Both of Seohyun ‘s upcoming drama partners Junyoung and Na Inwoo attended today’s AAA 🙊❤️ #AAAI2021

#AAAI2021 Come chat about C2PO: the causal, commonsense plot ordering storyteller and *how* ppl think about causality using commonsense expectations in stories. Sat. 2/6 8:45-10:30, 4:45-6:30 PST. Paper: https://t.co/lBehKDUsWx Site: https://t.co/EhatOmJ3p3 w/ EILab, @mark_riedl

More #AAAI2021 fun! I'll be doing a (live!) talk+poster👇 on getting RL agents to act+speak consistently and naturally while trying to achieve their motivations in grounded fantasy worlds. Project: https://t.co/QDlvgj9Jp8 Mon 2/8 at 1:30p EST, RLG Workshop https://t.co/KbrLmyft00

Source code comments become outdated when developers fail to update them upon code changes. Check out our #aaai2021 paper "Deep Just-In-Time Inconsistency Detection Between Comments and Source Code", w/ Sheena Panthaplackel, Milos Gligoric and Ray Mooney https://t.co/ZyADn7xM69

📢#AAAI2021 Check out our paper "Learning to Rationalize" w @VeredShwartz @YejinChoinka @rachelrudinger Join QA session: https://t.co/l8ik1bqXwO BC-D1-R1, Cluster F, Position 3 4-Feb 8:45-10:30AM / 4:45-6:30PM PST 📰Paper: https://t.co/XZ52yBy1iu 📺Video: https://t.co/gmjFvgucYh

Happening now! Join us for a demo on "AutoText: An End-to-End AutoAI Framework for Text" #AAAI2021. You can now create high-quality NLP models with just click of buttons. Joint efforts with multiple teams @IBMResearch. #NLProc #AutoAI #ArtificialIntelligence

Our #AAAI2021 paper (w/ Wenxuan and @xiangrenNLP) analyzes the [CLS] embedis, and reveals that they have high var. in std and high cor. across dims, which is harmful for fine-tuning BERT. We propose isotropic batch normalztn (IsoBN) to improve it. #NLProc https://t.co/w7eJgSC51w

Can we train an #AI to understand multiple languages while only trained on one? In a #AAAI2021 paper, researchers at IBM attempt to do just this. Check it out ➡️ https://t.co/d0iPj4FDtF

Segatron: I see your segment and positional embeddings and I raise you paragraph, sentence, and token embeddings. Richer specification of text structure does indeed improve effectiveness on downstream tasks. https://t.co/TDeDdcyNLU #AAAI2021

Professor Zhu Wenwu’s team from the department of Computer Science won the MetaDL Challenge at #AAAI2021.

We are actively working on Neural Architecture Search (NSA) and develop AI that builds AI Fundamentally, this is what makes no code/low code machine learning possible We will be presenting at #AAAI2021 tmrw at 8:45am and 4:45pm PT! Paper here - https://t.co/3bp33neqeA

Today I will be presenting our work on "Predicting Patient Outcomes with Graph Representation Learning" at the #W3PHIAI workshop at #AAAI2021 at 6:45pm GMT 🎉 Meanwhile my co-author Catherine will also be presenting the same work a little later at 7:30pm at DLG workshop

#AAAI2021 に採択された京介さん@kyoun との共著論文をarXivにアップしました． https://t.co/8I3JrMQt40 ドキュメント画像について視覚的に質問応答を行うタスク (VisualMRC)を提案しました．さらに，事前学習seq2seqモデルを利用してこのタスクに適応可能なモデルの提案も行いました．

Who will take the challenge? ⁦@luislamb⁩ proposes an exciting research program at the #AAAI2021 Neuro-Symbolic AI Panel.

In this paper, Amazon scientists propose an E2E system that is designed to jointly train on multiple speech-to-text tasks, such as ASR (speech-transcription) and SLU (speech-hypothesis), and text-to-text tasks, such as NLU (text-hypothesis). https://t.co/fZ5snvEIdF #AAAI2021

Fahad Kamran and Jenna Wiens propose a new training scheme for optimizing deep survival analysis models that maximizes discriminative performance, subject to good calibration. #AAAI2021 https://t.co/1NYCnk51N4

#NITIAayog Adviser @annaroy9 presented India's Strategy for AI at the International AAAI conference, in the session on Government's AI Strategy. #AIForAll #AAAI2021

We train a humanoid agent to sit on a chair in different styles with hierarchical reinforcement learning. Check out our latest #AAAI2021 paper: https://t.co/KRbFFPFCq8. Collaboration with Yu-Wei Chao, @wfchen9 and @jiadeng

Slides from the @RealAAAI #AAAI2021 panel on Neural-Symbolic AI. with @AvilaGarcez Neurosymbolic AI: the 3rd wave. Thank you @kerstingAIML @k_leyton_brown @mishumausam @zicokolter @guyvdb Marta Kwiatkowska, Leslie Kaelbling, Matt Botvinick 1/n

Looking forward to speak on Tuesday at the #AAAI2021 workshop on Plan, Activity & Intent Recognition (PAIR 2021) about some of our current work on facilitating fluid human-#AI interaction.. (Feb 9 7:15AM PST). https://t.co/6McB36pgTT