Towards Robust Evaluation for Geospatial Foundation Models

[NeurIPS'25 Spotlight] Boosting Generative Image Modeling via Joint Image-Feature Synthesis

Detail-Oriented Pixelization based on Contrast-Aware Outline Expansion.

[ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.

Collect some World Models for Autonomous Driving (and Robotic) papers.

Official repository for our work on micro-budget training of large-scale diffusion models.

[CVPR 2025] Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

[CVPR 2025 Oral] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

[NeurIPS 2025] Official Implementation of DINO-Foresight: Looking into the Future with DINO

Official PyTorch implementation of the WACV 2025 Oral paper "Composed Image Retrieval for Training-FREE DOMain Conversion".

Detail-Oriented CLIP for Fine-Grained Tasks (ICLR SSI-FM 2025)

Code for Neural Plasticity-Inspired Foundation Model for Observing the Earth Crossing Modalities

Official PyTorch implementation and benchmark dataset for IGARSS 2024 ORAL paper: "Composed Image Retrieval for Remote Sensing"

Sensor Independent Cloud and Shadow Masking with Ambiguous Labels and Multimodal Inputs

The Clay Foundation Model - An open source AI model and interface for Earth

Official Pytorch Implementation of SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024)

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

Official Release of NeurIPS 2023 Spotlight paper "Object-Centric Slot Diffusion"

Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

[Survey] Masked Modeling for Self-supervised Representation Learning on Vision and Beyond (https://arxiv.org/abs/2401.00897)

Official repository of CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders (NeurIPS '23)

This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes dataset. This code is implemented in Pytorch.

Official code for Slot-Transformer for Videos (STEVE)

This repo contains the official implementation of ICCV 2023 paper "Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?"

[Not Actively Maintained] Whitebox is an open source E2E ML monitoring platform with edge capabilities that plays nicely with kubernetes