Foundations of Machine Learning
• Statistical Learning Theory and Generalization
• Optimization for ML (Convex, Non Convex, Large Scale)
• Probabilistic Modeling, Bayesian Learning and Graphical Models
• Causal Inference, Causal ML and Counterfactual Reasoning
• Online Learning, Meta Learning and Continual Learning
• Multi Task Learning, Transfer Learning and Domain Adaptation
• Theory of Deep Learning and Emergent Behaviors
Deep Learning and Representation Learning
• Neural Network Architectures and Training Techniques
• Self Supervised Learning and Contrastive Learning
• Generative Models (GANs, Diffusion Models, VAEs)
• Diffusion Models for Images, Text, Time Series, Molecules and Graphs
• Foundation Models, LLMs, Vision Language Models and Multimodal Models
• Efficient Deep Learning (Pruning, Quantization, Distillation)
• Representation Learning for Structured, Temporal and Graph Data
Reinforcement Learning, Decision Making and Embodied AI
• Deep Reinforcement Learning and Policy Optimization
• Multi Agent RL, Game Theory and Coordination
• Offline RL, Safe RL and Risk Sensitive RL
• World Models, Embodied AI and Interactive Learning
• RL for Robotics, Control Systems and Real World Deployment
• Hierarchical RL and Skill Discovery
• Planning Augmented Models and Decision Transformers
Natural Language Processing, Speech and Multimodal AI
• Large Language Models and Instruction Tuned Models
• Retrieval Augmented Generation (RAG) and Knowledge Grounded Models
• Long Context Models, Memory Augmented Models and Tool Using LLMs
• Text Generation, Summarization and Dialogue Systems
• Speech Recognition, Speech Synthesis and Audio Language Models
• Vision Language Models, Video Language Models and Multimodal Fusion
• NLP for Low Resource Languages and Cross Lingual Learning
Computer Vision, Perception and Graphics
• Image Classification, Detection and Segmentation
• 3D Vision, Scene Understanding and SLAM
• Vision Transformers and Diffusion Based Vision Models
• Video Understanding, Action Recognition and Motion Prediction
• Generative Vision Models, Neural Rendering and 3D Generation
• Embodied Perception and Interactive Vision
• Vision Language Action Models for Robotics
Data Mining, Knowledge Discovery and Graph Learning
• Graph Neural Networks (GNNs) and Graph Representation Learning
• Knowledge Graphs, Reasoning and Neuro Symbolic AI
• Large Scale Data Mining and Pattern Discovery
• Time Series Forecasting, Anomaly Detection and Predictive Modeling
• Simulation Based ML and Synthetic Data Generation
• ML for Structured, Relational and Heterogeneous Data
Trustworthy, Explainable and Responsible AI
• Explainable AI (XAI) and Mechanistic Interpretability
• Fairness, Accountability, Transparency and Ethics in ML
• Robust ML, Adversarial Attacks and Defenses
• Jailbreak Resistant LLMs and Safety Evaluation
• Privacy Preserving ML (Differential Privacy, Federated Learning, Secure ML)
• Safety Critical ML and Reliability
• AI Governance, Risk Assessment and Policy Aligned ML
ML Systems, Hardware Acceleration and Efficient Computing
• Distributed and Parallel ML Systems
• Training and Inference Optimization for Foundation Models
• ML Compilers, Optimization and Deployment Frameworks
• Edge ML, TinyML and On Device Learning
• Edge Native Foundation Models and Distributed Inference
• Neuromorphic Computing and Brain Inspired ML
• Energy Efficient ML, Green AI and Carbon Aware ML Pipelines
Applied Machine Learning and Domain Specific ML
• Healthcare and Life Sciences
• Medical Imaging, Diagnostics and Clinical Decision Support
• Computational Biology, Genomics and Drug Discovery
• Digital Health, Wearables and Personalized Medicine
• ML for Neuroscience and Cognitive Modeling
• ML for Digital Therapeutics and Clinical Decision Automation
Science and Engineering
• ML for Physics, Chemistry, Materials Science and Climate Modeling
• Physics Informed ML and Scientific Machine Learning (SciML)
• Differentiable Physics, Neural Simulators and ML Accelerated Simulation
• ML for Robotics, Autonomous Systems and Control
• ML for Smart Cities, IoT and Cyber Physical Systems
Business, Finance and Social Systems
• ML for Finance, Risk Modeling and Fraud Detection
• Recommender Systems, Personalization and User Modeling
• Social Network Analysis and Computational Social Science
• ML for Policy Simulation and Societal Impact Modeling
Emerging Trends
• Agentic AI, Autonomous AI Systems and Multi Agent LLM Ecosystems
• Tool Using AI, Planning Augmented LLMs and Autonomous Agents
• Program Synthesis, AI for Code and ML Guided Theorem Proving
• Quantum Machine Learning and Quantum Inspired Algorithms
• AutoML, Neural Architecture Search (NAS) and Hyperparameter Optimization
• ML for Foundation Model Alignment, Safety and Governance
• ML for Autonomous Scientific Discovery and Robot Scientists
• ML for Synthetic Biology, Bio Inspired Algorithms and Living Systems

Hard copy of the proceedings will be distributed during the Conference. The softcopy will be available on AIRCC digital library.