AI agents running research on single-GPU nanochat training automatically

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

[ICCV 2025] Official pytorch implementation of "SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering"

A LaTex paper template for security and machine learning conferences

A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis (ICCV 2025, Oral)

[ICLR 2025] Official PyTorch implementation of "DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation"

Python interface for OSQP

Create a Gephi Citation Graph based on Text Analysis of PDFs from Zotero

WIP - Automated Question Answering for ArXiv Papers with Large Language Models (https://arxiv.taesiri.xyz/)

Tools for merging pretrained large language models.

Model Stock: All we need is just a few fine-tuned models

[ECCV 2022] Official Implementation for Unsupervised Selective Labeling for More Effective Semi-Supervised Learning

An open source implementation of CLIP.

Mode Connectivity and Fast Geometric Ensembles in PyTorch

Fine-tuning Vision Transformers on various classification datasets

Robust fine-tuning of zero-shot models

Learning Placeholders for Open-Set Recognition (CVPR'21 Oral)

Repo for the paper: "Increasing the Classification Margin with Uncertainty Driven Perturbations"

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Official implementation for Wavelet Feature Maps Compression for Image-to-Image CNNs, NeurIPS 2022.

Code Repository for Liquid Time-Constant Networks (LTCs)

Dataset Condensation (ICLR21 and ICML21)

Simple pytorch implementation of FGSM and I-FGSM

Code for "Personalized Fashion Recommendation with Visual Explanations based on Multi-model Attention Network"

Offical implemention of Robust Superpixel-Guided Attentional Adversarial Attack (CVPR2020)

[CVPR 2022] VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution