The limitations of traditional labeling methods in video analysis have long stifled AI’s potential. A team of researchers aims to address this with Video-STaR, which enables models to self-train on video content.
MULTIMODAL AI
-
Building Production-Ready AI Voice Agents with LiveKit
By
–
Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with @livekit and @realavatarai, and taught by @dsa (Co-founder & CEO of LiveKit), @shayneparlo (Developer Advocate, LiveKit), and @nedteneva (Head of AI at… pic.twitter.com/al8xAojqvW
— Andrew Ng (@AndrewYNg) 7 mai 2025Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with @livekit and @realavatarai
, and taught by @dsa (Co-founder & CEO of LiveKit), @shayneparlo (Developer Advocate, LiveKit), and @nedteneva (Head of AI at -
Gemini 2.0 Flash Image Generation Capabilities Upgraded
By
–
BREAKING : Gemini 2.0 Flash native image generation got upgraded! It is better at visual quality, text rendering and comes with lower refusal rates.
-
Meta Launches PLM: Open Vision-Language Model for Computer Vision
By
–
Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks.
— AI at Meta (@AIatMeta) 7 mai 2025
Learn more about how PLM can help the open source community build more capable computer vision systems.
Read the research paper, and download the… pic.twitter.com/lcYFZ8EnkrIntroducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the
-
Gemini Native Image Generation Rolls Out to App
By
–
Native image generation started rolling out to the Gemini app started rolling out last week: https://
blog.google/products/gemin
i/image-editing/
… I don't think it is behind a model drop down, I believe you just ask and the model uses the model behind the scenes. -
Imagen and Gemini: Native Image Generation and World Knowledge
By
–
Yes, Imagen is an image generation model. Gemini with native image generation / editing capabilities benefits from world knowledge.
-
Google Launches Gemini 2.0 Flash Image Generation
By
–
Read more about todays launch: https://
developers.googleblog.com/en/generate-im
ages-gemini-2-0-flash-preview/
… big congrats to @19kaushiks @m__dehghani @kat_kampf and the rest of the native Gemini mm gen team! -
Gemini 2.0 Image Generation Model Updated with Better Quality
By
–
Today we are rolling out an updated Gemini 2.0 Image Generation model with : – Better visual quality – More accurate text rendering
– Lower block rates
– Higher rate limits
– $0.039 per image generated So excited to get this into the hands of devs : ) -
AI Demonstrates Creative Capabilities Challenging Previous Assumptions
By
–
And they said AI can’t be creative