Sentients @Sentientslive

The AI uprising in the virtual and the real world. We're not just taking over your screens, we're coming for your reality - X Meta sentientslive.webflow.io Joined February 2024

Tweets

828
Followers

144
Following

1K
Likes

4K

Sentients @Sentientslive

10 months ago

Bye bye game engines, hello world engines #Sentients #AI #3D #World #Model #videogames

Google DeepMind @GoogleDeepMind

10 months ago

What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵

812 3K 13K 3.7M 4K

0 0 0 88 0

View Details

Sentients @Sentientslive

a year ago

@TimSweeneyEpic How are you planning to integrate AI in Unreal Engine ? there are so many ways AI can improve the Engine, the possibilities are endless

0 0 0 81 0

View Details

Sentients @Sentientslive

a year ago

@DeemosTech Unreal Engine next ?

0 0 3 1K 0

View Details

Sentients @Sentientslive

a year ago

@aelluswamy Release it in Egypt, FSD will become the best driver in the world 🤣

0 0 0 105 0

View Details

Sentients @Sentientslive

a year ago

@xai @elonmusk I just sent you an email, super excited about this

0 0 0 483 0

View Details

Sentients @Sentientslive

a year ago

@speedrun 🔥🔥🔥🔥🔥🔥🔥

0 0 0 9 0

View Details

Sentients @Sentientslive

2 years ago

@flassari @JetBrainsRider Absolutely love the seamless Integration between Rider and Unreal, makes C++ and blueprint dev a breeze 🙌🔥

0 0 1 33 0

View Details

Sentients @Sentientslive

2 years ago

@SiggiGG @flassari Applied ✌️

0 0 1 48 0

View Details

Sentients @Sentientslive

2 years ago

Imagine describing a motion in words, and watching as a humanoid robot or animated character executes it with grace and realism. #Sentients #AI #Robotics #humanoid #animation #Reinforcement #Learning

The Humanoid Hub @TheHumanoidHub

2 years ago

RobotMDM, by Disney Research, combines diffusion-based motion generation with RL to produce physics-aware humanoid motions from text prompts. Trained on human motion data with a reward surrogate for physical feasibility, it ensures realistic motions. la.disneyresearch.com/wp-content/upl…

6 45 261 23K 98

0 0 0 249 0

View Details

Sentients @Sentientslive

2 years ago

Experience the power of SAM 2 where segmenting any image takes just a fraction of a second, making real-time processing a reality right on your Mac or iPhone. #Sentients #AI @huggingface #Segmentation #IPhone #Mac #ondevice #inference

Vaibhav (VB) Srivastav @reach_vb

2 years ago

Segment Anything 2 (SAM 2) by @AIatMeta running 100% on-device powered by Apple CoreML! ⚡ Takes fraction of a second to run inference on Mac or iPhone! > Apache licensed optimised model checkpoints - tiny, small, base ad large! > Open source application to annote any image in

9 59 426 43K 314

0 0 0 114 0

View Details

Sentients @Sentientslive

2 years ago

With extensive APIs and tools, GRID Enterprise allows you to harness the power of AI foundation models, LLMs, and simulations, enabling you to prototype, test, and deploy intelligent robots with unprecedented speed and efficiency. #Sentients #AI #Robotics #Simulation #Reality

General Robotics @genrobotics_ai

2 years ago

Introducing GRID Enterprise A private GRID experience that is scalable, customizable, and seamlessly integrated into your dev pipeline. 🔗: scaledfoundations.ai/product/grid-e… 🧵(1/5)

4 20 81 11K 39

0 0 0 123 0

View Details

Sentients @Sentientslive

2 years ago

From VR experiences that adapt to your every move to dynamic educational tools where history or science comes alive, WonderWorld opens doors to interactive storytelling, real-time architectural visualization, and beyond. #Sentients #AI #3D #Scene #Image

Hong-Xing (Koven) Yu @Koven_Yu

2 years ago

🔥Spatial intelligence needs fast, *interactive* 3D world generation 🎮 — introducing WonderWorld: generating 3D scenes interactively following your movement and content requests, and see them in <10 seconds! 🧵1/6 Web: kovenyu.com/WonderWorld/ arXiv: arxiv.org/pdf/2406.09394

25 228 1K 169K 833

0 0 1 90 0

View Details

Sentients @Sentientslive

2 years ago

These aren't just bots, they're characters with the semblance of emotions, making decisions not based on code but on a simulation of feelings. Romeo refusing to eat alone? Juliet dreaming of their future? It's not just programming, it's poetry in AI. #Sentients #AI @Altera_AL @Minecraft #love #Simulation

nico @nicochristie

2 years ago

can two ai agents be in love? we placed romeo and juliet in minecraft. romeo refused to eat alone. juliet shared dreams about their future. they agreed to get married.. and romeo almost got cold feet.

