Results for “pre-pr”

Access AI-ready drug discovery datasets, benchmarks, and molecular oracles from Therapeutics Data Commons for therapeutic machine learning and pharmacological prediction.

Computes the SQuAD metric using torchmetrics, given predictions and ground truth. Use when evaluating question-answering outputs with exact match and F1 scores.

Reduce high-dimensional data with UMAP for visualization, clustering preprocessing, and supervised or semi-supervised learning, including parameter tuning guidance.

Evaluates how well internal model representations (hidden states) predict token-level information importance in summarization tasks, using NDCG@10 and Spearman's rank correlation.

Build and train graph neural networks for drug discovery, protein modeling, and molecular science using PyTorch-native tools.

Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface, covering loading, preprocessing, drift correction, spike sorting, quality metrics, and unit curation.

Quantize large language models to 4-bit precision using activation-aware weight quantization, reducing memory footprint and speeding up inference with minimal accuracy loss.

Predict molecular properties, train graph neural networks, and run drug discovery workflows using DeepChem's featurizers, models, and MoleculeNet benchmarks.

Provides expert guidance for distributed training with DeepSpeed, covering ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, and sparse attention.

Train large-scale MoE models with FP8/INT4 low-precision RL, speculative decoding, and train-inference alignment using the miles framework.

Build, fit, validate, and compare Bayesian models using PyMC, including hierarchical models, MCMC sampling, variational inference, posterior predictive checks, and model comparison.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Integrate a HuggingFace computer vision model into the NVIDIA TAO Toolkit ecosystem, covering the full pipeline from prerequisites to container testing.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends and integrations with HuggingFace Transformers, vLLM, and PEFT/LoRA.

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking, creates orchestration DAGs, builds feature store schemas, deploys model registries, and automates retraining and validation workflows.

Performs finite element analysis, computational fluid dynamics, thermal analysis, modal analysis, and design optimization for validating designs against physical loads and predicting product behavior.

Predicts chromatin state across 919 tracks (histone marks, DNase, TF binding) for DNA sequences via the hosted Genomic Intelligence API, producing a report and JSON results.

Collects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

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

Predict continuous values from temporal sequences using aeon's time series regressors, covering convolutional, deep learning, distance-based, feature-based, hybrid, interval-based, and shapelet-based approaches.

Quantifies the minimum accuracy gap needed between two models for a sampled micro-benchmark to reliably preserve their ranking, using the MDAD metric from Yauney et al. (2025).

Fine-tune Gemma models locally using QLoRA, Unsloth, or TRL for SFT, DPO, and reward modeling, with dataset preparation and conversion to GGUF or LiteRT-LM.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends for deployment with vLLM or HuggingFace Transformers.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Run TAO SDK jobs as Docker containers on a local or remote Docker daemon with NVIDIA GPU support, including preflight checks and credential handling.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

Generates and analyzes proteins using ESM3 and ESM C language models, covering sequence generation, structure prediction, inverse folding, embeddings, and function conditioning with local or cloud-based Forge API inference.

Load pre-trained models from Hugging Face Hub, run pipeline inference, generate text, and fine-tune models on NLP, vision, audio, and multimodal tasks using the Transformers library.

Generate high-quality sentence and text embeddings for semantic similarity, clustering, and retrieval using 5000+ pre-trained models. Supports multilingual and domain-specific embeddings for RAG and semantic search.

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.

Convert chemical structures (SMILES or RDKit molecules) into numerical representations for machine learning, covering 100+ featurizers including ECFP, MACCS, descriptors, and pretrained models like ChemBERTa, with support for QSAR modeling and virtual screening.

Evaluates text-to-image generation models by decomposing assessment into five specialized skills (object presence, count, spatial relations, scale, and text rendering) and open-ended prompts, producing interpretable binary scores with visual and textual explanations.

Analyze whole-slide pathology images with Python: load 160+ slide formats, preprocess H&E stains, segment nuclei, construct spatial graphs, train ML models, and process multiplex immunofluorescence data (CODEX, Vectra).

Extract false-positive and false-negative gaps from VLM binary-classification-question predictions by comparing model responses against ground truth, producing a structured JSONL file and summary report for downstream root-cause analysis.

Quantifies how sensitive a language model benchmark's reliability and ranking stability are to specific design choices, such as the selection of scenarios, subscenarios, examples, and few-shot prompts. Use when the user has predictions and gold and needs to compute DIoR.