CACML 2027 welcomes relevant paper submissions from researchers in academia, industry, and government, such as students, engineers, practitioners, scientists, and policy makers. We welcome paper submissions with original technical and scientific research results in relevant topics.
Main Topics of Interest:
Track 1: Algorithm Design and Analysis |
|---|
| Graph algorithms and combinatorial optimization |
| Approximation, randomized, and online algorithms |
| Parameterized and exact algorithms |
| Algorithmic game theory and mechanism design |
| Streaming, sketching, and sublinear algorithms |
| Parallel, distributed, and quantum algorithms |
| Algorithm engineering and performance evaluation |
| Theoretical foundations of machine learning algorithms |
| Optimization algorithms (convex, non-convex, metaheuristic) |
Track 2: Machine Learning Theories and Models |
| Supervised, unsupervised, semi-supervised, and self-supervised learning |
| Deep learning architectures (CNN, RNN, Transformer, GNN, State Space Models) |
| Reinforcement learning and multi-agent learning |
| Generative models (GANs, VAEs, diffusion models, flow-based models) |
| Transfer learning, meta-learning, and few-shot/zero-shot learning |
| Explainable, interpretable, and robust machine learning |
| Federated learning, distributed learning, and privacy-preserving ML |
| Bayesian inference and probabilistic graphical models |
| Representation learning and manifold learning |
Track 3: Computing Paradigms and Infrastructures |
| Cloud, edge, fog, and serverless computing architectures |
| High-performance computing (HPC) and parallel/distributed systems |
| Quantum computing and novel computational models |
| Big data processing frameworks (Hadoop, Spark, Flink) |
| GPU/TPU/NPU acceleration for AI workloads |
| Containerization, orchestration, and MLOps |
| Operating systems, virtualization, and system software |
| Green computing and energy-efficient algorithms |
| Computational complexity and resource-aware computing |
Track 4: AI-Enabled Applications and Interdisciplinary Innovations |
| Natural language processing and large language models (LLMs) |
| Computer vision, image/video understanding, and multimodal learning |
| Speech and audio processing |
| Recommender systems and personalization |
| Healthcare, bioinformatics, and biomedical data analysis |
| Financial modeling, algorithmic trading, and fraud detection |
| Autonomous systems and robotics |
| AI for science (climate, materials, physics, chemistry) |
| Social network analysis and graph mining |
| Time series forecasting and anomaly detection |
Track 5: Emerging Frontiers in Algorithms, Computing, and Machine Learning |
| Neural architecture search and automated machine learning (AutoML) |
| Model compression, pruning, quantization, and efficient inference |
| Retrieval-augmented generation (RAG) and knowledge-enhanced models |
| Agentic AI, planning, and reasoning with foundation models |
| Edge AI, tinyML, and on-device intelligence |
| Causal inference and discovery |
| Adversarial robustness, model security, and safety |
| Ethical AI, fairness, bias detection, and mitigation |
| Federated and split learning for decentralized data |
| AI-driven algorithm design (learning-augmented algorithms) |
