SynCity: Training-Free Generation of 3D Worlds This paper presents SynCity, a novel approach to generating large-scale 3D worlds from textual descriptions. It combines the geometric precision of pre-trained 3D generative models with the artistic flexibility of 2D image
MULTIMODAL AI
-
Aligning Multimodal LLMs with Human Preferences: Survey
By
–
Aligning Multimodal LLM with Human Preference: A Survey This paper reviews alignment algorithms for Multimodal Large Language Models (MLLMs), which handle tasks involving text, visual, and auditory data, aiming to address issues like truthfulness, safety, and alignment with
-
Top 10 Foundation Model Papers: Humanoid Robots and Multimodal LLMs
By
–
This week was huge for foundation models, from generalist humanoid robots to multimodal LLMs that learn from human preferences and negative examples – here are the top 10 papers for the week – DAPO: An Open-Source LLM Reinforcement Learning System at Scale
– GR00T N1: An -
Grok adds DeepSearch and OCR capabilities for JFK archive analysis
By
–
JFK files prompt suggestion is now live on Grok. It triggers DeepSearch across archives dot gov and scans through a bunch of PDF files. A lovely demonstration of the OCR feature
-
Follow-up actions on historical messages with model comparison
By
–
You can now perform follow-up actions on all historical messages by right clicking or long pressing and selecting “Follow Up”. You can use this to compare models, ask follow-up questions, or enhance images through upscaling or animation. (2/4) pic.twitter.com/XNeFLYBCat
— Poe (@poe_platform) 22 mars 2025You can now perform follow-up actions on all historical messages by right clicking or long pressing and selecting “Follow Up”. You can use this to compare models, ask follow-up questions, or enhance images through upscaling or animation. (2/4)
-
Practical guide to using Grok for image processing
By
–
1. Just go to https://
x.com/i/grok and upload your image
2. Write a prompt Hit enter, done! -
Grok Releases New AI-Powered Image Editing Tool
By
–
Grok just released image editing. Upload a pic → type what you want changed → done. AI just made Photoshop look ancient. Original Grok image editing
-
Ameca: Advanced AI-Powered Humanoid Robot Technology
By
–
Meet #Ameca, a highly advanced robot whose brain is powered by artificial intelligence – technology that's either the smartest or most dangerous thing humanity has ever created!
— Amitav Bhattacharjee (@bamitav) 22 mars 2025
pic.twitter.com/AISESmlElD#AI #ArtificialInteligence #technology #Tech #robotgirl #Robotics #humanoid…Meet #Ameca, a highly advanced robot whose brain is powered by artificial intelligence – technology that's either the smartest or most dangerous thing humanity has ever created! #AI #ArtificialInteligence #technology #Tech #robotgirl #Robotics #humanoid
-
Future of UI: Generative Design Adapts to Users
By
–
The future of UI is generative. "Just in time" design that customizes to what you're doing and when/where you're doing it. And it'll keep adapting along with you – people aren't static either
-
NVIDIA’s NEO Humanoid Robot Demonstrates Advanced AI Interaction
By
–
At #NVIDIAGTC, I had the incredible chance to interact with #NEO, the world’s first humanoid robot powered by NVIDIA’s Isaac GR00T N1.
— Helen Yu (@YuHelenYu) 21 mars 2025
What blew my mind was how NEO could high five, shake my hands, mimic my behavior and interact with me with a sense of humor, thanks to its… pic.twitter.com/sSJ06j82SgAt #NVIDIAGTC, I had the incredible chance to interact with #NEO, the world’s first humanoid robot powered by NVIDIA’s Isaac GR00T N1. What blew my mind was how NEO could high five, shake my hands, mimic my behavior and interact with me with a sense of humor, thanks to its