From f455cdf2b2b34a3ab0d9ae8fd17eb1e689820367 Mon Sep 17 00:00:00 2001 From: Sarvesh Date: Thu, 4 Jun 2026 15:27:13 +0530 Subject: [PATCH] Update README.md with centered header, badges, and quick links --- README.md | 25 +++++++++++++++++++++---- 1 file changed, 21 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 56c0b34..69dcd22 100644 --- a/README.md +++ b/README.md @@ -1,13 +1,30 @@ -# Video2LoRA +
-Video2LoRA trains a hypernetwork that converts a video into LoRA weights for a -frozen vision-language model. The generated adapter lets the model answer later -text prompts without feeding the video tokens again. +# Video2LoRA: Parametric Video Internalization for Vision-Language Models + +Official PyTorch implementation of **Video2LoRA** + +[**Manan Suri**](https://manansuri.com/)  ·  [**Sarvesh Baskar**](https://orcid.org/0009-0006-3831-6811)  ·  [**Dinesh Manocha**](https://www.cs.umd.edu/people/dmanocha) + +*University of Maryland, College Park* + +[![project page](https://img.shields.io/badge/🌐_project-page-3b82f6?style=flat-square)](https://video2lora.github.io/) +[![arxiv paper](https://img.shields.io/badge/📄_arxiv_paper-2606.04351-b31b1b?style=flat-square)](https://arxiv.org/abs/2606.04351) +[![hf checkpoints](https://img.shields.io/badge/🤗_checkpoints-Video2LoRA-orange?style=flat-square)](https://huggingface.co/MananSuri27/Video2LoRA-SmolVLM-ckpts) +[![license](https://img.shields.io/badge/⚖️_license-MIT-gray?style=flat-square)](LICENSE) + +--- + +### [Install](#install)  •  [Checkpoints](#checkpoints)  •  [Inference](#inference)  •  [Data Format](#data-format)  •  [Training](#train)

Animated Video2LoRA method diagram

+
+ +Video2LoRA trains a hypernetwork that converts a video into LoRA weights for a frozen vision-language model. The generated adapter lets the model answer later text prompts without feeding the video tokens again. + ## Install Install `uv`.