning Task |
| Foundations and Advances in Neural Network Architectures | Time Series Generation for Augmenting Multi-Channel Automotive Audio Data |
| Reinforcement Learning and Control Systems | Learning to Optimize Entropy in the Soft Actor-Critic |
| Reinforcement Learning and Control Systems | Evolving Spatially Embedded Recurrent Spiking Neural Networks for Control Tasks |
| Reinforcement Learning and Control Systems | Proactive Depot Discovery: A Generative DRL Framework for Adaptive Location-Routing |
| Reinforcement Learning and Control Systems | Evaluating the Impact of Data Curation on Off-Policy Reinforcement Learning |
| Reinforcement Learning and Control Systems | A Spiking Central Pattern Generator Capable of Adaptive Gait Control in Quadruped Locomotion |
| Robustness, Generalization, and Out-of-Distribution Learning | PaRCE: Probabilistic and Reconstruction-based Competency Estimation for CNN-based Image Classification |
| Robustness, Generalization, and Out-of-Distribution Learning | Beran Estimator Kernel Learning using Nearest-Neighbours and its Application to Reliability Analysis |
| Robustness, Generalization, and Out-of-Distribution Learning | How Inductive Biases Affect OOD Generalization: An Investigation in Formal Language Recognition with Autoregressive Models |
| Robustness, Generalization, and Out-of-Distribution Learning | D2R: Dual Regularization Loss with Collaborative Adversarial Generation for Model Robustness |
| Robustness, Generalization, and Out-of-Distribution Learning | Uncertainty Quantification in Video Distortion Classification under Dataset Shift |
| Robustness, Generalization, and Out-of-Distribution Learning | XOOD: A Self-Supervised Algorithm for Detecting Out-of-Distribution Data for Image Classification |
| Scientific and Physics-Informed Machine Learning | Studying the Generalization Behavior of Surrogate Models for Punch-Bending by Generating Plausible Counterfactuals |
| Scientific and Physics-Informed Machine Learning | Sensor-Enhanced PINNs for Contaminant Dispersion Modeling |
| Scientific and Physics-Informed Machine Learning | Improving physics-informed neural network extrapolation via transfer learning and adaptive activation functions |
| Scientific and Physics-Informed Machine Learning | A Fokker-Planck Perspective on the Flow of Information in Continuous Memory Neural Networks |
| Spiking and Neuromorphic Intelligence | Firing rates and representational error in efficient spiking networks are bounded by design |
| Spiking and Neuromorphic Intelligence | Continuous representation of tactile information achieved by unsupervised liquid state machine |
| Spiking and Neuromorphic Intelligence | Full Integer Arithmetic Online Training for Spiking Neural Networks |
| Spiking and Neuromorphic Intelligence | Evaluating distributed storage mechanisms in a constructive model of associative memory |
| Symbolic Reasoning, Explainability, and Structured Systems | Small transformer architectures for task switching |
| Symbolic Reasoning, Explainability, and Structured Systems | RDGE-6D: Reverse Direction Geometry Injection for 6D Pose Estimation |
| Symbolic Reasoning, Explainability, and Structured Systems | ConSens: Assessing context grounding in open-book question answering |
| Symbolic Reasoning, Explainability, and Structured Systems | Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study |
| Symbolic Reasoning, Explainability, and Structured Systems | Correcting the Modified Stochastic Synaptic Model of Synaptic Dynamics – Refinement of Vesicle and Neurotransmitters Functions |
| Symbolic Reasoning, Explainability, and Structured Systems | Robustness Verification for Object Detectors using Set-Based Reachability Analysis |
| Symbolic Reasoning, Explainability, and Structured Systems | Identification and Realization of a Class of Discrete Event Systems by Neural Networks -Timed Petri Nets- |
