Are World Models the Next Big Thing? | Merve Noyan

In this clip, Merve breaks down her predictions on ai for 2026 and explains why it matters in practice. Merve goes deep on world models, VLA systems, and on-device agentic models. Chapters: - 00:00 Your Predictions on AI for 2026 - 00:18 World Models - 00:56 World Labs - 02:13 Observations, State, and Action - 03:01 V-JEPA 2 - 03:28 Vision-Language-Action Models - 04:26 PaliGemma for Action - 05:53 OpenClaw - 06:32 On-Device Agents Topics covered: - World Models - Genie 3 - World Labs - Observations, State, and Action - V-JEPA 2 More from Merve Noyan: - Merve on X — https://x.com/mervenoyann - Vision Language Models (O'Reilly) — https://www.oreilly.com/library/view/vision-language-models/9798341624030/ Sources mentioned: - World Models — https://arxiv.org/abs/1803.10122 - Genie 3: A new frontier for world models — https://deepmind.google/discover/blog/genie-3-a-new-frontier-for-world-models/ - About World Labs — https://www.worldlabs.ai/about - V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning — https://arxiv.org/abs/2506.09985 - Physical AI with World Foundation Models | NVIDIA Cosmos — https://www.nvidia.com/en-us/ai/cosmos/ - RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control — https://arxiv.org/abs/2307.15818 - PaliGemma: A versatile 3B VLM for transfer — https://arxiv.org/abs/2407.07726 - OpenClaw documentation — https://docs.openclaw.ai/index