Call for Papers
Track 1 – Statistical Learning Theory and Methods
Foundations of statistical learning and inference
High-dimensional statistics and regularisation techniques
Bayesian learning, probabilistic models, and uncertainty quantification
Robust statistics and outlier-resistant learning methods
Graphical models and structured prediction
Semi-supervised and unsupervised learning methods
Statistical optimisation techniques for large-scale problems
Conformal prediction and distribution-free inference
Track 2 – Machine Learning, Deep Learning, and Hybrid Approaches
Foundations and advances in machine learning and data mining
Reinforcement learning and adaptive decision-making
Transfer learning, domain adaptation, and meta-learning
AutoML and neural architecture search
Explainable and interpretable ML models
Time-series forecasting and sequential data modeling
Quantum machine learning and emerging paradigms
Anomaly detection, ensemble methods, and model aggregation
ML for healthcare, diagnostics, and biomedical data
Track 3 – Generative AI and Foundation Models
Generative adversarial networks (GANs) and variational autoencoders (VAEs)
Diffusion models, energy-based models, and flow-based generative techniques
Large language models (LLMs) and multimodal foundation models
Data synthesis, augmentation, and privacy-preserving generation
Controllable text, image, and audio generation
Evaluation, alignment, and safety of generative models
Few-shot, zero-shot, and prompt-based learning techniques
Applications of generative AI in science, design, and industry
Track 4 – Natural Language Processing and Multimodal Understanding
Sentiment and emotion analysis, opinion mining
Information retrieval, question answering, and knowledge-augmented LLMs
Conversational agents, dialog management, and interactive AI
Cross-lingual NLP and low-resource language processing
Neural machine translation and speech-language models
Text summarization, argument mining, and discourse analysis
Multimodal fusion of text, audio, and vision data
Ethical considerations in language and multimodal models
Track 5 – Computer Vision, Image Processing, and 3D Understanding
Foundations and advances in computer vision and image processing
Semantic and instance segmentation, object detection in complex scenes
Visual reasoning, image captioning, and visual question answering
Video understanding, activity recognition, and temporal vision
3D reconstruction, SLAM, and multi-view geometry
Generative image and video synthesis
Facial recognition, affective computing, and biometrics
Image forgery detection, tamper analysis, and deepfake detection
Vision for autonomous systems and human-centric AI
Track 6 – Data Science, Analytics, and Real-World Applications
Foundations and advances in data science, analytics, and real-world systems
Big data analytics and scalable data processing
AI-driven decision support systems
Smart city and urban computing applications
AI in finance, fintech, and risk modeling
Healthcare analytics and personalized medicine
Intelligent transportation, logistics, and mobility solutions
AI for environmental sustainability and climate modeling
Educational analytics and adaptive learning platforms
Track 7 – Robotics, Autonomous Systems, and Edge Intelligence
Learning-based control and safe autonomous navigation
Human-robot interaction, social and collaborative robotics
Swarm intelligence and distributed decision-making
Perception and sensing for robotic platforms
AI at the edge: low-latency, resource-aware intelligence
Soft robotics, bio-inspired systems, and adaptive mechanisms
Reinforcement learning for real-world robotic applications
Reliable and explainable autonomous systems in safety-critical domains