-
Imagine @ Ecole des Ponts ParisTech
- The Stack / Paris
- https://imagine.enpc.fr/~siglidii/
- @YSiglidis
Highlights
- Pro
Block or Report
Block or report ysig
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseStars
Language
Sort by: Recently starred
A WebGL viewer for UMAP or TSNE-clustered images
A library for generative social simulation
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.
Author's implementation of "Visual Element Discovery as Discriminative Mode Seeking," Doersch, Gupta & Efros, NIPS 2013
Code for "Don’t drop your samples! Coherence-aware training benefits Conditional diffusion" CVPR 2024 Highlight
Experimenting Weaviate vector database with OpenAI vectorizer module and generative search
Unofficial implementation of: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics
A scikit-learn-compatible module to estimate prediction intervals and control risks based on conformal predictions.
The Places365-CNNs for Scene Classification
Rhythm GAN/CAN player for Ableton Live / Max for Live
[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering
A playbook for systematically maximizing the performance of deep learning models.
The hub for EleutherAI's work on interpretability and learning dynamics
A library for mechanistic interpretability of GPT-style language models
Zero-shot Image-to-Image Translation [SIGGRAPH 2023]
Automatically create Faiss knn indices with the most optimal similarity search parameters.
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Code for the paper "ViperGPT: Visual Inference via Python Execution for Reasoning"
Code for "The One Where They Reconstructed 3D Humans and Environments in TV shows" appearing in ECCV 2022.
Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]
Official Implementation for the "Conffusion: Confidence Intervals for Diffusion Models" paper.
Image/text geolocation with tensorflow and the MvMF
Pix2Seq codebase: multi-tasks with generative modeling (autoregressive and diffusion)
Locating and editing factual associations in GPT (NeurIPS 2022)
Reimplementation of Style Transfer by Relaxed Optimal Transport and Self-Similarity