TMAS Scaling Test-Time Compute via Multi-Agent Synergy
MULTIMODAL AI
-
Multi-Agent Synergy for Scaling Test-Time Compute
By
–
TMAS Scaling Test-Time Compute via Multi-Agent Synergy
-
Scal3R: New AI Research for Neural 3D Scene Reconstruction from Video
By
–
What if AI could reconstruct kilometer-scale 3D scenes from video as effortlessly as humans perceive a room? Researchers from Zhejiang University and Horizon Robotics present Scal3R. They introduce a neural context memory that compresses long-range scene info, adapting on the
-
Google to enable source selection for NotebookLM artifacts
By
–
Google will enable source selection for every artifact on NotebookLM soon. It will be possible to restrict Audio & Overviews, Slides, Infographics, and the rest of your creations only to selected sources. Power user feature * Not available yet
-
Sharing Papers and Apps on Hugging Face
By
–
Paper:
https://huggingface.co/papers/2605.10922
…
App:
https://huggingface.co/spaces/TencentARC/Pixal3D
… -
Pixel-Aligned 3D Generation
By
–
Pixal3D
— AK (@_akhaliq) 12 mai 2026
Pixel-Aligned 3D Generation from Images pic.twitter.com/DADl4UQVIGPixal3D Pixel-Aligned 3D Generation from Images
-
Praise for model’s image abstraction capability
By
–
I'm really impressed with how the model is able to reduce the concept of the original image to something so minimal
-
PromptEcho: A New Zero-Annotation Reward Method for Text-to-Image Models
By
–
You could train text-to-image models without expensive human feedback! Alibaba Group and Zhejiang University researchers present PromptEcho—a reward method that uses a frozen vision-language model to measure image-prompt alignment directly, with zero annotations or extra
-
Google to replace Veo with new Gemini Omni video model
By
–
🚨 Veo isn't getting an upgrade. It's getting replaced.
— God of Prompt (@godofprompt) 12 mai 2026
A "Gemini Omni" announcement card just surfaced inside the Gemini app ahead of Google I/O 2026.
Google's own copy: "Meet our new video model."
"Edit video directly in chat" tells you where this is heading. Video… pic.twitter.com/eXxaMqqi2nVeo isn't getting an upgrade. It's getting replaced. A "Gemini Omni" announcement card just surfaced inside the Gemini app ahead of Google I/O 2026. Google's own copy: "Meet our new video model." "Edit video directly in chat" tells you where this is heading.
