Results for “robot-learning”

AutoAugment: Learning Augmentation Strategies from Data

PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Multimodal Few-Shot Learning with Frozen Language Models

Automatically evaluates Claude Code sessions to extract reusable patterns and save them as learned skills.

Continuous self-improvement through systematic logging, pattern detection, and behavioral updates. Use when: the owner corrects you, a task fails, you discover a better approach, or you notice a recurring pattern. Store raw learnings in .learnings/, update the specific skill or workflow that caused the issue when appropriate, and avoid vague promises to do better.

Recursive self-improving holon λ(ο,Κ,Σ).τ' for knowledge compounding and schema evolution. USE WHEN learning, improving, optimizing, assessing, reflecting, debugging, synthesizing, or refining—whether human, AI, or organizational. Triggers on /learn, /compound, /improve, /refine, /optimize, /assess, /reflect, "lessons learned", "best practices", "continuous improvement". Preserves Κ-monotonicity, η≥4, homoiconicity.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

LoRA: Low-Rank Adaptation of Large Language Models

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Dolphins: Multimodal Language Model for Driving

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Expert en robotique avancée (ROS, SLAM, manipulation, autonomous navigation, DZ context)

No Robots: A Dataset of Personally Written Instructions

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Manages AI model retention and machine unlearning requirements. Covers training data deletion verification, model versioning for compliance, machine unlearning techniques (SISA, gradient-based), and retraining triggers. Keywords: AI retention, machine unlearning, model versioning, training data deletion, retraining, storage limitation.

Kinetics-400: A Large Video Understanding Dataset

Matryoshka Representation Learning

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Entrena modelos de machine learning con Scikit-learn, LightGBM y XGBoost, desde un baseline hasta un modelo productivo con validación robusta y explicabilidad.

Covers AI, machine learning, LLMs, prompt engineering, and blockchain development with code examples and best practices for building AI applications and smart contracts.

Improves skills by analyzing execution data to identify patterns in successful versus failed runs, staging changes for human approval.

Training Compute-Optimal Large Language Models

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Towards Open-World Segmentation of Parts

Develop, migrate, and debug ROS 1 and ROS 2 robotics projects with support for build systems, navigation, control, simulation, and embedded integration.

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

Record, search, and prune per-project learnings in .claude/learnings.jsonl — typed, confidence-scored, searchable across sessions

Multimodal Learning with Transformers: A Survey

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Universal transformation λ(ο,K).τ with recursive self-improvement. USE WHEN routing reasoning, validating knowledge graphs, preparing CICM/ANZCA examinations, or when self-improvement of reasoning/architecture/context is required. Routes queries through R0-R3 complexity pipelines, validates topology (η≥target) and governance (KROG), emits per style (Φ), and compounds learnings into knowledge K. Triggers on complexity assessment, multi-step reasoning, examination mode, or /λ invocation.

Train large language models (7B-70B+) with RLHF using PPO, GRPO, DPO, and other algorithms, accelerated by Ray and vLLM for distributed multi-GPU setups.

Improves AI skills for activation, clarity, and cross-model reliability through benchmarking, salience tuning, and regression triage.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.