| Poster session #1 | Wavelet-based Self-image Blending for More General Face Forgery Detection |
| Poster session #1 | Understanding Image Classification Prediction with Any Segment Explanation |
| Poster session #1 | Neural QSLIM for Mesh Autoencoders |
| Poster session #1 | DelGrad: Exact event-based gradients in spiking networks for training delays and weights |
| Poster session #1 | Amortizing Personnalization in Virtual Brain Twins |
| Poster session #1 | Stochastic Covariance Regularization for Imbalanced Datasets |
| Poster session #1 | Efficient Learning in Spiking Neural Networks – Introducing Feedback Alignment to the Reinforced Liquid State Machine |
| Poster session #1 | Object-Centric Dreamer |
| Poster session #1 | Backpropagation through space, time and the brain |
| Poster session #1 | Weight transport through spike timing for robust local gradients |
| Poster session #1 | Leveraging Machine-Translated Data for Sentiment Analysis in Low-Resource Languages: A Case Study on Bengali |
| Poster session #1 | The Explainability-Performance Coefficient: A New Metric for Model Transparency |
| Poster session #1 | NGAT: A Node-level Graph Attention Network for Long-term Stock Prediction |
| Poster session #1 | Continuous Fair SMOTE – Fairness-Aware Stream Learning from Imbalanced Data |
| Poster session #1 | Constrained Learnable Channel-wise Normalization for Single-Source Domain Generalization in Medical Image Segmentation |
| Poster session #1 | A Framework for Uncertainty Quantification Based on Nearest Neighbors Across Layers |
| Poster session #1 | VideoPCDNet: Video Parsing and Prediction with Phase Correlation Networks |
| Poster session #1 | Surrogate-Assisted Multi-Objective Design of Complex Multibody Systems |
| Poster session #2 | Dimensionality Reduction of Protein Language Model Embeddings for Viral Clustering |
| Poster session #2 | Efficient ReliefF: A low-power optimization of ReliefF for resource-constrained devices |
| Poster session #2 | Enhancing Adversarial Robustness through Multi-Objective Representation Learning |
| Poster session #2 | Prototype-Guided Local Spatial Attention for Model Explanation |
| Poster session #2 | Effect of Neuromodulation on the Brain Dynamical Repertoire |
| Poster session #2 | Sustainable techniques to improve Data Quality for training image-based explanatory models for Recommender Systems |
| Poster session #2 | Real-time and personalized product recommendations for large e-commerce platforms |
| Poster session #2 | MENGLAN:Multiscale Enhanced Nonparametric Gas Analyzer with Lightweight Architecture and Networks |
| Poster session #2 | ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks |
| Poster session #2 | Perpetual Generation: Online Learning of Linear State-Space Models from a Single Stream |
| Poster session #2 | DFU-Net: A Diffusion-based Fourier Neural Operator-aided U-Net Model for Medical Image Segmentation in Edge Devices |
| Poster session #2 | Targeted trust-based merging of customers’ opinions |
| Poster session #2 | A Scene Text Detection Method Based on Supervised Contrastive Learning |
| Poster session #2 | Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Rendering |
| Poster session #2 | Merging versus Separating Replay Samples in Continual Learning |
| Poster session #2 | Signal-to-noise difference as a correlate of class learning in neural networks |
| Poster session #2 | Complexity and Criticality in Neuro-Inspired Reservoirs |
| Poster session #2 | Modulation of Brain Activity via Deep Brain Stimulation in Parkinson’s Disease Patients: Individualized EEG- based assessment |
| Virtual session | HARNet: Human Activity Recognition with Spatial-temporal Features |
| Virtual session | ACGCN: A Sequence-Attention-Based Graph Convolutional Model for Enhanced Recommendation Systems |
