Stars
Reliable, minimal and scalable library for pretraining foundation and world models
Official code of Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
Official implementation of DIP: Unsupervised Dense In-Context Post-training of Visual Representations
[CVPR2025] Don’t Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving
[ICCV 2025] OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
FLOSS: Plug-in Training-free and label-free text template selection that boosts OVSS methods (ICCV 2025)
1 million FPS multi-agent driving simulator
Python scripts to help ACs with OpenReview
(CVPR 2025 highlight✨) Official repository of paper "LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models"
Official Implementation of "Pix2Cap-COCO: Advancing Visual Comprehension via Pixel-Level Captioning"
A 3DGS framework for omni urban scene reconstruction and simulation.
A generative world for general-purpose robotics & embodied AI learning.
Official implementation of the paper "HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving"
List of startups doing AI & ML
[CVPR 2023] BEVGuide: BEV-Guided Multi-Modality Fusion for Driving Perception
[ECCV Workshop W-CODA 2024] Official code for ReGentS
👋 Puncc is a python library for predictive uncertainty quantification using conformal prediction.
An extremely simple method for validation-free efficient adaptation of CLIP-like VLMs that is robust to the learning rate.
This is a repository that implements the Dense NN Retrieval Evaluation used for evaluating the In-Context Learning Capabilities of Vision Encoders.