Search Results for author:
Found 9 papers, 8 papers with code
Large Language Models of Code Fail at Completing Code with Potential Bugs
We find that the presence of potential bugs significantly degrades the generation performance of the high-performing Code-LLMs.
Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations
We show that fluent and adequate summaries can be generated with limited training data by fine-tuning BART on a specially constructed dataset.
COCO Denoiser: Using Co-Coercivity for Variance Reduction in Stochastic Convex Optimization
First-order methods for stochastic optimization have undeniable relevance, in part due to their pivotal role in machine learning.
An Empirical Investigation of Beam-Aware Training in Supertagging
This approach leads to mismatches as, during training, the model is not exposed to its mistakes and does not use beam search.
Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization
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.
Towards modular and programmable architecture search
We release an implementation of our language with this paper.
Learning Beam Search Policies via Imitation Learning
Beam search is widely used for approximate decoding in structured prediction problems.
DeepArchitect: Automatically Designing and Training Deep Architectures
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.
