Things stood out to me in order: > The voice kind of sounded like @adcock_brett at first
> This demo really shows how "humanoid" the robot is from the smoothness and slight stutters
> The visual + language reasoning is faster than I expected but still too slow for a full
MULTIMODAL AI
-
Humanoid Robot Demo Shows Impressive Visual Language Reasoning
By
–
-
ChatGPT Gets a Body: OpenAI Figure Partnership Robotics
By
–
Two weeks ago, OpenAI and Figure announced a partnership.
— Rowan Cheung (@rowancheung) 13 mars 2024
Today, ChatGPT has a body.
This is 100% end-to-end with no teleop or speedup. Wow. https://t.co/iSPmun6obgTwo weeks ago, OpenAI and Figure announced a partnership. Today, ChatGPT has a body. This is 100% end-to-end with no teleop or speedup. Wow.
-
NaturalSpeech 3: Zero-Shot Speech Synthesis with Diffusion
By
–
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models Ju et al.: https://
arxiv.org/abs/2403.03100 #ArtificialIntelligence #DeepLearning #MachineLearning -
Midjourney Releases Character Consistency Feature Using Image References
By
–
Midjourney AI just released the Character Consistency feature. Here's how it works:
– Type –cref [URL] after prompt with a URL to an image of a character.
– You can use –cw to modify reference 'strength' from 100 to 0 – strength 100 (–cw 100) is default and uses the face, -
Refik Anadol’s AI Living Archive Explores Ecosystem Synergy
By
–
#GTC24 attendees will have the opportunity to explore @refikanadol's LLM "A Living Archive" exhibit: An immersive journey through Earth's ecosystems with stunning visuals, sounds, and scents, it showcases the synergy between #AI and the natural world: https://t.co/b9gwqQOYnH
— NVIDIA (@nvidia) 12 mars 2024#GTC24 attendees will have the opportunity to explore @refikanadol
's LLM "A Living Archive" exhibit: An immersive journey through Earth's ecosystems with stunning visuals, sounds, and scents, it showcases the synergy between #AI and the natural world: https://
nvda.ws/4cfFy7y -
HRI Conference Workshop on Embodied Voices and TTS Models
By
–
Audience question on character voices and TTS needs @HRI_Conference – Consider our newly accepted RSS Workshop on Embodied Voices on July 15! Bringing the latest deep TTS models together with roboticists https://
rosielab.github.io/wev/ #hri2024 -
Hugging Face Diffusers: Guide to Image Generation Techniques
By
–
✨ Blog-tastic Tuesdays ✨https://t.co/AYSMGFv4yg
— Satya Mallick (@LearnOpenCV) 12 mars 2024
Our latest research article will guide you through using the Hugging Face Diffusers library to generate images with different techniques. Additionally, you will get access to a notebook with all the experiments discussed in this… pic.twitter.com/2mylHQHeBiBlog-tastic Tuesdays https://
learnopencv.com/hugging-face-d
iffusers/
… Our latest research article will guide you through using the Hugging Face Diffusers library to generate images with different techniques. Additionally, you will get access to a notebook with all the experiments discussed in this -
Testing AI Systems: Evaluating GPT-4V Vision Capabilities
By
–
This is a great illustration of how hard it is to figure out how good AI systems are via testing. GPT-4V solves the famous dog versus muffin image problem… except it doesn’t if the image is changed so it isn’t in the training data… except it does, but only some of the time.
-
AI Models’ Remarkable Image Analysis and Geolocation Inference Capabilities
By
–
The ability of the AI to make very educated guesses from images is underrated and never ceases to amaze me. Both Claude 3 and GPT-4 figure out I was likely in Monterrey from a picture of a sea otter and a small amount of architecture (pictures were from me, not in training.)
-
Covariant Unveils RFM-1: ChatGPT-like AI for Physical Robots
By
–
Robotics startup Covariant just unveiled RFM-1, an AI platform that brings ChatGPT-like language reasoning to physical robots.
— Rowan Cheung (@rowancheung) 12 mars 2024
The platform allows robots to learn new skills, adapt to unexpected situations, and interact with humans more naturally. pic.twitter.com/Sfq0buypxpRobotics startup Covariant just unveiled RFM-1, an AI platform that brings ChatGPT-like language reasoning to physical robots. The platform allows robots to learn new skills, adapt to unexpected situations, and interact with humans more naturally.