Octopus-v2: 2B LLMs that can run on mobile devices
Octopus-V2-2B is developed by Nexa AI at Stanford University and…
AI projects
Claude publishes function calling tool: Tool use
Allow models to interact with external systems and data Using…
POM trained Animatediff three MotionLora
WAS26: This model was selected for training from art works…
Meta announces URHand
The model is a high-fidelity universal prior of Reliable Hands…
Alibaba launches Qwen 1.5 – 32B model
Qwen 1.5 – 32B is the latest member of the…
An open source, low-cost robot arm that costs only $250
Can be used to do machine learning yourself The robotic…
Hugging and Intel release plan to improve spatial consistency of Wensheng graph models
The model’s ability to understand spatial relationships in prompt words…
Unbounded 3D urban generation
CVPR2024 proposes CityDreamer, a combinatorial generative model for synthesizing unbounded…
Interesting project: EMAGE
You can generate facial and body movements that are synchronized…
Automatic coloring technology for animation: You can automatically color line drawings in animation
The S-lab team at Nanyang Technological University has developed a…
MuseV: A complete solution for virtual human video
Based on SD, it supports cultural videos, graphic videos, and…
Living Images: Just enter the URL and automatically optimize the pictures on your website to make them more attractive
Enter your URL and it will automatically analyze and improve…