Preview - rendered architecture diagrams; full validated atlas + dataset coming.

Model gallery

14291 rendered preview records from the generated catalog export.

Showing 13297-13343 of 14291 models

Universal Transformer (recurrent self-attention with ACT) architecture thumbnail

Universal Transformer (recurrent self-attention with ACT)

universal transformer history not forward validated

Universal Transformer (recurrent self-attention with ACT) architecture thumbnail

Universal Transformer (recurrent self-attention with ACT)

universal transformer time-series_dynamics not forward validated

UniVLA architecture thumbnail

UniVLA

univla RL_robotics_control not forward validated

UniVLA (unified vision-language-action autoregressive transformer) architecture thumbnail

UniVLA (unified vision-language-action autoregressive transformer)

univla unified history not forward validated

univnet:base-vocoder architecture thumbnail

univnet:base-vocoder

univnet base audio_speech not forward validated

uno architecture thumbnail

uno

uno scientific_physics_weather_PDE not forward validated

UPerNet_beit_base architecture thumbnail

UPerNet_beit_base

upernet beit vision_segmentation not forward validated

unknown 529 ops

UPerNet_convnext_base architecture thumbnail

UPerNet_convnext_base

upernet convnext vision_segmentation not forward validated

unknown 529 ops

UPerNet_convnext_tiny architecture thumbnail

UPerNet_convnext_tiny

upernet convnext vision_segmentation not forward validated

unknown 529 ops

upernet:semantic-segmentation architecture thumbnail

upernet:semantic-segmentation

upernet semantic vision_classification-backbone not forward validated

unknown 529 ops

UPerNet_swin_base architecture thumbnail

UPerNet_swin_base

upernet swin vision_segmentation not forward validated

unknown 529 ops

UPerNet_swin_tiny architecture thumbnail

UPerNet_swin_tiny

upernet swin vision_segmentation not forward validated

unknown 529 ops

UQNO architecture thumbnail

UQNO

uqno scientific_physics_weather_PDE not forward validated

unknown 241 ops

USAD reference UsadModel architecture thumbnail

USAD reference UsadModel

usad reference time-series_dynamics not forward validated

USAD reference UsadModel (two-decoder anomaly autoencoder) architecture thumbnail

USAD reference UsadModel (two-decoder anomaly autoencoder)

usad reference history not forward validated

USAD (two-decoder adversarial autoencoder) architecture thumbnail

USAD (two-decoder adversarial autoencoder)

usad two history not forward validated

Uttley conditional-probability machine / Informon architecture thumbnail

Uttley conditional-probability machine / Informon

uttley conditional history not forward validated

uvit_diffusion architecture thumbnail

uvit_diffusion

uvit diffusion vision_classification-backbone not forward validated

unknown 142 ops

uvit_small architecture thumbnail

uvit_small

uvit small vision_classification-backbone not forward validated

unknown 142 ops

UVit2DModel architecture thumbnail

UVit2DModel

uvit2dmodel generative_diffusion-GAN-flow not forward validated

unknown 437 ops

V-JEPA ViT-Huge (joint embedding predictive video ViT) architecture thumbnail

V-JEPA ViT-Huge (joint embedding predictive video ViT)

v jepa history not forward validated

V-JEPA ViT-Huge (latent video joint-embedding predictor) architecture thumbnail

V-JEPA ViT-Huge (latent video joint-embedding predictor)

v jepa history not forward validated

V-JEPA ViT-Large (joint embedding predictive video ViT) architecture thumbnail

V-JEPA ViT-Large (joint embedding predictive video ViT)

v jepa history not forward validated

V-JEPA ViT-Large (latent video joint-embedding predictor) architecture thumbnail

V-JEPA ViT-Large (latent video joint-embedding predictor)

v jepa history not forward validated

V-JEPA2 architecture thumbnail

V-JEPA2

v jepa2 video_action not forward validated

V-JEPA2 ViT-G/16 256 (action-conditioned latent video predictor) architecture thumbnail

