16 citations · 16 across the 4 of their papers we have counts for
5 papers
Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta +5
Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inhe…
Exploring and Improving Drafts in Blockwise Parallel Decoding
Taehyeon Kim, Ananda Theertha Suresh, Kishore Papineni +3
Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Block…
Balancing Robustness and Sensitivity using Feature Contrastive Learning
Seungyeon Kim, Daniel Glasner, Srikumar Ramalingam +3
It is generally believed that robust training of extremely large networks is critical to their success in real-world applications. However, when taken to the extreme, methods that…
Text Segmentation by Cross Segment Attention
Michal Lukasik, Boris Dadachev, Gonçalo Simões +1
Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as informa…
Bidding for Representative Allocations for Display Advertising
Arpita Ghosh, Preston McAfee, Kishore Papineni +1
Display advertising has traditionally been sold via guaranteed contracts -- a guaranteed contract is a deal between a publisher and an advertiser to allocate a certain number of im…