1
Core Machine Learning & Deep Learning
Supervised, unsupervised & self-supervised learningNeural architecturesOptimisationGenerative modelsTransfer & few-shot learningModel interpretabilityTheory of generalisation
8 tracksBroad by design
Find your track
ICMLADS is broad by design. The eight tracks below help you find where your work belongs — but they're a starting point, not a fence. If your research sits near this scope and isn't listed, submit it anyway.
2
NLP & Large Language Models
LLMs & foundation modelsRetrieval-augmented generationText miningMachine translationDialogue systemsEvaluation, alignment & safety
3
Computer Vision & Pattern Recognition
Image & video understandingObject detection & segmentationMultimodal learningMedical & remote-sensing imagingGenerative vision
4
Applied Data Science & Analytics
Predictive analyticsTime-series forecastingCausal inferenceRecommender systemsAnomaly detectionData-driven decision-makingVisual analytics
5
Data Engineering, Big Data & MLOps
Scalable data pipelinesDistributed & federated learningFeature storesModel deployment, monitoring & governanceStreaming systemsData quality
6
Reinforcement Learning & Decision Systems
RL algorithms & applicationsMulti-agent systemsOptimisation under uncertaintyControlOperations research meets learning
7
Responsible AI: Ethics, Fairness & Governance
Fairness, accountability & transparencyBias detection & mitigationPrivacy-preserving MLAI regulation & policyTrustworthy & explainable AI
8
AI for Industry
HealthcareFinanceManufacturingEnergyRetailMobilityPublic sector — where models meet real constraints and real stakes
Don't see your topic?
Submit anyway. As long as your work relates to machine learning or applied data science, it's within scope. The tracks are a map, not a gate.
Submit Abstract