V-JEPA2 ViT-G/16 256 (action-conditioned latent video predictor)

v jepa2 history not forward validated

unknown 112 ops

V-JEPA2 ViT-G/16 384 (action-conditioned latent video predictor) architecture thumbnail

V-JEPA2 ViT-G/16 384 (action-conditioned latent video predictor)

v jepa2 history not forward validated

unknown 112 ops

V-JEPA2 ViT-g16 256 (latent video prediction ViT) architecture thumbnail

V-JEPA2 ViT-g16 256 (latent video prediction ViT)

v jepa2 history not forward validated

V-JEPA2 ViT-g16 384 (latent video prediction ViT) architecture thumbnail

V-JEPA2 ViT-g16 384 (latent video prediction ViT)

v jepa2 history not forward validated

V-JEPA2 ViT-H/16 256 (action-conditioned latent video predictor) architecture thumbnail

V-JEPA2 ViT-H/16 256 (action-conditioned latent video predictor)

v jepa2 history not forward validated

V-JEPA2 ViT-H16 256 (latent video prediction ViT) architecture thumbnail

V-JEPA2 ViT-H16 256 (latent video prediction ViT)

v jepa2 history not forward validated

V-JEPA2 ViT-L/16 256 (action-conditioned latent video predictor) architecture thumbnail

V-JEPA2 ViT-L/16 256 (action-conditioned latent video predictor)

v jepa2 history not forward validated

V-JEPA2 ViT-L16 256 (latent video prediction ViT) architecture thumbnail

V-JEPA2 ViT-L16 256 (latent video prediction ViT)

v jepa2 history not forward validated

VAC-CSLR architecture thumbnail

VAC-CSLR

vac cslr video_action not forward validated

VAC-CSLR (CNN + 1D-temporal + BiLSTM CTC sign-language, visual-alignment aux head) architecture thumbnail

VAC-CSLR (CNN + 1D-temporal + BiLSTM CTC sign-language, visual-alignment aux head)

vac cslr history not forward validated

VAE-original architecture thumbnail

VAE-original

vae original generative_diffusion-GAN-flow not forward validated

VAE with VampPrior (variational mixture of posteriors prior) architecture thumbnail

VAE with VampPrior (variational mixture of posteriors prior)

vae with history not forward validated

VAE with VampPrior (variational mixture of posteriors prior) architecture thumbnail

VAE with VampPrior (variational mixture of posteriors prior)

vae with generative_diffusion-GAN-flow not forward validated

vall_e_neural_codec_lm architecture thumbnail

vall_e_neural_codec_lm

vall e audio_speech not forward validated

vall_e_x_codeclm architecture thumbnail

vall_e_x_codeclm

vall e audio_speech not forward validated

van:image-classification architecture thumbnail

van:image-classification

van image vision_classification-backbone not forward validated

unknown 762 ops

VAR (Visual Autoregressive, next-scale coarse-to-fine prediction) architecture thumbnail

VAR (Visual Autoregressive, next-scale coarse-to-fine prediction)

var visual history not forward validated

unknown 181 ops

Variance-Preserving Flow Matching (VP interpolant, sigma-augmented time embedding) architecture thumbnail

Variance-Preserving Flow Matching (VP interpolant, sigma-augmented time embedding)

variance preserving history not forward validated

vaultgemma architecture thumbnail

vaultgemma

vaultgemma NLP_LLM_text not forward validated

unknown 165 ops

VDSR architecture thumbnail

VDSR

vdsr generative_diffusion-GAN-flow not forward validated

Vector Neurons VN-PointNet (SO(3)-equivariant 3D-vector neurons) architecture thumbnail

Vector Neurons VN-PointNet (SO(3)-equivariant 3D-vector neurons)

vector neurons history not forward validated

Vector Neurons (VNN) architecture thumbnail

Vector Neurons (VNN)

vector neurons 3D_geometry_NeRF_point-cloud not forward validated

VectorNeurons architecture thumbnail

VectorNeurons

vectorneurons exotic_other not forward validated