jaesung choe (@choe_jaesung) 's Twitter Profile
jaesung choe

@choe_jaesung

Research scientist @NVIDIA

ID: 1551841156388233218

linkhttps://jaesung-choe.github.io/ calendar_today26-07-2022 08:05:50

11 Tweet

8 Takipçi

52 Takip Edilen

NVIDIA AI Developer (@nvidiaaidev) 's Twitter Profile Photo

📣 #NVIDIAResearch paper, XCube, generates highly-detailed #3D scenes with resolutions of up to 1024³ in under 30 seconds. 👀 Capable of leveraging voxel attributes such as normals, semantics, & TSDF, this model is pushing the boundary of 3D generation. nvda.ws/3TeXk3K

Jim Fan (@drjimfan) 's Twitter Profile Photo

OpenAI is expected to demo a real-time voice assistant tomorrow. What does it take to deliver an immersive, or even magical experience? Almost all voice AI go through 3 stages: 1. Speech recognition or "ASR": audio -> text1, think Whisper; 2. LLM that plans what to say next:

OpenAI is expected to demo a real-time voice assistant tomorrow. What does it take to deliver an immersive, or even magical experience?

Almost all voice AI go through 3 stages: 
1. Speech recognition or "ASR": audio -> text1, think Whisper;
2. LLM that plans what to say next:
Jim Fan (@drjimfan) 's Twitter Profile Photo

What makes up the abstract concept of an apple? We read the word "apple" as a string, see 2D pictures online, 3D shape in real life, and moving apples in videos. We touch the apple, feel its geometry in our palms and texture through the rich tactile sensation on our fingers. Do

What makes up the abstract concept of an apple? We read the word "apple" as a string, see 2D pictures online, 3D shape in real life, and moving apples in videos. We touch the apple, feel its geometry in our palms and texture through the rich tactile sensation on our fingers. 

Do
Yuke Zhu (@yukez) 's Twitter Profile Photo

Excited to announce RoboCasa, a large-scale simulation framework of everyday tasks! We use generative AI tools to create diverse objects, scenes, and tasks. Simulation plays a pivotal role in our Data Pyramid for training generalist robots. Open-source at robocasa.ai

Guy Davidson (@guyd33) 's Twitter Profile Photo

New preprint! How should we think about cognitive representations of goals? We argue that thinking about goals as a type of symbolic cognitive program makes a lot sense -- and perform behavioral and computational work to support this idea: 1/n exps.gureckislab.org/guydav/goal_pr…

New preprint! How should we think about cognitive representations of goals? We argue that thinking about goals as a type of symbolic cognitive program makes a lot sense -- and perform behavioral and computational work to support this idea: 1/n

exps.gureckislab.org/guydav/goal_pr…
Nando de Freitas (@nandodf) 's Twitter Profile Photo

Meta Chameleon and Gemini have also adopted the Gato ( arxiv.org/pdf/2205.06175 ) architecture. Is this going to be the ultimate approach for MIMO (multimodal input multimodal output models) or is there something else we should be trying? There’s been great progress in scaling

Allen T. (@mr_allent) 's Twitter Profile Photo

MusePose comfyui node 🔥 MusePose is a pose driven image2video framework for virtual human generation Link to comfyui node in post below:

Radiance Fields (@radiancefields) 's Twitter Profile Photo

The Three.js-based 3DGS implementation of Gaussian Splatting, GaussianSplats3D from Mark Kellogg has officially added 2DGS support with v0.4.3! Article: radiancefields.com/three-js-based… Github: github.com/mkkellogg/Gaus…

MrNeRF (@janusch_patas) 's Twitter Profile Photo

Click-Gaussian: Interactive Segmentation to Any 3D Gaussians arxiv.org/abs/2407.11793 Project: seokhunchoi.github.io/Click-Gaussian/ Method ⬇️ 1 | 2