| Virtual session | HCNQA: Enhancing 3D Visual Question-Answering with Hierarchical Concentration Narrowing Supervision |
| Virtual session | Text-Image Encoder-based Contrastive Regression for AI-Generated Image Quality Assessment |
| Virtual session | Deblurring with Improved Video Diffusion Model |
| Virtual session | Hyperparameter-Free Bi-Level Knowledge Graph Optimization for Link Prediction |
| Virtual session | MRT-NAS: Boosting Training-free NAS via Manifold Regularization |
| Virtual session | SWIFT: State-space Wavelet Integrated Forecasting Technology for Enhanced Time Series Prediction |
| Virtual session | MSfusion: A Dynamic Model Splitting Approach for Resource-Constrained Machines to Collaboratively Train Larger Models |
| Virtual session | DeepCTL: Neural Branching-Time CTL Satisfiability Checking via Recursive Decision Trees |
| Virtual session | Federated Privacy-Preserving for Cross-Domain Sequential Recommendation |
| Virtual session | Epilepsy Prediction based on Intra- and Inter-Channel Feature Mixing |
| Virtual session | MFMamba: A Hierarchical Weakly Causal Mamba with Multi-Scale Feature Fusion for Vision Tasks |
| Virtual session | F2Unet: F-shaped U-Net Architecture for Medical Image Segmentation Combining Fourier Transforms |
| Virtual session | Efficient Real-Time On-Mobile Video Super-Resolution with Automatic Evolutionary Neural Architecture Search |
| Virtual session | Swin-DAG-VNet for Fetal Head Segmentation and Elliptical Parameter Regression for Circumference Measurement |
| Virtual session | GPIS: Geometric Informed Polygon Prompt for Incision Segmentation |
| Virtual session | Characterizing trainability, expressivity and generalization of neural architecture with metrics from neural tangent kernel |
| Virtual session | Topological Enhancement Learning Module for Segmentation of Complex and Irregular Structures in 3D Medical Imaging |
| Virtual session | Multi-Representation Adapter with Neural Architecture Search for Efficient Range-Doppler Radar Object Detection |
| Virtual session | Fine-grained Recognition of Arteriovenous Fistula Stenosis Using Blood Flow Sounds: An Animal Model-Based Dataset and a Frequency-Aware Decoupling Network |
| Virtual session | SMART-RetroNet: A Framework for Chemical Retrosynthesis Prediction |
| Virtual session | LPSF-LiDARNet: Log-Polar Spatiotemporal Fusion-Based LiDAR Point Cloud Semantic Segmentation for Autonomous Driving |
| Virtual session | Few-shot Learning for Syndrome Differentiation with Two Prompts |
| Virtual session | PSRDET: Fast Multimodal Detecton based on Prior Scene Repair for All-weather Road Sensing |
| Virtual session | FedTP: Traceable Passport-based Ownership Verification for Federated Deep Neural Network Models |
| Virtual session | Art Style Backdoor Attacks on Semantic Segmentation Models |
| Virtual session | CLIP-Guided Frequency-Aware Representation Learning for Generalizable Remote-Sensing Image Tampering Detection |
| Virtual session | Parallelizing Sharpness-Aware Minimization: A Semi-Asynchronous, Small-Batch Approach |
| Virtual session | An Enhanced Audio Feature Tailored for Anomalous Sound Detection Based on Pre-trained Models |
| Virtual session | Generalized Object Detection in the Infrared Domain based on Common-Representation Learning |
| Virtual session | Balance Discriminability and Integrality for Robust Salient Object Detection |
| Virtual session | Unsupervised Domain Adaptive Hand Mesh Reconstruction of 2D Images in the Wild |
| Virtual session | Multimodal Sentiment Analysis with Parallel Attention and Correlation Fusion |
| Virtual session | Towards Context-Aware Compositional Zero-Shot Food Recognition via SalientFusion |
| Virtual session | SparWR: A Lightweight Architecture for Medical Grayscale Image Super-Resolution |
| Virtual session | A Hybrid Learning Approach for Continual Knowledge Graph Embedding: Contrastive Masking and Joint Anti-Forgetting |
