相关论文: Unity is Strength: Cross-Task Knowledge Distillati…

Grounded text generation, encompassing tasks such as long-form question-answering and summarization, necessitates both content selection and content consolidation. Current end-to-end methods are difficult to control and interpret due to…

Automated code review comment generation (RCG) aims to assist developers by automatically producing natural language feedback for code changes. Existing approaches are primarily either generation-based, using pretrained language models, or…

The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks…

Code generation plays a crucial role in various tasks, such as code auto-completion and mathematical reasoning. Previous work has proposed numerous methods to enhance code generation performance, including integrating feedback from the…

State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks, such as revising source code to address code reviews, hindering their practical…

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook…

Code generation aims to automatically generate a piece of code given an input natural language utterance. Currently, among dominant models, it is treated as a sequence-to-tree task, where a decoder outputs a sequence of actions…

Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks. However, a significant challenge nowadays is maintaining performance when we use a lightweight model with limited…

Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical…

Document interpretation and dialog understanding are the two major challenges for conversational machine reading. In this work, we propose Discern, a discourse-aware entailment reasoning network to strengthen the connection and enhance the…

Visual perception entails solving a wide set of tasks, e.g., object detection, depth estimation, etc. The predictions made for multiple tasks from the same image are not independent, and therefore, are expected to be consistent. We propose…

Reinforcement Learning (RL) has emerged as a popular training paradigm, particularly when paired with reasoning models. While effective, it primarily focuses on generating responses and lacks mechanisms to explicitly foster critique or…

Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses. We first build a…

Automatically generating concise, informative comments for source code can lighten documentation effort and accelerate program comprehension. Retrieval-augmented approaches first fetch code snippets with existing comments and then…

Code review is an important practice in software development, yet it is time-consuming and requires substantial effort. While open-source datasets have been used to train neural models for automating code review tasks, including review…

Background: Modern Code Review (MCR) is a key component for delivering high-quality software and sharing knowledge among developers. Effective reviews require an in-depth understanding of the code and demand from the reviewers to…

Binary code analysis and comprehension is critical to applications in reverse engineering and computer security tasks where source code is not available. Unfortunately, unlike source code, binary code lacks semantics and is more difficult…

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

Code review is a practice widely adopted in open source and industrial projects. Given the non-negligible cost of such a process, researchers started investigating the possibility of automating specific code review tasks. We recently…

With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has emerged as an important research direction. However, a…