[ICCV 2025] ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models

Ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.

Official Implementation of NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering

Fork of CARLA-Garage, which will serve as a minimum viable repository for the autonomous driving group at CVC.

BEVFormer, UniAD, VAD in Closed-Loop CARLA Evaluation with World Model RL Expert Think2Drive

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

🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

Code for the paper Don't Pay Attention

How to swap/switch CUDA versions on Windows

Extension of our work on Kinetic manipulation of the latent space

[NeurIPS 2024 Datasets and Benchmarks Track] Closed-Loop E2E-AD Benchmark Enhanced by World Model RL Expert

[ICCV'23] Hidden Biases of End-to-End Driving Models & A starter kit for the CARLA leaderboard 2.0.

Making it easy and transparent how to collect data in the CARLA simulator

VaViM and VaVAM: Autonomous Driving through Video Generative Modeling (official repository).

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

An object-oriented Python approach towards providing a giant wrapper for Tikz code, with the goal of streamlining the process of creating complex figures for TeX documents.

A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.

React + Next.js template for research websites (for PhD students, researchers, etc)

Official Pytorch Implementation for "SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time" (WACV 2025) https://spotdiffusion.github.io/

Simple hugo academic theme for scientist personal page

The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"

Theia: Distilling Diverse Vision Foundation Models for Robot Learning

Visualising Losses in Deep Neural Networks

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

A complete computer science study plan to become a software engineer.