133 citations · 182 across the 11 of their papers we have counts for
11 papers
Computron: Serving Distributed Deep Learning Models with Model Parallel Swapping
Daniel Zou, Xinchen Jin, Xueyang Yu +2
Many of the most performant deep learning models today in fields like language and image understanding are fine-tuned models that contain billions of parameters. In anticipation of…
Breaking the Curse of Quality Saturation with User-Centric Ranking
Zhuokai Zhao, Yang Yang, Wenyu Wang +5
A key puzzle in search, ads, and recommendation is that the ranking model can only utilize a small portion of the vastly available user interaction data. As a result, increasing da…
NoisywikiHow: A Benchmark for Learning with Real-world Noisy Labels in Natural Language Processing
Tingting Wu, Xiao Ding, Minji Tang +3
Large-scale datasets in the real world inevitably involve label noise. Deep models can gradually overfit noisy labels and thus degrade model generalization. To mitigate the effects…
Deep Masked Graph Matching for Correspondence Identification in Collaborative Perception
Peng Gao, Qingzhao Zhu, Hongsheng Lu +2
Correspondence identification (CoID) is an essential component for collaborative perception in multi-robot systems, such as connected autonomous vehicles. The goal of CoID is to id…
UKP-SQuARE v3: A Platform for Multi-Agent QA Research
Haritz Puerto, Tim Baumgärtner, Rachneet Sachdeva +5
The continuous development of Question Answering (QA) datasets has drawn the research community's attention toward multi-domain models. A popular approach is to use multi-dataset m…
Innovative Drug-like Molecule Generation from Flow-based Generative Model
Haotian Zhang, Linxiaoyi Wan
To design a drug given a biological molecule by using deep learning methods, there are many successful models published recently. People commonly used generative models to design n…
Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
Daniel Y. Fu, Will Crichton, James Hong +7
Many real-world video analysis applications require the ability to identify domain-specific events in video, such as interviews and commercials in TV news broadcasts, or action seq…
Simple Applications of BERT for Ad Hoc Document Retrieval
Wei Yang, Haotian Zhang, Jimmy Lin
Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval. This required confronting the challenge posed by doc…
Evaluating Sentence-Level Relevance Feedback for High-Recall Information Retrieval
Haotian Zhang, Gordon V. Cormack, Maura R. Grossman +1
This study uses a novel simulation framework to evaluate whether the time and effort necessary to achieve high recall using active learning is reduced by presenting the reviewer wi…
Exploring the Effectiveness of Convolutional Neural Networks for Answer Selection in End-to-End Question Answering
Royal Sequiera, Gaurav Baruah, Zhucheng Tu +4
Most work on natural language question answering today focuses on answer selection: given a candidate list of sentences, determine which contains the answer. Although important, an…
Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams
Jinfeng Rao, Hua He, Haotian Zhang +4
Time is an important relevance signal when searching streams of social media posts. The distribution of document timestamps from the results of an initial query can be leveraged to…