1 18 113

Jonathan Korstad PRO

jkorstad

AI & ML interests

Deep Reinforcement Learning, Generative 3D, Accessibility, Multimodal Models, Agents, Computer Vision. Staying curious.

Recent Activity

upvoted a paper about 7 hours ago

MatAnyone: Stable Video Matting with Consistent Memory Propagation

upvoted an article 3 days ago

Open-R1: a fully open reproduction of DeepSeek-R1

reacted to m-ric's post with 🔥 3 days ago

Now you can launch a code agent directly from your terminal! ✨ 𝚜𝚖𝚘𝚕𝚊𝚐𝚎𝚗𝚝 "𝚈𝚘𝚞𝚛 𝚝𝚊𝚜𝚔" directly launches a CodeAgent ▶️ This also works with web agents (replace 𝚜𝚖𝚘𝚕𝚊𝚐𝚎𝚗𝚝 with 𝚠𝚎𝚋𝚊𝚐𝚎𝚗𝚝) thanks to @merve ! 💾 Another treat from smolagents release 1.7.0: Now agents have a memory mechanism, enabling many possibilities like replaying the last run with 𝚊𝚐𝚎𝚗𝚝.𝚛𝚎𝚙𝚕𝚊𝚢(), thank you @clefourrier ! Check the release notes here 👉 https://github.com/huggingface/smolagents/releases/tag/v1.7.0

View all activity

Organizations

jkorstad's activity

upvoted a paper about 7 hours ago

MatAnyone: Stable Video Matting with Consistent Memory Propagation

Paper • 2501.14677 • Published 10 days ago • 7

upvoted an article 3 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

7 days ago

• 590

upvoted an article 10 days ago

Article

We now support VLMs in smolagents!

11 days ago

• 70

upvoted an article 18 days ago

Article

Run ComfyUI workflows for free on Spaces

Jan 14, 2024

• 49

upvoted a paper about 1 month ago

Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Paper • 2412.15322 • Published Dec 19, 2024 • 18

upvoted a paper 3 months ago

Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models

Paper • 2411.07126 • Published Nov 11, 2024 • 28

upvoted a collection 3 months ago

OpenCoder

Collection

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 8 items • Updated Nov 23, 2024 • 79

upvoted 2 papers 3 months ago

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

Paper • 2411.02327 • Published Nov 4, 2024 • 11

GenXD: Generating Any 3D and 4D Scenes

Paper • 2411.02319 • Published Nov 4, 2024 • 20

upvoted a collection 3 months ago

MIT Talk 31/10 Papers

Collection

14 items • Updated Oct 28, 2024 • 31

upvoted 2 papers 4 months ago

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Paper • 2410.10306 • Published Oct 14, 2024 • 54

PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation

Paper • 2409.18964 • Published Sep 27, 2024 • 26

upvoted 3 papers 5 months ago

upvoted an article 6 months ago

Article

License to Call: Introducing Transformers Agents 2.0

May 13, 2024

• 127