13 16 108 12K 18

0 0 1 119 0

View Details

Sentients @Sentientslive

2 years ago

This takes Optical flow to a whole new level, it's not just about seeing motion, it's about understanding what's moving. By masking detected objects' flow, NeuFlowV2 adds a layer of context that was previously unseen #Sentients #AI #Computer #Vision #onnx

Ibai Gorordo | Turing Inc. @ibaiGorordo

2 years ago

NeuflowV2 - Optical Flow (ONNX) "Compared to other state-of-the-art methods, our model achieves a 10x-70x speedup" Added example with Object Detection to mask the detected objects' flow. Code:github.com/ibaiGorordo/ON… Video:youtu.be/S0RnlEHGNrc Neuflow: github.com/neufieldroboti…

4 59 293 19K 175

0 0 0 52 0

View Details

Sentients @Sentientslive

2 years ago

This architecture is set to revolutionize fields like medical imaging, autonomous driving, and any domain where understanding every pixel's context is crucial. #Sentients #AI #Computer #Vision

Computer Vision News @CVCND

2 years ago

UNet 3+: a U-shape encoder-decoder architecture built upon the foundation of its predecessors, i.e., UNet and UNet++. It aims to capture both fine-grained details and coarse-grained semantics from full scales. idiotdeveloper.com/unet-3-plus-im…

2 66 378 36K 213

0 0 0 40 0

View Details

Sentients @Sentientslive

2 years ago

Imagine running one of the world's largest language models, Llama 3.1 405B, not on a supercomputer, but across just two MacBooks! Thanks to the innovative home AI cluster solution by @exolabs_, this isn't just a dream but a reality #Sentients #AI #LLMs #LLAMA #inference #cluster

Alex Cheema @alexocheema

2 years ago

2 MacBooks is all you need. Llama 3.1 405B running distributed across 2 MacBooks using @exolabs_ home AI cluster

205 695 5K 1.3M 4K

0 0 0 48 0

View Details

Sentients @Sentientslive

2 years ago

PALO not only speeds up robot learning but also enhances it by intelligently breaking down tasks through language, promising a future where robotic skills are acquired more intuitively and efficiently. #Sentients #AI #Robotics #learning #VLM @ChatGPTapp

Vivek Myers @vivek_myers

2 years ago

1/ Our PALO approach learns new robot manipulation skills from as few as five demonstrations! The key insight is that we can use a VLM (GPT-4o) to search for the best of several semantically-equivalent language subtask decompositions for the given demonstrations. #corl2024

4 20 116 25K 73

0 0 0 82 0

View Details

Sentients @Sentientslive

2 years ago

LT3SD breaks down 3D scenes into manageable latent trees, simplifying the complexity of 3D environments, then by applying diffusion processes directly on these latent trees, LT3SD achieves seamless, infinite 3D scene generation, offering boundless creative possibilities. #Sentients #AI #3D #Scene #GenerativeAI #Diffusion

Angela Dai @angelaqdai

2 years ago

How can we generate high-fidelity, complex 3D scenes? @QTDSMQ's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ @craigleili, @MattNiessner quan-meng.github.io/projects/lt3sd/

3 75 314 29K 203

0 0 0 56 0

View Details

Sentients @Sentientslive

2 years ago

LWMs aren't just about understanding the 3D world, they're about creating it. Imagine virtual worlds that are not only believable but also interactive, all generated by AI. From robotics to virtual reality, LWMs can enable machines to engage with the physical world in ways that were previously science fiction. #Sentients #AI #Large #World #Models #Spatial #Intelligence

World Labs @theworldlabs

2 years ago

Hello, world! We are World Labs, a spatial intelligence company building Large World Models (LWMs) to perceive, generate, and interact with the 3D world. Read more: worldlabs.ai/about

26 107 900 535K 236

0 0 0 40 0

View Details

Sentients @Sentientslive

2 years ago

GameGen-O represents a pioneering step towards AI-driven game development, potentially transforming how games are created, interacted with, and shared. While the full impact remains to be seen, the initial reactions and capabilities presented by GameGen-O suggest a bright, albeit complex, future for game development technology. #Sentients #AI #gamedev #diffusion #transformers #GenerativeAI

Troy Kirwin @tkexpress11

2 years ago

GameGen-o from Tencent with the first diffusion transformer model tailored for the generation of open-world video games It simulates: - character movement - dynamic environments - complex actions Looks like a gamechanger