Pepijn Kooijmans's picture

Building on HF

Pepijn Kooijmans PRO

pepijn223

·

AI & ML interests

Robotics and AI

Organizations

upvoted an article about 18 hours ago

Article

Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

+5

Sep 11

•

166

upvoted an article 5 days ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

5 days ago

•

223

upvoted an article 11 days ago

Article

Continuous batching from first principles

+1

11 days ago

•

240

upvoted a collection 18 days ago

Qwen3-VL

37 items • Updated Nov 1 • 485

upvoted an article 18 days ago

Article

🚀 Build a Qwen 2.5 VL API endpoint with Hugging Face spaces and Docker!

Jan 29

•

21

upvoted 4 articles about 1 month ago

Article

Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac

Oct 29

•

27

Article

NVIDIA Isaac GR00T in LeRobot

Oct 28

•

22

Article

LeRobot v0.4.0: Supercharging OSS Robot Learning

+7

Oct 24

•

46

Article

Streaming datasets: 100x More Efficient

+3

Oct 27

•

70

upvoted 2 articles about 2 months ago

Article

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

Sep 30

•

42

Article

LeRobot.js

Jul 14

•

15

upvoted 2 collections 2 months ago

Open X-Embodiment

Datasets from Open X-Embodiment (OXE) in LeRobot dataset format • 57 items • Updated Oct 2 • 7

RDT 2

RDT 2, the sequel to RDT-1B, is the first foundation model that achieves zero-shot deployment on unseen embodiments for simple open-vocabulary tasks. • 4 items • Updated Sep 26 • 16

upvoted 2 articles 3 months ago

Article

`LeRobotDataset:v3.0`: Bringing large-scale datasets to `lerobot`

+9

Sep 16

•

47

Article

Welcome PaliGemma 2 – New vision language models by Google

+2

Dec 5, 2024

•

162

upvoted a paper 3 months ago

π_0: A Vision-Language-Action Flow Model for General Robot Control

Paper • 2410.24164 • Published Oct 31, 2024 • 30

upvoted a collection 3 months ago

Libero Benchmark Dataset

18 items • Updated Aug 28 • 7

upvoted 2 papers 3 months ago

π_{0.5}: a Vision-Language-Action Model with Open-World Generalization

Paper • 2504.16054 • Published Apr 22 • 3

EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control

Paper • 2508.21112 • Published Aug 28 • 77

upvoted a collection 3 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 398