Jeff Dean, Google's Chief Scientist, tells a student what it's like to be a computer scientist. v/
@JeffDean
@mit_csail
-
Jeff Dean shares insights on computer science careers
By
–
-
Web Development Evolution: From HTML to Vue Framework
By
–
Web development timeline (v/
@fireship_dev
): 1990: HTML invented
1994: CSS invented to fix HTML
1995: JS invented to fix HTML/CSS
2006: jQuery invented to fix JS
2010: AngularJS invented to fix jQuery
2013: React invented to fix AngularJS
2014: Vue invented to fix React & Angular -
Inside MIT’s Stata Center: Home to CSAIL Researchers
By
–
Take a trip inside MIT's Stata Center, home to many CSAIL researchers. pic.twitter.com/iFdJJ4cCmA
— MIT CSAIL (@MIT_CSAIL) 19 octobre 2024Take a trip inside MIT's Stata Center, home to many CSAIL researchers.
-
Kid Mistakes 3D-Printed Floppy Disk for Save Icon
By
–
True story: a kid saw this and said, "oh, you 3D-printed the 'Save' Icon." http://
bit.ly/2yxk0ml Credit: @Bill_Gross -
Diffusion Forcing: Versatile Sequence Model Backbone for World Models
By
–
Across each demo, Diffusion Forcing acted as a full sequence model, a next-token prediction model, or both. According to the researchers, this versatile approach could potentially serve as a powerful backbone for a "world model" one day.
-
Diffusion Forcing generates stable high-resolution videos from single frames
By
–
To generate videos, they trained Diffusion Forcing on Minecraft gameplay & colorful digital environments created w/i Google's DeepMind Lab Simulator.
— MIT CSAIL (@MIT_CSAIL) 17 octobre 2024
When given a single frame of footage, the method produced more stable, higher-resolution videos than comparable baselines,… pic.twitter.com/x4ETG13DZJTo generate videos, they trained Diffusion Forcing on Minecraft gameplay & colorful digital environments created w/i Google's DeepMind Lab Simulator. When given a single frame of footage, the method produced more stable, higher-resolution videos than comparable baselines,
-
New Robotics Research Paper from Chen, Du, Tedrake, Sitzmann
By
–
Authors: Boyuan Chen (
@BoyuanChen0
), Diego Martí Monsó, Yilun Du (
@du_yilun
), Max Simchowitz (
@max_simchowitz
), Russ Tedrake (
@RussTedrake
), Vincent Sitzmann (
@vincesitzmann
)
Paper: https://
bit.ly/3U1MrC7 Full video: https://
bit.ly/48cPTj8 -
Diffusion Forcing: Neural Networks Learn Token Denoising and Prediction
By
–
Diffusion Forcing trains neural networks to cleanse a collection of tokens, removing different amounts of noise w/i each one while simultaneously predicting the next few tokens.
-
Robotic Arm AI Masters Multi-Step Tasks With Memory
By
–
When implemented into a robotic arm, for example, it helped swap two toy fruits across three circular mats, a minimal example of a family of long-horizon tasks that require memories. Despite starting from random positions and seeing distractions like a shopping bag blocking the
-
Diffusion Forcing Bridges Diffusion Models and Teacher Forcing
By
–
Diffusion Forcing found common ground between diffusion models & teacher forcing: they both use training schemes that involve predicting masked (noisy) tokens from unmasked ones. In the case of diffusion models, they gradually add noise to data, which can be viewed as fractional