1k citations
- Stanford UniversityUS33 papers
- Google (United States)US32 papers
- University of Illinois Urbana-ChampaignUS32 papers
- University of California, BerkeleyUS29 papers
- Massachusetts Institute of TechnologyUS28 papers
- Carnegie Mellon UniversityUS26 papers
- University of California San DiegoUS25 papers
- University College LondonGB22 papers
- Georgia Institute of TechnologyUS21 papers
- University of Maryland, College ParkUS21 papers
- University of MichiganUS18 papers
- University of Southern CaliforniaUS16 papers
125 papers · 1 filter
Get It Scored Using AutoSAS -- An Automated System for Scoring Short Answers
Yaman Kumar, Swati Aggarwal, Debanjan Mahata +3
In the era of MOOCs, online exams are taken by millions of candidates, where scoring short answers is an integral part. It becomes intractable to evaluate them by human graders. Th…
Continuous Curve Textures
Peihan Tu, Li-Yi Wei, Koji Yatani +2
Repetitive patterns are ubiquitous in natural and human-made objects, and can be created with a variety of tools and methods. Manual authoring provides unmatched degree of freedom…
Budgeted and Non-budgeted Causal Bandits
Vineet Nair, Vishakha Patil, Gaurav Sinha
Learning good interventions in a causal graph can be modelled as a stochastic multi-armed bandit problem with side-information. First, we study this problem when interventions are…
On Shapley Credit Allocation for Interpretability
Debraj Basu
We emphasize the importance of asking the right question when interpreting the decisions of a learning model. We discuss a natural extension of the theoretical machinery from Janzi…
Split: Inferring Unobserved Event Probabilities for Disentangling Brand-Customer Interactions
Ayush Chauhan, Aditya Anand, Shaddy Garg +2
Often, data contains only composite events composed of multiple events, some observed and some unobserved. For example, search ad click is observed by a brand, whereas which custom…
Few-shot Image Generation with Elastic Weight Consolidation
Yijun Li, Richard Zhang, Jingwan Lu +1
Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. As it is unreasonable to expect to fully infer the distribution…