Starred repositories
Token-efficient pull/edit/push workflow for AI agents editing Google Workspace files (Sheets, Docs, Slides, Forms)
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
World Modeling by Forecasting Vision Foundation Model Features
Code, data and weights for the paper **What drives success in physical planning with Joint-Embedding Predictive World Models?**
An additive cyclic noise shader that makes a cool effect.
🌱 a fast, batteries-included static-site generator that transforms Markdown content into fully functional websites
KV Cache Steering for Inducing Reasoning in Small Language Models
📊 Check your GitHub rating, view results and enhance your profile quality.
(ICCV 2025) "Principal Components" Enable A New Language of Images
A beautiful, simple, clean, and responsive Jekyll theme for academics
"Near, far: Patch-ordering enhances vision foundation models' scene understanding": A New SSL Post-Training Approach for Improving DINOv2’s spatial representations in 19 GPU hours with Patch Neighb…
This is a repository that implements the Dense NN Retrieval Evaluation used for evaluating the In-Context Learning Capabilities of Vision Encoders.
📝🌈 A VS Code extension for improving the display of markdown directly in the editor
This repository includes the official implementation our paper "Scaling White-Box Transformers for Vision"
Code for CRATE (Coding RAte reduction TransformEr).
[ICML 2025] Official Implementation for SimDINO/SimDINOv2
Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations ICCV23
torchvision-based transforms that provide access to parameterization
Plugin for zotero to retrieve reference data from Semantic Scholar API and add them to your library
[ICML-2025] We introduce Lie group Relative position Encodings (LieRE) that goes beyond RoPE in supporting n-dimensional inputs.
Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
Training, optimization and deployment of Object Detection model with dinov2 backbone for efficient inference on NVIDIA Jetson
Personal knowledge base and AI/ML research notes exported from Obsidian
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