activity
20122023
most citedLinearized Alternating Direction Method with Adaptive Penalty and Warm Starts for Fast Solving Transform Invariant Low-Rank Textures

65 citations · 80 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL20221 cited

Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality

Pei Zhou, Hyundong Cho, Pegah Jandaghi +4

Human communication relies on common ground (CG), the mutual knowledge and beliefs shared by participants, to produce coherent and interesting conversations. In this paper, we demo…

cs.CL2022

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

Dong-Ho Lee, Akshen Kadakia, Brihi Joshi +8

NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging ai…

cs.CV20221 cited

Curriculum Learning for Data-Efficient Vision-Language Alignment

Tejas Srinivasan, Xiang Ren, Jesse Thomason

Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-train…

cs.CL202012 cited

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Peifeng Wang, Nanyun Peng, Filip Ilievski +2

Commonsense question answering (QA) requires background knowledge which is not explicitly stated in a given context. Prior works use commonsense knowledge graphs (KGs) to obtain th…

cs.IR20191 cited

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

Weizhi Ma, Min Zhang, Yue Cao +6

Explainability and effectiveness are two key aspects for building recommender systems. Prior efforts mostly focus on incorporating side information to achieve better recommendation…

cs.CV201265 cited

Linearized Alternating Direction Method with Adaptive Penalty and Warm Starts for Fast Solving Transform Invariant Low-Rank Textures

Xiang Ren, Zhouchen Lin

Transform Invariant Low-rank Textures (TILT) is a novel and powerful tool that can effectively rectify a rich class of low-rank textures in 3D scenes from 2D images despite signifi…