open-arms-mini: cheap human like teleoperation device that supports human in the loop corrections

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

Towards Scalable Pre-training of Visual Tokenizers for Generation

The first pure DINO representation diffusion model for high-quality visual generation.

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Unofficial PyTorch implementation of Neural Assets from Google DeepMind

a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to generate actions

EdgeVLA: An open-source edge vision-language-action model for robotics.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Official Code for LightVLA (ICRA 2026)

Implementation of "SimVLA: A Simple VLA Baseline for Robotic Manipulation"

This is a pytorch implementation of k-means clustering algorithm

Fast and memory-efficient exact kmeans

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

Implementing a JEPA-style World Model using the Energy-Based-Transformer, an Attentive State Pooler and LeJEPA loss.

Code release for "UnSAMv2: Self-Supervised Learning Enables Segment Anything at Any Granularity"

[CVPR 2024 Highlight] Official GraCo: Granularity-Controllable Interactive Segmentation.

Pytorch implementations of "Learning Object-Centric Representation via Reverse Hierarchy Guidance"

[CVPR'26 Findings] Source code for "RADSeg Unleashing Parameter and Compute Efficient Zero-Shot Open-Vocabulary Segmentation Using Agglomerative Models"

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Official code of Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

Convert between robotics dataset formats (RLDS, LeRobot v2/v3, Zarr, HDF5, Rosbag). Inspect, visualize, and analyze datasets. Works with HuggingFace Hub. Built for OpenVLA, Octo, LeRobot, and Diffu…

Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".

[ICLR '26 Oral] Official repository of the paper "AnyUp: Universal Feature Upsampling".

Official repository for "AM-RADIO: Reduce All Domains Into One"

Smoothing Slot Attention Iterations and Recurrences, arXiv:2508.05417.

[NeurIPS 2024] Unsupervised Hierarchy-Agnostic Segmentation: Parsing Semantic Image Structure