5 Photos and videos
ShaLab retweeted
10 Jun 2020
Excited to share our work in collaboration with @whi_rl!
We propose a multi-agent RL technique to improve generalization across scenarios where the types and quantities of agents change by "imagining" sub-scenarios.
arxiv.org/abs/2006.04222
2
8
40
ShaLab retweeted
12 May 2020
BabyWalk AI breaks complex navigation into simple steps ift.tt/2LmtJRV
7
5
14 May 2020
Excited to share our #acl2020nlp paper:
"BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps"
by Wang (Bill) Zhu, @Hexiang_Hu, Jiacheng Chen, Zhiwei Deng, @vihaniaj, @ieeugene, and @feishaAI
arxiv.org/pdf/2005.04625.pdf
4
9
13 Jan 2020
Check out our new paper at #AISTATS2020:
"Amortized Inference of Variational Bounds for Learning Noisy-OR" by Yiming Yan, Melissa Ailem, and @feishaAI
arxiv.org/abs/1906.02428
4
30 May 2019
New paper at #ICML2019: "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" by @shariqbal and @feishaAI
Paper: arxiv.org/abs/1810.02912
Code: github.com/shariqiqbal2810/M…
4
6
ShaLab retweeted
5 Feb 2019
It is out ! @ShaLabUSC @feishaAI
5 Feb 2019
Hyper-parameter Tuning under a Budget Constraint. (arXiv:1902.00532v1 [cs.LG]) bit.ly/2SqVbD3
1
1
1
Our lab’s work on zero-shot learning, combining several conference papers and updating with new perspectives, results and evaluation metrics, along with codes. @ShaLabUSC @weilunchao @BoqingGo @martbeerina arxiv.org/abs/1812.06423
3
14
ShaLab retweeted
12 Dec 2018
Great article published this week by @feishaai about #Learning #ComputerScience #ComputerVision #PatternRecognition deepai.org/publication/learn…
3
9
6 Dec 2018
Check out our #NeurIPS2018 paper: "Synthesized Policies for Transfer and Adaptation across Tasks and Environments" by @Hexiang_Hu, Liyu Chen, @boqinggo, and @feishaAI.
Paper: hexianghu.com/pdf/hu2018synp…
Project Page: sites.google.com/view/neurip…
Poster: hexianghu.com/pdf/posters/ni…
9
7
15 Nov 2018
Farewell lunch for our postdoc, @Chao_Kai_Chiang. Best of luck in the next stage of your career!
2
ShaLab retweeted
12 Nov 2018
Hey! Our NEW zero-shot learning toolbox has been released: github.com/pujols/Zero-shot-…. Includes our algorithms SynC and EXEM, as well as scripts for generalized zero-shot learning evaluation. Joint work with @weilunchao @boqinggo and @feishaAI.
5
12
3 Nov 2018
Saying good-bye to Han-Jia Ye, our visiting PhD student from Nanjing University. It was great having you at @ShaLabUSC this past year!
7
18 Sep 2018
[1/2] Check out our papers from #ECCV2018!
(1) "Cross-Modal and Hierarchical Modeling of Video and Text" (openaccess.thecvf.com/conten…) by @bwzhang_usc, @Hexiang_Hu, and @feishaAI.
1
3
5
18 Sep 2018
[2/2]
(2) "Retrospective Encoders for Video Summarization" (openaccess.thecvf.com/conten…) by Ke Zhang, Kristen Grauman, and @feishaAI.
2
3
How a bot (or perhaps even a person) can be an engaging conversation partner? - being curious! arxiv.org/abs/1808.07104 to appear at @conll2018 @ShaLabUSC
4
7
Is multi-task learning useful in NLP? Our (@shalabusc) extensive empirical study appearing at @coling2018 suggests so, at least half of the time for sequence tagging tasks. arxiv.org/abs/1808.04151
5
12
27 Jul 2018
Harry's (@weilunchao) last day in the lab! After graduation, Harry will be doing a postdoc at @Cornell, before becoming an assistant professor at @OhioState in Fall 2019. We'll miss you!
5
11 Jul 2018
Celebrating ShaLab's two newest PhD grads: Dr. @schangpi and Dr. @weilunchao! Congratulations, Beer and Harry!
1
7
5 Jul 2018
In April 2018, we journeyed into the mountains of Running Springs, CA for our first-ever ShaLab Retreat. Check out some of the exciting moments from an action-packed weekend of paintball, archery, s'mores, and lab bonding! youtu.be/j3ugTqkIzGU
2
3