1 code implementation • NeurIPS 2023 • Tuan Dinh, Jinman Zhao, Samson Tan, Renato Negrinho, Leonard Lausen, Sheng Zha, George Karypis
We find that the presence of potential bugs significantly degrades the generation performance of the high-performing Code-LLMs.
1 code implementation • Findings (EMNLP) 2021 • Longxiang Zhang, Renato Negrinho, Arindam Ghosh, Vasudevan Jagannathan, Hamid Reza Hassanzadeh, Thomas Schaaf, Matthew R. Gormley
We show that fluent and adequate summaries can be generated with limited training data by fine-tuning BART on a specially constructed dataset.
1 code implementation • 7 Sep 2021 • Manuel Madeira, Renato Negrinho, João Xavier, Pedro M. Q. Aguiar
First-order methods for stochastic optimization have undeniable relevance, in part due to their pivotal role in machine learning.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Renato Negrinho, Matthew R. Gormley, Geoffrey J. Gordon
This approach leads to mismatches as, during training, the model is not exposed to its mistakes and does not use beam search.
1 code implementation • 27 Dec 2019 • Lourenço V. Pato, Renato Negrinho, Pedro M. Q. Aguiar
In this setting, we use a bidirectional RNN with attention for contextual rescoring and introduce a training target that uses the IoU with ground truth to maximize AP for the given set of detections.
2 code implementations • NeurIPS 2019 • Renato Negrinho, Darshan Patil, Nghia Le, Daniel Ferreira, Matthew Gormley, Geoffrey Gordon
We release an implementation of our language with this paper.
1 code implementation • NeurIPS 2018 • Renato Negrinho, Matthew R. Gormley, Geoffrey J. Gordon
Beam search is widely used for approximate decoding in structured prediction problems.
1 code implementation • ICLR 2018 • Renato Negrinho, Geoff Gordon
In addition, these experiments show that our framework can be used effectively for model discovery, as it is possible to describe expressive search spaces and discover competitive models without much effort from the human expert.
no code implementations • NeurIPS 2014 • Renato Negrinho, Andre Martins
We propose a general framework for regularization based on group majorization.