| Virtual session | Sparse Attention Diffusion Model for Pathological Micrograph Deblurring |
| Virtual session | MPCCP:A Multi-chain Perception Crime Charge Prediction Method |
| Virtual session | Brain Generative Replay for Continual Learning |
| Virtual session | RRetFC: Leveraging Recursive Retrieval For LLM-Enhanced Complex Fact-Checking |
| Virtual session | Dynamic Ensembles Towards Out-Of-Distribution Generalization of Affect Models |
| Virtual session | RDIF: Infrared and Visible Image Fusion Based on Reverse Cross-Attention and Diffusion Model |
| Virtual session | Feature-Aware Sequence Models for Tabular Data Processing with Missing Values |
| Virtual session | CIBR: Cross-modal Information Bottleneck Regularization for Robust CLIP Generalization |
| Virtual session | Cascade Pre-Attention: Regulating Neuronal Activation Distributions in MetaFormer-Based Spiking Neural Networks |
| Virtual session | Topic-Driven Hyper-Relational Knowledge Graphs with Adaptive Reconstruction for Multi-Hop Question Answering Using LLMs |
| Virtual session | Towards Better Graph Anomaly Detection: A Performance-Aware Neural Architecture Search Approach |
| Virtual session | YOLO11n_BSS: Examination Room Behaviors Detection Based on Improved YOLO11n Model |
| Virtual session | Conformalized Causal Learning for Uncertainty-Aware Mineral Prospectivity Mapping |
| Virtual session | Learning Joint General and Specific Representation with Masked Auto-encoder for Radiology Report Generation |
| Virtual session | Process Adaptive Learning for Visual-Language Navigation |
| Virtual session | Audio-Driven Talking Head Generation with Emotion Based on FLAME Geometry Model |
| Virtual session | Improving Stability of Parameter Sharing in Cooperative Multi-Agent Reinforcement Learning |
| Virtual session | Efficient Long-Term Motion Feature Learning via Frequency-Based Key Frame Guidance for Action Recognition |
| Virtual session | GLFMamba-U: Global-Local Fused Mamba-Unet |
| Virtual session | Region Expansion: Optimization of Patch-fetching Method for Point Cloud Denoising |
| Virtual session | SAMTNU: Adaptive Segment Anything Model for Thyroid and Nodule Ultrasound Image Segmentation |
| Virtual session | FaceSnap: Enhanced ID-fidelity Network for Tuning-free Portrait Customization |
| Virtual session | Improving the Transferability of Point Cloud Attack via Spectral-aware Admix and Optimization Designs |
| Virtual session | Toward Better Document-Level Relation Extraction: De-Sampling and Mixture of Experts in Action |
| Virtual session | CSM: Corn Instance Segmentation Model Fusing Dilated Residual Networks and Low-Rank Adaptation |
| Virtual session | IHCP:Image Hiding against Blind Compression Based on Quality Prediction |
| Virtual session | ChiMDQA: Towards Comprehensive Chinese Document QA with Fine-grained Evaluation |
| Virtual session | Uniform Representation of Parametric CAD Models for Generative Application |
| Virtual session | Emotional Text-to-Speech via Style Decoder with Emotion Shared Styleformer Block and RoPE Prior Encoder |
| Virtual session | KANLoc: WiFi Localization with A Lightweight KAN |
| Virtual session | DualGF: Example-based Path Planning via Dual Gradient Fields |
| Virtual session | Improving monotonic optimization in heterogeneous multi-agent reinforcement learning with optimal marginal deterministic policy gradient |
| Virtual session | Early Acoustic and Vision Cross-modal Interation Learning for Multimal Sentiment Analysis |
| Virtual session | PIMSeg: Point Cloud Segmentation via 2D Image Mapping and Multimodal Feature Integration |
| Virtual session | Trustworthy Learning with Noisy Labels |
| Virtual session | Incorporating Feature Pyramid Tokenization and Open Vocabulary Semantic Segmentation |
| Virtual session | ViSMoE: Visual-Aware Sparse Mixture-of-Experts for Embodied Referring Expression Grounding |
