Yuchen Cui
@YuchenCui1
Followers
1,159
Following
552
Media
5
Statuses
26
Postdoc @Stanford in Interactive Robot Learning 🤖🤖🤖 | previously CS PhD @UTAustin , BS @PurdueECE
Stanford, CA
Joined August 2011
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
#T20WorldCup
• 892110 Tweets
#INDvSA
• 455241 Tweets
#TeamIndia
• 308861 Tweets
Bumrah
• 250145 Tweets
South Africa
• 218909 Tweets
Italy
• 160743 Tweets
Switzerland
• 88732 Tweets
#SvizzeraItalia
• 80259 Tweets
Miller
• 74750 Tweets
#ViratKohli𓃵
• 73876 Tweets
#RohitSharma𓃵
• 70019 Tweets
Denmark
• 57709 Tweets
Jai Hind
• 52442 Tweets
ايطاليا
• 48295 Tweets
Arshdeep
• 48162 Tweets
भारतीय टीम
• 47538 Tweets
टीम इंडिया
• 44088 Tweets
Alemania
• 42803 Tweets
Thala
• 40886 Tweets
Spalletti
• 40069 Tweets
Suiza
• 35895 Tweets
भारतीय क्रिकेट टीम
• 34399 Tweets
#GERDEN
• 34169 Tweets
#SUIITA
• 33530 Tweets
#ネーションズリーグ
• 32870 Tweets
سويسرا
• 32866 Tweets
#HardikPandya
• 32786 Tweets
المانيا
• 31751 Tweets
Swiss
• 31739 Tweets
イタリア
• 31658 Tweets
#SuryakumarYadav
• 31562 Tweets
Dinamarca
• 25933 Tweets
Donnarumma
• 24643 Tweets
Dortmund
• 23523 Tweets
Xhaka
• 22821 Tweets
スロベニア
• 22624 Tweets
Klassen
• 20896 Tweets
#Champions
• 16771 Tweets
#RahulDravid
• 16573 Tweets
#RishabhPant
• 14653 Tweets
Havertz
• 13523 Tweets
#indiawins
• 13416 Tweets
決勝進出
• 10141 Tweets
Pinned Tweet
Thrilled to announce that I am joining
@CS_UCLA
as an Assistant Professor this Fall! 🐻
Many thanks to my incredible advisors, mentors, family and friends for the encouragement and support. ❤️Looking forward to this exciting new chapter and all the opportunities ahead! 🤖🤖🤖
37
15
647
We use gestures all the time for specifying targets! How can robots make sense of “gimme that one”?
We propose GIRAF, a framework for interpreting human gesture instructions using LLMs.
Paper to appear in
@corl_conf
:
Website:
7
15
85
Thanks Scott for all the support and guidance throughout my PhD!
Congrats to
@YuchenCui1
for successfully defending her dissertation, "Efficient Algorithms for Low-Effort Human Teaching of Robots". Keep an eye out for her upcoming work as a postdoc with
@DorsaSadigh
at Stanford!
3
5
83
2
0
24
Excited to share our work EMPATHIC on learning from implicit human feedback!
To be presented at
#CoRL2020
tomorrow at 11:10AM PT.
website:
video:
w/
@Qipingzhang2015
@ale_allievi
Peter Stone
@scottniekum
@bradknox
0
1
15
How does the design of ML interaction influences the human in the loop and the learning outcomes? Check out our latest survey paper on this!
How should we structure an AI's interaction with a teacher to improve learning? Our survey paper on "Understanding the Relationship between Interactions and Outcomes in Human-in-the-Loop Machine learning" was just accepted to IJCAI'21. Pre-print:
1
6
21
0
0
7
Our user study shows that GIRAF achieves higher success rates and is preferred by users over the language-only baseline (code as policies) in tasks that are hard to specify.
0
0
7
It is frustrating to see robots making the same mistakes over and over again, come to
@LihanZha
's poster at ICRA and see how we enable robots to remember language corrections with LLMs!
Excited to share our work DROC at
#ICRA2024
!🚀 DROC empowers robots to learn from online language corrections and effortlessly generalize to new tasks.
Join my presentation in room AX-F201 from 13:30 - 15:00 on Thu 16 May,and swing by our poster at BT13-AX.6 between 16:30-18:00!
0
2
20
0
0
8
We further construct a GestureInstruct evaluation suite and demonstrate that GIRAF can reason about diverse types of gestures including deictic, iconic, symbolic and semaphoric gestures.
Link:
1
0
5
GIRAF describes the scene and human gesture in language to prompt an LLM task planner. This enables grounding the LLM to capture the scene and human intent.
1
0
5
We are presenting this work at
#NeurIPS2023
Wednesday morning at poster
#423
. Come and check it out if you are also in New Orleans! ⚜️
In imitation learning (IL), we often focus on better algorithms, but what about improving the data? What does it mean for a dataset to be high quality?
Our work takes a first step towards formalizing and analyzing data quality. (1/5)
1
14
79
0
1
3
GIRAF also enables the robot to interpret different gestures as well as interpret the same gesture differently in long-horizon interaction.
0
0
3
0
0
2