Skip to main content

Roadmap

We’re continuously expanding AITraining’s capabilities. Here’s what’s currently supported and what’s coming next.

Currently Supported

LLM Training

  • SFT - Supervised Fine-Tuning for instruction following
  • DPO - Direct Preference Optimization
  • ORPO - Odds Ratio Preference Optimization
  • PPO - Proximal Policy Optimization (RL)
  • Reward Modeling - Train reward models for RLHF
  • Knowledge Distillation - Transfer knowledge from larger models

Text Tasks

  • Text Classification - Sentiment, spam detection, categorization
  • Token Classification - NER, POS tagging, entity extraction
  • Sequence-to-Sequence - Translation, summarization
  • Extractive QA - Answer questions from context
  • Sentence Transformers - Semantic similarity embeddings

Vision Tasks

  • Image Classification - Categorize images into labels
  • Image Regression - Predict continuous values from images
  • Object Detection - Locate and identify objects in images
  • Vision-Language Models - Multimodal image+text tasks

Tabular Data

  • XGBoost - Gradient boosting
  • LightGBM - Fast gradient boosting
  • Random Forest - Ensemble decision trees
  • CatBoost - Categorical feature handling
  • ExtraTrees - Extremely randomized trees

Reinforcement Learning

  • PPO Trainer - Proximal Policy Optimization for LLMs
  • DPO Trainer - Direct Preference Optimization
  • Reward Models - Standard, pairwise, and multi-objective
  • RL Environments - Text generation, math problems, code generation
  • Async Forward-Backward Pipeline - Efficient training pipeline

Planned Training Tasks

Vision Tasks (Planned)

TaskDescriptionStatus
Image SegmentationPixel-level labeling for medical imaging, satellite analysis, background removalPlanned
Semantic SegmentationScene understanding with class labels per pixelPlanned
Instance SegmentationDetect and segment individual object instancesPlanned
Panoptic SegmentationCombined semantic + instance segmentationPlanned

Time Series & Forecasting (Planned)

TaskDescriptionStatus
Time Series ForecastingPredict future values (stock prices, demand, weather)Planned
Anomaly DetectionIdentify outliers in sequential dataPlanned
Time Series ClassificationClassify sequences (ECG, sensor data, activity recognition)Planned

Additional ML Algorithms (Planned)

TaskDescriptionStatus
Support Vector MachinesSVMs for classification and regressionPlanned
K-Nearest NeighborsInstance-based learningPlanned
Gaussian ProcessesProbabilistic predictions with uncertaintyPlanned
Neural Networks (sklearn)Simple MLPs for tabular dataPlanned

Specialized LLM Training (Planned)

TaskDescriptionStatus
Code LLM Fine-tuningSpecialized training for code generation modelsPlanned
Math ReasoningTrain models for mathematical problem solvingPlanned
Multi-turn DialogueEnhanced conversation modelingPlanned
Tool Use / Function CallingTrain models to use external toolsPlanned
Agentic BehaviorsTrain models for autonomous task completionPlanned

Audio & Speech (Planned)

TaskDescriptionStatus
Speech Recognition (ASR)Automatic speech-to-textPlanned
Text-to-Speech (TTS)Voice synthesis and cloningPlanned
Audio ClassificationSound event detection, music genre classificationPlanned
Speaker DiarizationIdentify who spoke whenPlanned

Multimodal (Planned)

TaskDescriptionStatus
Video UnderstandingAction recognition, video captioningPlanned
Document AILayout analysis, form understandingPlanned
Chart/Graph UnderstandingExtract data from visualizationsPlanned
3D VisionPoint cloud processing, depth estimationPlanned

Specialized Domains (Planned)

TaskDescriptionStatus
Medical/Clinical NLPHIPAA-aware training for healthcarePlanned
Legal Document AnalysisContract review, case law searchPlanned
Scientific LiteraturePaper parsing, citation analysisPlanned
Financial AnalysisSentiment, risk assessment, report generationPlanned

Planned Features

Training Enhancements

  • Ray Tune integration for distributed sweeps
  • Curriculum learning support
  • Continual learning / catastrophic forgetting prevention
  • Mixture of Experts (MoE) fine-tuning
  • Speculative decoding training

Infrastructure

  • Full TUI (Terminal User Interface) wizard
  • Web-based training UI
  • Kubernetes deployment templates
  • AWS/GCP/Azure marketplace images

Evaluation

  • Automated red-teaming
  • Bias and fairness benchmarks
  • Domain-specific evaluation suites
  • Human preference collection interface

Vote for Features

Want to influence our priorities? Let us know what matters most to you:

Contributing

Interested in helping build these features? We welcome contributions:
  • Core Development: Python, PyTorch, Transformers
  • Documentation: Help us document new features
  • Testing: Test new trainers and report issues
  • Examples: Share your training recipes
See our GitHub repository for contribution guidelines.

Release Notes

For current features and recent updates, see the Changelog.