10. CellVerse Introduces a benchmark to evaluate LLMs on single-cell biology tasks by converting multi-omics data into natural language.
MULTIMODAL AI
-
Kling v1.6 Now Supports Scene Elements in Video Generation
By
–
Kling v1.6 models on Replicate now support scene elements (reference_images).
— Replicate (@replicate) 18 mai 2025
Add up to 4 elements, like brands, characters, products or styles, to a video.https://t.co/2PL2Njue3d
Here's a generation that used two elements: a character and a Replicate hat. pic.twitter.com/Q8bUYk8KQqKling v1.6 models on Replicate now support scene elements (reference_images). Add up to 4 elements, like brands, characters, products or styles, to a video. https://
replicate.com/kwaivgi Here's a generation that used two elements: a character and a Replicate hat. -
LightLab: Diffusion Model Controls Light Sources in Images
By
–
LightLab: Controlling Light Sources in Images with Diffusion Models LightLab presents a diffusion-based method for precise, parametric control over light sources in a single image, enabling users to edit light intensity and color with photorealistic results. The approach
-
Maya: Open-Source Multilingual Vision Language Model
By
–
Behind Maya: Building a Multilingual Vision Language Model This paper introduces Maya, an open-source multilingual Vision-Language Model (VLM) designed to enhance performance on vision-language tasks across eight diverse languages. Maya addresses the underperformance of existing
-
AI Motion Transfer: From Photos to Video, Animals, and 3D
By
–
Vous filmez un squat. Vous donnez une photo.
— VISION IA (@vision_ia) 17 mai 2025
L’IA vous génère une vidéo où la photo… fait le squat.
C’est Flexi-ACT.
Transfert de mouvement cross-média : humain → image, image → animal, animal → 3D.
Un pas de plus vers le deep motion cloning total.
Jusqu’où va-t-on… pic.twitter.com/6HN2lpYg8pVous filmez un squat. Vous donnez une photo. L’IA vous génère une vidéo où la photo… fait le squat. C’est Flexi-ACT. Transfert de mouvement cross-média : humain → image, image → animal, animal → 3D. Un pas de plus vers le deep motion cloning total.
Jusqu’où va-t-on -
BAIR Researchers Win ACM SIGGRAPH Award for Neural Rendering
By
–
Congratulations to BAIR alumni @BenMildenhall and @_pratul_ who have been awarded ACM SIGGRAPH's @siggraph Significant New Researcher awards "For outstanding contributions to neural rendering and novel view synthesis."
-
GPT-4o: A Year of Unprecedented LLM Performance and Innovation
By
–
Difficile à croire, mais GPT-4o est sorti il y a juste un an. C’est sûrement le bond de performance le plus marquant jamais vu dans les LLM. Et pourtant… on a l’impression que ça fait deux trois ans, tant le rythme d’avancement a été irréel. Le saut entre GPT-4o et le modèle
-
Copilot Think Deeper and Read Aloud Feature Mashup
By
–
Underrated feature mashup in @Copilot: use Think Deeper for a detailed answer (the hockey playoffs are my latest rabbit hole) then long press + "Read Aloud". Perfect for multitasking, when making a cup of coffee in the morning, or just giving your eyes a break from blue light pic.twitter.com/MhKwfNakXd
— Mustafa Suleyman (@mustafasuleyman) 16 mai 2025Underrated feature mashup in @Copilot
: use Think Deeper for a detailed answer (the hockey playoffs are my latest rabbit hole) then long press + "Read Aloud". Perfect for multitasking, when making a cup of coffee in the morning, or just giving your eyes a break from blue light -
Big Tech Companies Developing Digital Nose Technology
By
–
ive heard something very interesting through the AI grapevine; apparently, lurking deep in the shadows of the big tech companies, there lies a group of smart and well-funded AI researchers building a Digital Nose these scientists, so far, have only succeeded in digitizing and
-
Runway Gen-4 Image API Now Available for Developers
By
–
Gen-4 Image is now available on the Runway API. To learn more and get started, visit https://t.co/rXkYz9sNCR pic.twitter.com/nb3vElz0vk
— Runway (@runwayml) 16 mai 2025Gen-4 Image is now available on the Runway API. To learn more and get started, visit http://
docs.dev.runwayml.com