VCLA_UCLA

Center for Vision, Cognition, Learning, and Autonomy from UCLA.
#AI #ComputerVision #CognitiveScience #MachineLearning #Robotics

[Sean Welleck @wellecks]

MathAI4Ed - a NeurIPS workshop on the intersection of math, AI, and education - is coming up soon!

Dec 14, 9am - 6pm PST


We’ll have papers/posters, a live interview with @stephen_wolfram, 6 invited speakers, & a live panel on math/AI/education

https://t.co/ch1woTU0AU
👇1/8

[Arjun Akula @arjunreddy2613]

Excited to share that our work on introducing Theory-of-Mind based cognitive framework for explaining deep learning models is accepted by iScience Journal. #XAI

Joint work from UCLA, UMich, OSU, BIGAI, Peking University, Tsinghua University.

arXiv link: https://t.co/TcDcaaYifM

[VCLA_UCLA @VCLA_UCLA]

Welcome to the NeurIPS 2021 workshop on the intersection of AI, mathematics, and education!📣

[Sean Welleck @wellecks]

Excited to announce “Math AI for Education: Bridging the Gap Between Research and Smart Education" (MathAI4Ed)

A NeurIPS 2021 workshop on the intersection of AI, mathematics, and education.

https://t.co/ch1woTU0AU

Now accepting submissions!
(due Oct 06, 2021)
(1/6)

[Pan Lu @COLM2026 @lupantech]

🎉Excited to release the data and code of our recent work on geometry problem solving: https://t.co/C3sbqPhGfQ! We propose a large-scale geometry problem dataset Geometry3K and an Interpretable Geometry Problem Solver (Inter-GPS) with neuro-symbolic reasoning.
#ACL2021

[VCLA_UCLA @VCLA_UCLA]

Three papers are accepted to ACL-IJCNLP 2021 @aclmeeting. More details and codes coming soon. Congratulations to all labmates and collaborators! @ Zilong Zheng @shuwen @lifeng_fan @liangqiu_1994 @YouPP97675560 @lupantech @nikepupu
#ACL2021NLP

[Jianwen Xie @jianwen_xie]

#CVPR2021 #EBMs CVPR 2021 Tutorial on "Theory and Application of Energy-Based Generative Models" is now available at https://t.co/trItdscfs8 !! @EBMworkshop @VCLA_UCLA

[Jianwen Xie @jianwen_xie]

Please share our accepted new work #CVPR2021 on learning energy-based models #EBMs for unordered point sets for synthesis, reconstruction, and classification: https://t.co/fNyrvgTvPr

[Jianwen Xie @jianwen_xie]

Our accepted PAMI paper about training a conditional EBM with a conditional generator as amortized sampling. It mimics the fast-thinking and slow-thinking process in brains, and also related to hot topics of amortized sampling for EBMs #EBMs in #ICLR2021. https://t.co/IvxFpMudbM

[Jianwen Xie @jianwen_xie]

Our new PAMI paper about 3D voxel EBM. It includes hot ideas in current #ICLR2021 for EBMs, such as (1) MCMC-based MLE, (2) amortized sampling with a generator, (3) multi-scaled Langevin sampling for EBM, and (4) using EBM for classification. #EBMs https://t.co/deyazEEEOB

[DeepAI @DeepAI]

Towards Socially Intelligent Agents with Mental State Transition and Human Utility
https://t.co/c6SOHeUEzF
by Liang Qiu et al. including @lupantech
#Computation #Language

[Jianwen Xie @jianwen_xie]

Late announcement: A review paper "Representation Learning: A Statistical Perspective" https://t.co/HV5ZS03234 was published by @AnnualReviews with @RuiqiGao @erik_nijkamp.The paper covers the current hot topics, e.g. ConvNet-EBM, amortized sampling for EBM, grid-cell model, etc.

[VCLA_UCLA @VCLA_UCLA]

Our recent work on unsupervised dialogue structure learning. #NLProc #emnlp2020 https://t.co/ExtECBNUTa

[Liang Qiu @liangqiu_1994]

Our paper “Structured Attention for Unsupervised Dialogue Structure Induction” is accepted as a long paper by #emnlp2020. I’d like to thank the contribution of each co-author, with special thanks to Prof. @Zhou_Yu_AI for great advice and detailed comments. #NLProc

[Erik Nijkamp @erik_nijkamp]

Grateful to have our work accepted in ECCV 2020 with amazing co-authors @TianHan10, @bo_pang0, et al.,
"Learning multi-layer latent variable model via variational optimization of short run MCMC for approximate inference":
https://t.co/ENVrrjdz9R
#ECCV2020 #mcmc

[VCLA_UCLA @VCLA_UCLA]

Our recent work on activity analysis. Accepted to #ECCV2020 @eccvconf

[arxiv @arxiv_org]

LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities. https://t.co/MWvJcxYgyh

[VCLA_UCLA @VCLA_UCLA]

Congratulations to @Sealiqing, our PhD candidate for the BEST paper award in the workshop of #ICML2020!

[Qing Li @Sealiqing]

Our paper is selected as the Best Paper Award in the ICML2020 Workshop on "Bridge Between Perception and Reasoning: Graph Neural Networks&Beyond"! Welcome to our spotlight talk (Sat 7:25 - 7:30 am PDT) and poster session (Sat 12:10 - 1:00 pm) if you are attending ICML this year.

[Arjun Akula @arjunreddy2613]

Thank you for a nice summary of our work @ecekt2

Join us (@gspandana , @sivareddyg ) at live Q&A today (Tuesday) at 11 pm PDT and Tomorrow (Wednesday) at 1pm PDT.

#acl2020nlp

[Ruiqi Gao @RuiqiGao]

(1/2) Interested in understanding towards grid cells? Check our preprint "A Representational Model of Grid Cells Based on Matrix Lie Algebras" https://t.co/QpuVb0zyCb (with @jianwen_xie, SC Zhu, YN Wu), with learned regular hexagon grid patterns!

[Erik Nijkamp @erik_nijkamp]

(1/2) "Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC" (@erik_nijkamp*, @RuiqiGao*, P. Sountsov, S. Vasudevan, @bo_pang0, S.-C. Zhu, Y. N. Wu):
https://t.co/mONLl9svzx
We show (1) exponential tilting of Glow, (2) mixing MCMC, (3) improved synthesis.

[Meagan Phelan @MeaganPhelan]

Explainable #AI continues to be discussed as critical to garnering human trust in automation and #robotics. A February paper in @SciRobotics by @VCLA_UCLA highlights this.

[Qing Li @Sealiqing]

(1/3) I am very happy to share our new paper accepted at #icml2020 @VCLA_UCLA

"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning"

paper with code: https://t.co/CO60qDpI19
https://t.co/kKtQHE95wJ