Today we release ScreenSuite, the most comprehensive evaluation suite for GUI agents (aka Computer Use agents). We packed 13 benchmarks, and 3 different environments, to evaluate the full range of agentic capabilities for vision models. And it turns out, @Alibaba_Qwen models are
MULTIMODAL AI
-
Computer Vision Papers Feature Superior Visual Quality
By
–
computer vision papers have the best figures. this is a fact of life.
-
ElevenLabs Releases Eleven v3 Alpha with Emotional Expression Control
By
–
ICYMI: ElevenLabs released Eleven v3 (alpha) – a new TTS model with support for emotional expressions. There, you can add more voice controls to the transcript template, like:
— 🚨 AI News | TestingCatalog (@testingcatalog) 6 juin 2025
– Emotions [sad] [happy]
– Delivery direction [whispers] [shouts]
– Reactions [laughs][sighs] https://t.co/onm51mqZHR pic.twitter.com/McQgs7S2ODICYMI: ElevenLabs released Eleven v3 (alpha) – a new TTS model with support for emotional expressions. There, you can add more voice controls to the transcript template, like: – Emotions [sad] [happy]
– Delivery direction [whispers] [shouts]
– Reactions [laughs][sighs] -
Practical AI Tools: Podcasting, Voice Recording, and Transcription
By
–
You need to try things like: – recording a podcast
– speaking into a mic
– transcript of what's being said -
GigaScale 3D Converts Single Photo Into Photorealistic 3D Model
By
–
Un seul cliché. Un modèle 3D photoréaliste.
— VISION IA (@vision_ia) 6 juin 2025
GigaScale 3D est en train de pulvériser toutes les limites connues en génération 3D à partir d’image.
Niveau de détail, textures, proportions : on frôle l’irréel.
Open source, en ligne, gratuit.
Le futur du design 3D commence ici.… https://t.co/XqXrJVOxew pic.twitter.com/iqzzqPqf7iUn seul cliché. Un modèle 3D photoréaliste. GigaScale 3D est en train de pulvériser toutes les limites connues en génération 3D à partir d’image. Niveau de détail, textures, proportions : on frôle l’irréel.
Open source, en ligne, gratuit. Le futur du design 3D commence ici. -
Podcast Recording and AI Transcription Techniques
By
–
You need to try things like: – recording a podcast
– speaking into a mic
– transcript of what's being said -
Veo 3 AI-generated videos becoming harder to detect authentically
By
–
I think this genre of Veo 3 videos is the hardest to spot as AI. Short realistic clips, gestures that go with the audio, not much movement to spot incoherencies in.
— fofr (@fofrAI) 6 juin 2025
This also highlights how video with native audio is so much better than a video with lipsync added later. pic.twitter.com/WV1DcFyuvuI think this genre of Veo 3 videos is the hardest to spot as AI. Short realistic clips, gestures that go with the audio, not much movement to spot incoherencies in. This also highlights how video with native audio is so much better than a video with lipsync added later.
-
AI Creates iOS Apps from Screenshots Instantly
By
–
Try specifically to ask to recreate an iOS app from a screenshot, you gonna have your mind blown!
-
Imagen 4 Cinematic Portrait Generation Prompt Showcase
By
–
Prompt for this image made with Imagen 4: > Create a cinematic wide angle, photorealistic portrait shot capturing the nostalgic warmth of a late 90s indie film. The focus is a young woman with a blonde updo haircut, she is off-center. She wears a designer dress. She holds up a
-
Google’s Veo 3 Video AI Now Available Through Replicate
By
–
Good morning Europehttps://t.co/7p85ylT4dq
— fofr (@fofrAI) 6 juin 2025
> A woman sits in a cafe in Paris with a croissant and coffee, she says: Good morning Europe, you can use Veo 3 through Replicate now. Also, the woman is an animated woman, but the scene is live action. pic.twitter.com/I7RznhAEC1Good morning Europe https://
replicate.com/google/veo-3 > A woman sits in a cafe in Paris with a croissant and coffee, she says: Good morning Europe, you can use Veo 3 through Replicate now. Also, the woman is an animated woman, but the scene is live action.