Results for “masked-autoencoder”

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Trains, evaluates, and runs inference for Mask Auto-Label (MAL) weakly-supervised segmentation models using ViT-MAE backbones with minimal point or box annotations.

Trains, evaluates, exports, quantizes, and runs inference for a Mask Grounding DINO model for open-set instance segmentation guided by text prompts.

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

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.

Fine-tune, evaluate, run inference, and export Cosmos-Embed1 video-text embedding models for tasks like text-to-video retrieval and semantic deduplication.

Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace, covering architectures, routing, load balancing, and expert parallelism.

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