Artificial Intelligence : Papers & Concepts
Episodes
Gradient-Based Planning
13 Dec 2025
Contributed by Lukas
How should an AI or robot decide what to do next? In this episode, we explore a new approach to planning that rethinks how world models are trained. T...
SAM3D: The Next Leap in 3D Understanding
10 Dec 2025
Contributed by Lukas
Forget flat photos—SAM3D is rewriting how machines understand the world. In this episode, we break down the groundbreaking new model that takes the ...
DINOv3 : A new Self-Supervised Learning (SSL) Vision Language Model (VLM)
29 Oct 2025
Contributed by Lukas
In this episode, we explore DINOv3, a new self-supervised learning (SSL) vision foundation model from Meta AI Research, emphasizing its ability to sca...
dots.ocr SOTA Document Parsing in a Compact VLM
28 Oct 2025
Contributed by Lukas
dots.ocr is a powerful, multilingual document parsing model from rednote-hilab that achieves state-of-the-art performance by unifying layout detect...
DeepSeek-OCR : A Revolutionary Idea
23 Oct 2025
Contributed by Lukas
In this episode, we dive deep into DeepSeek-OCR, a cutting-edge open-source Optical Character Recognition (OCR) / Text Recognition model that's redefi...
nanochat by Karpathy - How to build your own ChatGPT for $100
21 Oct 2025
Contributed by Lukas
"The best ChatGPT that $100 can buy." That's Andrej Karpathy's positioning for nanochat—a compact, end‑to‑end stack that goes from tokenizer tr...
SmolVLM: Small Yet Mighty Vision Language Model
01 Oct 2025
Contributed by Lukas
In this episode of Artificial Intelligence: Papers and Concepts, we explore SmolVLM, a family of compact yet powerful vision language models (VLMs) de...
Common Pitfalls in Computer Vision & AI Projects (and How to Avoid Them)
01 Oct 2025
Contributed by Lukas
In this episode, we dig deep into the unglamorous side of AI and computer vision projects — the mistakes, misfires, and blind spots that too often d...