"…the ambition here feels somewhat limitless. What if an AI assistant could see your whole world, know what was what, and help you navigate it? That’s the big idea behind Copilot Vision." Couldn't have said it better myself, @adamclarkestes
.
MULTIMODAL AI
-
Copilot Vision: AI Assistant Seeing Your Whole World
By
–
-
PRoC3S Enables Robots to Complete Complex Multi-Step Household Tasks
By
–
In the future, PRoC3S could help robots complete more intricate chores in dynamic environments like houses, where they may be prompted to do a general chore composed of many steps (like "make me breakfast").
-
PRoC3S Successfully Demonstrates Drawing and Block Stacking Tasks
By
–
In simulations, PRoC3S successfully drew stars & letters 8/10 times each. It also could stack digital blocks in pyramids & lines, & place items w/accuracy, like fruits on a plate.
— MIT CSAIL (@MIT_CSAIL) 12 décembre 2024
Across each of these digital demos, the CSAIL method completed the requested task more… pic.twitter.com/lW9Q1HC0MpIn simulations, PRoC3S successfully drew stars & letters 8/10 times each. It also could stack digital blocks in pyramids & lines, & place items w/accuracy, like fruits on a plate. Across each of these digital demos, the CSAIL method completed the requested task more
-
Teaching Robots Safe Task Execution Using Vision and LLMs
By
–
Can we teach a robot its limits to do chores safely & correctly? 🧵
— MIT CSAIL (@MIT_CSAIL) 12 décembre 2024
To help robots execute open-ended, multi-step tasks, MIT CSAIL researchers used vision models to see what’s near the machine & model its constraints. An LLM sketches up a plan that’s checked in a simulator to… pic.twitter.com/u5HyfQwUicCan we teach a robot its limits to do chores safely & correctly? To help robots execute open-ended, multi-step tasks, MIT CSAIL researchers used vision models to see what’s near the machine & model its constraints. An LLM sketches up a plan that’s checked in a simulator to
-
Post-Training Data Boom: Computing Beyond Pre-Training Limits
By
–
Compute matters, but so does data, and we have reached a pre-training data wall. Get ready for the post-training data boom. Companies will race to have the best frontier data—multi-modal, agentic, complex reasoning, and more. Follow the data, find the winners. 7/8
-
IJCV Special Issue on Audio-Visual Generation Call for Papers
By
–
We are organizing an IJCV special issue on audio-visual generation, submission will be open soon. #IJCV
CfP: https://
avgen123.github.io -
Gemini 2.0 Launch: Real-Time Multimodal AI with Screen Sharing
By
–
New Gemini 2.0 is absolutely mindblowing! Try it for free: https://
aistudio.google.com/live You can share your screen with it (or webcam), play a game, and have real-time voice conversation with it. It can hear you and also see your screen. I just played Space Engineers 2 with -
Patchwork: New Multiplayer AI Worldbuilding Tool Launches
By
–
Today we're opening up a new experimental multiplayer worldbuilding tool called "Patchwork". It combines language models, image models, and a canvas-based interface to build out the foundations of stories. Check out the 🧵below for links and further documentation. Have fun! pic.twitter.com/IgoJrJ8bO9
— Midjourney (@midjourney) 11 décembre 2024Today we're opening up a new experimental multiplayer worldbuilding tool called "Patchwork". It combines language models, image models, and a canvas-based interface to build out the foundations of stories. Check out the below for links and further documentation. Have fun!
-
SambaLingo: Teaching LLMs New Languages at NeurIPS
By
–
Chat with us at @NeurIPSConf about our SambaLingo paper. #NeurIPS2024 It's all about teaching LLMs new languages & diving deeper into how we train our SambaLingo series of multilingual models. Paper Link https://
bit.ly/3YROYAl -
AI Face Clones: The Emerging Identity Crisis in Fintech
By
–
The Rise Of AI Face Clones Could Trigger A Fintech Identity Crisis
#payments #fintech #paymentsolutions @briansolis @Xbond49 @VitalikButerin @DataScienceCtrl @Benioff @johnnosta @IrmaRaste @Tiffani_Bova