-
Saarland University
- SaarbrĂĽcken, Germany
- m-parchami.github.io
- in/amin-parchami
- https://scholar.google.com/citations?hl=en&user=Z9sSK2EAAAAJ
Stars
Official Implementation of CAVE: Robust Conceptual Reasoning through Interpretable 3D Neural Object Volumes
Implementation of VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
Repository of the paper "AnyUp: Universal Feature Upsampling".
Automatically receive the latest publications from your favorite authors or on your favorite topics conveniently by e-mail using the arXiv API.
Simple code for generating a color-coded latex table from raw data
Official implementation of "Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks." CVPR 2025
The official implementation of our work How to Probe: Simple Yet Effective Techniques for Improved Post-hoc Explanations
Keeping my favorite snippets here so that I don't have to look them up again.
Nimfa: Nonnegative matrix factorization in Python
[CVPR2025] Number it: Temporal Grounding Videos like Flipping Manga
Official code for "Good Teachers Explain: Explanation-enhanced Knowledge Distillation". ECCV 2024
Repository of the 3DV paper "Gaussians-to-Life: Text-Driven Animation of 3D Gaussian Splatting Scenes".
[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
[NeurIPS 2024] Code for the paper: B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable.
[NeurIPS 2024] Official implementation of "NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory"
TensorDict is a pytorch dedicated tensor container.
E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data
Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
[ECCV 2024] Implementation of latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
Modified 3D Gaussian rasterizer for latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
Implementation of SimNP: Learning Self-Similarities Between Neural Points
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.