With Reve topping image generation leaderboards and Gemini’s native image generation and editing, no one really talks about Dall-e anymore. Are we getting true native AI image generation and editing in ChatGPT today? OpenAI never lets Google have the spotlight for too long…
MULTIMODAL AI
-
OpenAI announces native image output for GPT-4o
By
–
BREAKING : OpenAI is about to announce native image output for GPT-4o later today!
-
Google unveils new model and Agents tools for Gemini
By
–
BREAKING : Google is set to reveal a new model for Gemini this week! In addition to that, Gemini will get a new toolbox for "Agents", aka "agentic use cases" for Gemini, like Canvas or Deep Research. Soon, we may get something new added there.
-
InfiniteYou: Flexible Photo Recrafting While Preserving Identity
By
–
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity Jiang et al.: https://
arxiv.org/abs/2503.16418 #artificialIntelligence #DeepLearning #MachineLearning -
Google rolls out Project Astra for Gemini on Android
By
–
Google started rolling out Project Astra for Gemini to more Android users. This feature enables vision capabilities on Gemini Live. The rollout is expected to be slow and gradual as the current adoption rate is still very low.
— 🚨 AI News | TestingCatalog (@testingcatalog) 25 mars 2025
Thanks to t@__andreshernandez for the recording 🔥 pic.twitter.com/3xJoH9gBufGoogle started rolling out Project Astra for Gemini to more Android users. This feature enables vision capabilities on Gemini Live. The rollout is expected to be slow and gradual as the current adoption rate is still very low. Thanks to t@__andreshernandez for the recording
-
Video-T1: Test-Time Scaling for Video Generation
By
–
-T1: Test-Time Scaling for Generation
Paper: https://
arxiv.org/pdf/2503.18942
Page: https://
liuff19.github.io/Video-T1/
Code: -
Test-Time Compute Improves Video Quality Significantly
By
–
And what did they find? Increasing test-time compute consistently leads to significant improvements in video quality.
-
Video Generation Models Leverage Inference Compute for Quality
By
–
If a video generation model is allowed to use a non-trivial amount of inference-time compute, how much can it improve generation quality for challenging text prompts?
This is exactly what a new paper from Tsinghua University explores. -
Google Astra: Gemini Live Gets Real-Time Visual Understanding
By
–
Google's Project Astra features started rolling out to Gemini Live
— Rowan Cheung (@rowancheung) 25 mars 2025
The update will allow Gemini to “see” your screen or through your smartphone camera and answer questions real-timepic.twitter.com/KzJ26AP0dKGoogle's Project Astra features started rolling out to Gemini Live The update will allow Gemini to “see” your screen or through your smartphone camera and answer questions real-time
-
Alibaba Qwen2.5-VL-32B-Instruct: Advanced Vision-Language Model
By
–
The Qwen team of Alibaba open-sourced Qwen2.5-VL-32B-Instruct, a new vision-language model —Features enhanced mathematical reasoning and visual capabilities
—Beats Qwen2-VL-72B, Mistral Small 3.1-24B, and GPT-4o-0513
—Apache 2.0 licensed