달 @putmesmile

방가방가 Joined June 2014

Tweets

20
Followers

8
Following

120
Likes

190

달 @putmesmile

3 years ago

@TanselYucelen @UW Currently can’t see in Youtube

1 0 1 77 0

View Details

Archit Sharma @archit_sharma97

4 years ago

It feels hard to do robotics research these days. There seems to be this pressure to deliver "large scale" results to keep up with vision/language, to tie your results to the LLM bandwagon and ride the wave

Flo Crivello @Altimor

4 years ago

LLMs have generally sucked the oxygen out of the room, but robotics seems to have been particularly impacted Been meeting with robotics experts over the last few days, and the mood is gloomy to say the least

42 98 1K 523K 303

4 7 111 20K 11

View Details

Andreas Zeller @AndreasZeller

4 years ago

What makes a well-written grant proposal? After two decades of writing, revising, and reviewing grant proposals, I recently discovered the blog posts of @amderrington, who like no one else captures the most crucial points. A selection.👇

6 76 447 64K 478

View Details

Greg Brockman @gdb

5 years ago

Biggest mental shift while switching from classic to scientific programming: explicit “for” loops are now extremely expensive. Instead, you express as much as you can by chaining hyperoptimized lower-level “for” loop primitives, eg matrix multiplies. Fun & new way of thinking.

18 16 273 0 32

View Details

Ben Recht @beenwrekt

5 years ago

Last month at the Stanford ISL colloquium I discussed the early history of machine learning, noting the astounding groundwork done before 1970. youtube.com/watch?v=47tKry…

3 32 131 0 67

View Details

Heidi Howard @heidiann360

5 years ago

I have finally decided that life is too short to use TikZ. What do my fellow researchers recommend for drawing diagrams for papers?

181 71 810 0 321

View Details

Ludovico Lami @LamiLudovico

5 years ago

@heidiann360 For an illustration of how pointless it is to spend too much time drawing diagrams, I recommend looking at Figure 1 here arxiv.org/abs/quant-ph/0…

2 3 78 0 4

View Details

Nathan Lambert @natolambert

5 years ago

"Synergy of Prediction and Control in Model-based Reinforcement Learning" My thesis is now available, thank you @Berkeley_EECS and all who contributed to this. It has been a massive journey. www2.eecs.berkeley.edu/Pubs/TechRpts/… I'll explain what I wrote about and a few reflections 👇 1/

10 17 177 0 36

View Details

Kevin Zakka @kevin_zakka

5 years ago

Dove into a new area at the beginning of the year: dexterous hand manipulation. It's been incredibly gratifying to learn new things on the daily: new simulator (MuJoCo), inverse kinematics (differential & QP), and now motion capture and retargeting (little bit of Blender) 😀

3 2 82 0 14

View Details

Gabriel Peyré @gabrielpeyre

5 years ago

The Rosenbrock function is the most famous test function for optimization algorithms. en.wikipedia.org/wiki/Rosenbroc…

3 67 349 0 48

View Details

Sergey Levine @svlevine

8 years ago

Favorite quote so far from Emo Todorov's CoRL 2018 tutorial: "The world is not really stochastic. If you've noticed -- a robot doesn't just spontaneously start shaking. Unless you hook up an RL algorithm to it."

0 52 290 0 6

View Details

Kevin Zakka @kevin_zakka

5 years ago

I’ve been working with MuJoCo + dm_control full-time for the last 2 months, and it’s been an absolute pleasure. Completely sold! So much respect for @DeepMind’s clarity of thought and foresight re:the API design. Will write up a blog post at a more appropriate time!

3 5 137 0 25

View Details

flight GNC @flight_gnc

5 years ago

Russ Tedrake. Robot Manipulation: Perception, Planning, and Control (Course Notes for MIT 6.800/6.843). manipulation.mit.edu.

1 1 3 0 0

View Details

flight GNC @flight_gnc

5 years ago

Russ Tedrake. Underactuated Robotics: Algorithms for Walking, Running, Swimming, Flying, and Manipulation (Course Notes for MIT 6.832). underactuated.mit.edu

0 1 3 0 0

View Details

Eric Heiden @eric_heiden

5 years ago

We introduce a new method to learn simulators from depth and RGB videos. The "URDF" of an articulated rigid-body mechanism is reconstructed, and the parameters of the simulator inferred through Bayesian inference. Website: eric-heiden.github.io/video2sim/ Paper: arxiv.org/abs/2203.10488

4 47 300 0 59

View Details

Andrew Carr 🤸 @andrew_n_carr

5 years ago

I had no clue that just 6 lines of code would improve my research productivity / reproducibility so dramatically

28 132 1K 0 595

View Details

yobibyte @y0b1byte

5 years ago

A lot of people complain that RL doesn't work and RL researchers are still playing games. While this criticism is true to some extent, there's been a new trend of applying RL for real-life problems. This is a thread of notable papers split by the topic. 1/n