PANews reported on October 16 that WorldLabs, a spatial intelligence company founded by Stanford University professor Fei-Fei Li, officially released a research preview version of its new generation real-time generation model RTFM (Real-Time Frame Model), which can generate videos and 3D scenes in real time during the interaction process, realizing a persistent virtual world. RTFM is designed around three core principles: efficiency, scalability, and persistence. The model runs at interactive frame rates on a single NVIDIA H100 GPU, generating scenes with complex effects like reflections, shadows, and glossiness from a single image without explicit 3D modeling. Its "spatial memory" mechanism maintains world persistence through frame pose modeling and context juggling, supporting long-term interactive exploration.PANews reported on October 16 that WorldLabs, a spatial intelligence company founded by Stanford University professor Fei-Fei Li, officially released a research preview version of its new generation real-time generation model RTFM (Real-Time Frame Model), which can generate videos and 3D scenes in real time during the interaction process, realizing a persistent virtual world. RTFM is designed around three core principles: efficiency, scalability, and persistence. The model runs at interactive frame rates on a single NVIDIA H100 GPU, generating scenes with complex effects like reflections, shadows, and glossiness from a single image without explicit 3D modeling. Its "spatial memory" mechanism maintains world persistence through frame pose modeling and context juggling, supporting long-term interactive exploration.
World Labs releases real-time generative world model (RTFM): a single H100 GPU can generate 3D worlds in real time
PANews reported on October 16 that WorldLabs, a spatial intelligence company founded by Stanford University professor Fei-Fei Li, officially released a research preview version of its new generation real-time generation model RTFM (Real-Time Frame Model), which can generate videos and 3D scenes in real time during the interaction process, realizing a persistent virtual world.
RTFM is designed around three core principles: efficiency, scalability, and persistence. The model runs at interactive frame rates on a single NVIDIA H100 GPU, generating scenes with complex effects like reflections, shadows, and glossiness from a single image without explicit 3D modeling. Its "spatial memory" mechanism maintains world persistence through frame pose modeling and context juggling, supporting long-term interactive exploration.
Disclaimer: The articles reposted on this site are sourced from public platforms and are provided for informational purposes only. They do not necessarily reflect the views of MEXC. All rights remain with the original authors. If you believe any content infringes on third-party rights, please contact service@support.mexc.com for removal. MEXC makes no guarantees regarding the accuracy, completeness, or timeliness of the content and is not responsible for any actions taken based on the information provided. The content does not constitute financial, legal, or other professional advice, nor should it be considered a recommendation or endorsement by MEXC.
You May Also Like
Australia Cleas Path for Stablecoins: Here’s What It Means for Crypto Distribution
TLDR: ASIC grants class relief for intermediaries handling licensed stablecoins, reducing the need for separate AFS licences. Exemption covers distribution, market, and clearing licences but still requires issuers to hold an AFS licence. Guidance updates to INFO 225 will add examples for stablecoins, meme coins, and wrapped tokens under financial laws. ASIC says it will [...] The post Australia Cleas Path for Stablecoins: Here’s What It Means for Crypto Distribution appeared first on Blockonomi.
Share
Blockonomi2025/09/18 23:56
The HackerNoon Newsletter: Hard Problems Are Easier, Once You Think Like This (12/10/2025)
How are you, hacker?
🪐 What’s happening in tech today, December 10, 2025?
The HackerNoon Newsletter brings the HackerNoon homepage straight to your
Share
Hackernoon2025/12/11 00:02
The Bistro Group, going loca(l)
THE RETURN of Krazy Garlik under The Bistro Group’s portfolio signifies Bistro’s respect for local culture and its motivation to do more in the local scene (as opposed to their forte, bringing in international franchises). It’s a comeback concept, having first opened in 2014, patterned after a Korean concept that worshipped the flavor (albeit a […]
Share
Bworldonline2025/12/11 00:07