PatchFM is a basic model for univariate time series forecasting based on the Transformer architecture. It uses a block-by-block forecasting method, drawing on the training ideas of large language models to divide the time series into blocks for next-block forecasting. It supports multi-quantile output and uncertainty estimation.

Scientific ComputingSafetensors

ConfTuner-Ministral is a quantized large language model based on the Mistral architecture, specifically fine-tuned for trustworthy AI scenarios, supporting text generation and confidence estimation functions. The model offers multiple quantized versions suitable for different resource-constrained environments.

Natural Language ProcessingTransformersEnglish

This is a static quantized version of the liushiliushi/ConfTuner-Ministral model, suitable for text generation and confidence estimation tasks. This model is based on the Mistral architecture and has been fine-tuned to provide reliable AI outputs. It supports multiple quantization levels to meet different hardware requirements.

Natural Language ProcessingTransformersEnglish

MapAnything is an end-to-end trained Transformer model that can take multiple modalities as input and directly regress the decomposed metric 3D geometric structure of the scene. This model supports more than 12 different 3D reconstruction tasks, including multi-image SfM, multi-view stereo vision, and monocular metric depth estimation.

Computer VisionSafetensorsEnglish

DINOv3 is a series of general visual foundation models developed by Meta AI. Without fine-tuning, it can outperform specialized state-of-the-art models in a wide range of visual tasks. This model uses self-supervised learning to generate high-quality dense features and performs excellently in various tasks such as image classification, segmentation, and depth estimation.

Computer VisionTransformersEnglish

An advanced Vision Transformer model that can simultaneously perform high-precision age estimation and gender classification, achieving a gender classification accuracy of 94.3% and an average absolute age error of 4.5 years on the UTKFace dataset.

Computer VisionPytorchEnglish

LightGlue is an efficient model for keypoint matching that can adaptively adjust the amount of computation and is suitable for tasks such as image matching and pose estimation.

Computer VisionTransformers

MEMFOF is a memory-efficient optical flow estimation method designed for full HD videos, combining high precision and low memory usage.

Computer VisionPytorchEnglish

A diffusion model-based video frame interpolation tool supporting multi-frame input with uncertainty estimation

Computer VisionSafetensorsEnglish

Image depth estimation model based on Latent Bridging Matching (LBM) technology, achieving rapid image transformation through latent space bridging

Computer VisionSafetensors

Distill-Any-Depth is a new SOTA monocular depth estimation model trained using knowledge distillation algorithms.

Computer VisionTransformers

Distill-Any-Depth is a SOTA monocular depth estimation model trained based on knowledge distillation algorithms, capable of efficient and accurate depth estimation.

Computer VisionTransformers

Distill-Any-Depth is a model for depth estimation, based on the transformers architecture, suitable for estimating depth information from images.

Computer VisionTransformers

PoseLess is an innovative robotic hand control framework that directly maps 2D images to joint angles using projection representations, eliminating the need for explicit pose estimation.

MultimodalTransformers

Poseless-3B is a vision-language model (VLM)-based robotic hand control framework that directly maps 2D images to joint angles without explicit pose estimation.

MultimodalTransformers

LightGlue is an efficient keypoint detection and matching model for feature matching and pose estimation problems in computer vision.

Computer VisionTransformers

A machine translation quality estimation model fine-tuned based on ModernBERT-base, supporting long-context document-level evaluation

Natural Language ProcessingTransformersMultiple Languages

A depth estimation model from the Lotus model series, utilizing diffusion model technology for high-quality dense prediction

Computer VisionDiffusers

A monocular depth estimation model based on the latent diffusion model, supporting high-resolution image processing

Computer VisionDiffusersEnglish

DepthMaster is a refined single-step diffusion model that customizes generative features from diffusion models for discriminative depth estimation tasks.

Computer VisionDiffusersEnglish