paper-conference

We introduce Syntax-Aware Fill-In-the-Middle (SAFIM), a new benchmark for evaluating Large Language Models (LLMs) on the code Fill-in-the-Middle (FIM) task.

We introduce AST-T5, a novel pretraining paradigm that leverages the Abstract Syntax Tree (AST) for enhanced code generation, transpilation, and understanding.

This paper explores the effectiveness of model-generated signals in improving zero-shot generalization of text-to-text Transformers such as T5.

We propose a transpiler across deep learning frameworks using LLM and adversarial learning techniques.

We train language models for knowledge graph completion tasks.

In this paper, we propose the new task of synthesizing visualization programs from a combination of natural language utterances and code context.

We propose a new family of autoregressive model that enables anytime sampling.

We propose two language model based approaches, including a novel length-agnostic permutation language model, find non-sense methods to be more effective than sense-based methods.

Technical report for WMT19 News Translation competition, where we won the first place for 8 of the 11 translation directions.

We explore an efficient training method for BERT models.