Fields

Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.

Machine learning theory, optimisation and reliability 0

Optimisation for deep learning (optimisers and schedules) 0
Generalisation, double descent and grokking 0
Robustness and distribution shift 0
Uncertainty estimation and calibration 0
Continual learning 0
Federated learning 0

Generative models 0

Diffusion and flow matching for images 0
Autoregressive and tokenizer-based generation 0
Audio and speech generation 0
Evaluation metrics for generative models 0

Graph representation learning 0

Node and graph property prediction with message-passing networks 0
Long-range dependencies, heterophily, expressivity and graph transformers 0
Link prediction and knowledge-graph completion 0
Combinatorial optimisation on graphs with GNNs 0

Time-series analysis (forecasting, foundation models, anomaly detection, classification) 0

Supervised forecasting (long-horizon multivariate and M-competition style) 0
Time-series foundation models and zero-shot forecasting 0
Time-series anomaly detection 0
Time-series classification and representation learning 0

Domain

Machine learning foundations

How learning systems are trained and why they work, and the model families the other domains build on.

Fields

Machine learning foundations

No papers here yet