Desktop and web interface for OpenCode AI agent

OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3

Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"

Awesome Remote Sensing Vision-Language Datasets

Python library for the Tessera embeddings

iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

PyTorch code and models for the DINOv2 self-supervised learning method.

Pytorch toolbox for large-scale hyperspectral image classification using WHU-OHS dataset

[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

An implementation of (Induced) Set Attention Block, from the Set Transformers paper

Li, X., Li, C., Ghamisi, P., Hong, D., Benediktsson, J., Chanussot, J. (2026). FlexiMo: A Flexible Remote Sensing Foundation Model. IEEE Transactions on Geoscience and Remote Sensing, 2026, DOI: 10…

Li, X., Li, C., Vivone, G., Hong, D. (2026). SeaMo: A Season-Aware Multimodal Foundation Model for Remote Sensing, 125: 103334.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Official repo for [CVPR 2026] "SARMAE: Masked Autoencoder for SAR Representation Learning"

EarthVL: A Progressive Earth Vision-Language Understanding and Generation Framework

This free RAM cleaner uses native Windows features to optimize memory areas. It's a compact, portable, and smart application.

Research Code for Multimodal-Cognition Team in Ant Group

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

EuroSAT: Land Use and Land Cover Classification with Sentinel-2

LoMaR (Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction)

[AAAI 2026] Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter

Tailscale Backed Chat Server

Official implementation of SCTNet (AAAI2024)

AAAI26 | MaRS: A Multi-Modality Very-High-Resolution Remote Sensing Foundation Model with Cross-Granularity Meta-Modality Learning