This upgrade marks progress toward 4D asset generation for professional production workflows, from generating sprite sheets for in-game characters, to supporting assets for film and virtual worlds. Multi-view generation, however, remains complex due to the inherent ambiguity of
MULTIMODAL AI
-
SV4D 2.0 Achieves State-of-the-Art 4D Generation Results
By
–
Our analysis shows that SV4D 2.0 achieves state-of-the-art results in 4D generation, ranking first across all major benchmarks. (2/4)
-
Stable Video 4D 2.0 Upgrades 4D Output Quality from Single Videos
By
–
We’ve upgraded Stable Video Diffusion 4D to Stable Video 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video.
— Stability AI (@StabilityAI) 20 mai 2025
While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object… pic.twitter.com/8q85kFiu4ZWe’ve upgraded Stable Diffusion 4D to Stable 4D 2.0 (SV4D 2.0), improving the quality of 4D outputs generated from a single object-centric video. While 3D provides a static view of an object’s shape and size; 4D extends this by including time, showing how the object
-
Tencent Hunyuan Game: Try AI-Powered Gaming Experience
By
–
In case if you wanna give it a try: https://
hunyuan.tencent.com/game/home -
Azure AI Foundry Updates: New Models and Advanced Workflow Features
By
–
4. Azure AI Foundry updated with new models including Grok 3, Flux Pro 1.1, and Sora (coming soon)
— Rowan Cheung (@rowancheung) 20 mai 2025
Also includes new model router, multi-agent workflows, observability features, and Foundry local for creating localized AI apps on Windows and Macpic.twitter.com/93V1RyScld4. Azure AI Foundry updated with new models including Grok 3, Flux Pro 1.1, and Sora (coming soon) Also includes new model router, multi-agent workflows, observability features, and Foundry local for creating localized AI apps on Windows and Mac
-
Which TTS speaks Chinese best? Audio Turing Test
By
–
Which TTS speaks Chinese best? Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese Paper: https://
arxiv.org/pdf/2505.11200 -
Visual Affordance Learning Advances Robotics Research
By
–
Very excited by our work on visual affordance learning in the wild for robotics! 🤩 https://t.co/SjC94HS7Uf
— Fei-Fei Li (@drfeifei) 19 mai 2025Very excited by our work on visual affordance learning in the wild for robotics!
-
Axelera AI Vision: Build Next-Generation AI-Powered Applications
By
–
We’ve seen builds that speak, blink, switch, log, open, notify and even warn.
Yours could be next.
If you had all the gear you wanted, what would you build with the power of Axelera's vision AI?
Make it happen: https://
eu1.hubs.ly/H0kblwn0
#AIThatReacts -
DeepAgent Creates Complete Presentations with Graphs and Photos
By
–
One-shot an entire presentation with DeepAgent – complete with graphs and photos.
