Results for “model-extraction”

Reads and preprocesses 5-minute stock candlestick CSV data, then clusters the time series using tslearn's TimeSeriesKMeans, including data cleaning, percentage change calculation, model training, saving, and representative sample extraction.

TRAK: Attributing Model Behavior at Scale

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

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

Train, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.

Train, evaluate, export, quantize, and run inference on Mask2Former models for panoptic, instance, and semantic segmentation using NVIDIA TAO.

Convert daily market observations and news reactions into structured edge hints, with optional LLM augmentation, outputting a canonical hints.yaml for downstream concept synthesis.

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

Extract features from 1D signals using signalTimeFeatureExtractor, signalFrequencyFeatureExtractor, and signalTimeFrequencyFeatureExtractor. Use when computing time-domain features (amplitude, energy, shape factors), frequency-domain features (spectral location, power, bandwidth, PSD), or time-frequency features (spectral shape, instantaneous, ridges, wavelet, EMD-derived) on a per-frame basis. Use when the user asks to "extract features", "compute spectral features", "build a feature table for a classifier", "get per-frame statistics", "run feature extraction on this signal", or describes a vibration / biosignal / radar / sensor signal needing features for downstream ML or analysis. Includes optional GPU acceleration via canUseGPU and gpuArray. Does not cover filter design, audio-specific feature extraction (use audioFeatureExtractor in Audio Toolbox instead), batch dataset orchestration, or 2D / image features.

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new contexts.

Every metric encodes an opinion about which mistake hurts.

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.

"Make it interpretable" is four different requests.

Evaluate model quality with task-appropriate metrics and systematic error analysis. Use when: (1) comparing models, (2) analyzing failures, (3) setting go/no-go thresholds. NOT for: production monitoring implementation.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for

Extract and preprocess tiles from whole-slide images (WSI) with histolab — OpenSlide-backed slide loading, tissue detection and masks, Random/Grid/Score tile extraction, and image/morphological filters for H&E preprocessing. Use when the user needs lightweight WSI slide preprocessing — building tile datasets for ML training, tissue segmentation, or quick tile-based inspection of histopathology slides. For end-to-end computational-pathology, deep-learning model training, nucleus segmentation, or multiplexed/spatial-proteomics (CODEX, Vectra) pipelines prefer alterlab-pathml instead. Part of the AlterLab Academic Skills suite.

Run full computational-pathology workflows with PathML — whole-slide-image (WSI) analysis across 160+ slide formats, multiplexed immunofluorescence (CODEX, Vectra, MERFISH), nucleus segmentation/classification (HoVer-Net, HACTNet), tissue- and cell-graph construction, HDF5 dataset management, and deep-learning model training on pathology data. Use when the user builds end-to-end deep-learning pathology pipelines, analyzes multiplexed or spatial-proteomics slides, or segments nuclei. For lightweight H&E slide preprocessing, tissue masking, or plain Random/Grid/Score tile extraction prefer alterlab-histolab instead. Part of the AlterLab Academic Skills suite.