| Virtual session | PaFi-GS: Gaussian Splatting via Propagation-Aware Filtering for Urban Street View Rendering |
| Virtual session | TimeFlowDiffuser: A Hierarchical Diffusion Framework with Adaptive Context Sampling for Multi-Horizon Time Series Forecasting |
| Reinforcement Learning and Control Systems | Dopamine-modulated Learning and Decision-making with Neuromorphic Computing |
| Virtual session | FDFRL: Credit Card Fraud Detection Based on Federated Reinforcement Learning |
| Virtual session | Vision-Text Interaction with Orientation-Awareness for Referring Remote Sensing Image Segmentation |
| Virtual session | A Unified Platform to Evaluate STDP Learning Rule and Synapse Model using Pattern Recognition in a Spiking Neural Network |
| Virtual session | ConDTab: Conditional Diffusion Transformer for Mixed-Type Tabular Synthesis with Dual Attention Latent Encoding |
| Virtual session | SentiAug: Adaptive Keywords Replacement and Confidence-guided Self-training Selection for Robust Sentiment Classification |
| Virtual session | U-FQA: A Unified Face Quality Assessment Score for Improved Unknown Identity Detection in Facial Recognition Systems |
| Virtual session | A Two-Stage Framework Integrating Prompt Learning and Fine-tuning for Code Summarization |
| Virtual session | DialGACL: Nonlinear Graph Attention Reasoning with Contrastive Learning for Complex Dialogue Fact Verification |
| Virtual session | DA-NeRF: High-Fidelity Talking Face Generation From Speech With Neural Radiance Fields |
| Virtual session | Improving Consistency Distillation with Rectified Trajectories |
| Virtual session | CM-MNet: A Coordinate Space-Aware Mamba-Based Multi-Task Model for 3D Fine Lesions in Elongated Structures Segmentation and Diagnosis in MS and NMOSD |
| Virtual session | Problem-Driven and Shape-Guided: Multi-scale Deform KAN for X-shaped Anterior Visual Pathway Segmentation |
| Virtual session | A Camouflaged Object Detection Network with Global Cross-space Perception and Flexible Local Feature Refinement Network |
| Virtual session | TimbreAdv: Timbre Adversarial Attacks on Speaker Verification Systems |
| Virtual session | Accurate SDF Reconstruction with Geometric-Differential Regularization and Categorized Sampling Strategy |
| Virtual session | See Beyond: Benchmarking MLLMs’ Visual Relational Reasoning Ability |
| Virtual session | Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay |
| Virtual session | HeteroCap: Hierarchical Visual-Semantic Fusion with Heterogeneous Graphs for Image Captioning |
| Virtual session | Dual-Head Feature Enhancement for Graph-Based Cross-View Multi-Object Tracking |
| Virtual session | Optimized Supervised Control of Stochastic Timed Discrete Event Systems using Supervisory Control Theory and Reinforcement learning |
| Virtual session | A Classification Algorithm for Bronchiolitis Obliterans in Pediatric CT Images with Extreme Class Imbalance |
| Virtual session | DISEncoder:A Dual-Branch Query Encoder Using Graph Models for Distributed Databases |
| Virtual session | A Subject-Independent Stress Detection Model Based on Temporal Feature Disentanglement |
| Virtual session | Supervised feature selection with class self-representation |
| Virtual session | PGD: Probe Guided Decoding for Alignment |
| Virtual session | Semantic Enhanced Interaction for Unsupervised Cross-modal Hashing Retrieval |
| Virtual session | FedP2PAvg: A Peer-to-Peer Collaborative Framework for Federated Learning in Non-IID Scenarios |
| Virtual session | AgileIR: Memory-Efficient Group Shifted Windows Attention for Lightweight Image Restoration |
| Virtual session | PhysMamba: Synergistic State Space Duality Model for Remote Physiological Measurement |
| Virtual session | Uncovering Causal Relation Shifts in Event Sequences under Out-of-Domain Interventions |