paper-with-me

홈 › Papers

Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals

2020-10-26 · NeurIPS 2020 12 · Tongzhou Mu, Jiayuan Gu, Zhiwei Jia, Hao Tang, Hao Su

We study how to learn a policy with compositional generalizability. We propose a two-stage framework, which refactorizes a high-reward teacher policy into a generalizable student policy with strong inductive bias. Particularly, we implement an object-centric GNN-based student policy, whose input objects are learned from images through self-supervised learning. Empirically, we evaluate our approach on four difficult tasks that require compositional generalizability, and achieve superior performance compared to baselines.

📄 PDF Abstract BibTeX arXiv:2011.00971

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive BiasSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Contrastive Distillation Is a Sample-Efficient Self-Supervised Loss Policy for Transfer Learning

2022-12-21 · Chris Lengerich, Gabriel Synnaeve, Amy Zhang, Hugh Leather 외

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization. Whi…

Few-Shot LearningLanguage ModellingSelf-LearningTransfer Learning

Toward the Automatic Classification of Self-Affirmed Refactoring

2020-09-19 · Eman Abdullah AlOmar, Mohamed Wiem Mkaouer, Ali Ouni

The concept of Self-Affirmed Refactoring (SAR) was introduced to explore how developers document their refactoring activities in commit messages, i.e., developers' explicit documentation of refactoring operations intenti…

Classificationfeature selectionGeneral Classification

How We Refactor and How We Document it? On the Use of Supervised Machine Learning Algorithms to Classify Refactoring Documentation

2020-10-26 · Eman Abdullah AlOmar, Anthony Peruma, Mohamed Wiem Mkaouer, Christian Newman 외

Refactoring is the art of improving the design of a system without altering its external behavior. Refactoring has become a well established and disciplined software engineering practice that has attracted a significant …

RefAgent: A Multi-agent LLM-based Framework for Automatic Software Refactoring

2025-11-05 · Khouloud Oueslati, Maxime Lamothe, Foutse Khomh arxiv

Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs have shown the ability to reduce development time and enhance c…

DeCo: Decomposition and Reconstruction for Compositional Temporal Grounding via Coarse-To-Fine Contrastive Ranking

2023-01-01 · CVPR 2023 1 · Lijin Yang, Quan Kong, Hsuan-Kung Yang, Wadim Kehl 외

Understanding dense action in videos is a fundamental challenge towards the generalization of vision models. Several works show that compositionality is key to achieving generalization by combining known primitive el…

Boundary DetectionSentence