Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction

The Best Agent Harness. Meet Sisyphus: The Batteries-Included Agent that codes like you.

AirLLM 70B inference with single 4GB GPU

Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

The contents of /home/oai/skills in ChatGPT's code interpreter environment

RLP: Reinforcement as a Pretraining Objective

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

OCR, layout analysis, reading order, table recognition in 90+ languages

This repository is established to store personal notes and annotated papers during daily research.

The official code for "MSFlow: Multi-Scale Normalizing Flows for Unsupervised Anomaly Detection"

SSRL: Self-Search Reinforcement Learning

The Open Source Feature Store for AI/ML

A collective list of free APIs

Weekly discussions on Spatial AI amongst members of Spatial AI KR

Official Code for Paper: Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation

Code for "Scaling Language-Free Visual Representation Learning" paper (Web-SSL).

Cameras as Relative Positional Encoding

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

Code release for "Generative Modeling of Weights: Generalization or Memorization?"

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.

Paper List of Inference/Test Time Scaling/Computing

[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers

[CVPR 2025 Highlight] Interpreting Object-level Foundation Models via Visual Precision Search

[NeurIPS 2025] Official code for JAFAR: Jack up Any Feature at Any Resolution

Official implementation of "Text-Aware Image Restoration with Diffusion Models"

About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025, Highlight)