SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams ACL

Te-Lin Wu | Satwik Kottur | Andrea Madotto | Mahmoud Azab | Pedro Rodriguez | Babak Damavandi | Nanyun Peng | Seungwhan Moon |

Learning Action Conditions from Instructional Manuals for Instruction Understanding ACL

Te-Lin Wu | Caiqi Zhang | Qingyuan Hu | Alexander Spangher | Nanyun Peng |

ACQUIRED: A Dataset for Answering Counterfactual Questions In Real-Life Videos EMNLP

Te-Lin Wu | Zi-Yi Dou | Qingyuan Hu | Yu Hou | Nischal Chandra | Marjorie Freedman | Ralph Weischedel | Nanyun Peng |

Localizing Active Objects from Egocentric Vision with Symbolic World Knowledge EMNLP

Te-Lin Wu | Yu Zhou | Nanyun Peng |

Understanding Multimodal Procedural Knowledge by Sequencing Multimodal Instructional Manuals ACL

Te-Lin Wu | Alex Spangher | Pegah Alipoormolabashi | Marjorie Freedman | Ralph Weischedel | Nanyun Peng |

Character-centric Story Visualization via Visual Planning and Token Alignment EMNLP

Hong Chen | Rujun Han | Te-Lin Wu | Hideki Nakayama | Nanyun Peng |

HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning EMNLP Findings

Mingyu Derek Ma | Muhao Chen | Te-Lin Wu | Nanyun Peng |

COM2SENSE: A Commonsense Reasoning Benchmark with Complementary Sentences Findings

Shikhar Singh | Nuan Wen | Yu Hou | Pegah Alipoormolabashi | Te-lin Wu | Xuezhe Ma | Nanyun Peng |