1 code implementation • 27 Feb 2024 • Roy Xie, Chengxuan Huang, Junlin Wang, Bhuwan Dhingra
Large language models (LLMs) have significantly transformed the educational landscape.
no code implementations • 14 Jun 2023 • Margarita Geleta, Jiacen Xu, Manikanta Loya, Junlin Wang, Sameer Singh, Zhou Li, Sergio Gago-Masague
We assessed Maestro's influence on students' engagement, motivation, and learning success in robust AI.
1 code implementation • 8 May 2023 • Phillip Howard, Junlin Wang, Vasudev Lal, Gadi Singer, Yejin Choi, Swabha Swayamdipta
We introduce NeuroComparatives, a novel framework for comparative knowledge distillation overgenerated from language models such as GPT-variants and LLaMA, followed by stringent filtering of the generated knowledge.
no code implementations • 9 Dec 2022 • Huiling Zhang, Junlin Wang, Zi Xu, Yu-Hong Dai
$\mathcal{O}\left( \varepsilon ^{-4} \right)$) under nonconvex-strongly concave (resp.
no code implementations • 1 Oct 2022 • Hongwei Wu, Junlin Wang, Xin Wang, Hui Nan, Yaxin Wang, Haonan Jing, Kaixuan Shi
It is a challenge to segment the location and size of rectal cancer tumours through deep learning.
1 code implementation • 19 Jan 2022 • Junchen Zhao, Yurun Song, Junlin Wang, Ian G. Harris
In this work, we propose GAP-Gen, a Guided Automatic Python Code Generation method based on Python syntactic constraints and semantic constraints.
Ranked #2 on Code Generation on CodeXGLUE - CodeSearchNet (using extra training data)
no code implementations • Findings of the Association for Computational Linguistics 2020 • Junlin Wang, Jens Tuyls, Eric Wallace, Sameer Singh
Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, their faithfulness.
1 code implementation • IJCNLP 2019 • Eric Wallace, Jens Tuyls, Junlin Wang, Sanjay Subramanian, Matt Gardner, Sameer Singh
Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior.