Zhengying Liu

Orcid: 0000-0001-6385-6082

According to our database1, Zhengying Liu authored at least 28 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data.
CoRR, 2024

2023
A Survey of Reasoning with Foundation Models.
CoRR, 2023

Large Language Models as Automated Aligners for benchmarking Vision-Language Models.
CoRR, 2023

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis.
CoRR, 2023

LEGO-Prover: Neural Theorem Proving with Growing Libraries.
CoRR, 2023

Lyra: Orchestrating Dual Correction in Automated Theorem Proving.
CoRR, 2023

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.
CoRR, 2023

FIMO: A Challenge Formal Dataset for Automated Theorem Proving.
CoRR, 2023

Forward-Backward Reasoning in Large Language Models for Verification.
CoRR, 2023

Progressive-Hint Prompting Improves Reasoning in Large Language Models.
CoRR, 2023

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models.
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022
Learning to Prove Trigonometric Identities.
CoRR, 2022

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification.
CoRR, 2022

Filtering participants improves generalization in competitions and benchmarks.
Proceedings of the 30th European Symposium on Artificial Neural Networks, 2022

2021
Automated Deep Learning : Principles and Practice. (Apprentissage profond automatisé : principes et pratique).
PhD thesis, 2021

Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019.
IEEE Trans. Pattern Anal. Mach. Intell., 2021

AgEBO-tabular: joint neural architecture and hyperparameter search with autotuned data-parallel training for tabular data.
Proceedings of the International Conference for High Performance Computing, 2021

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification.
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Asymptotic Analysis of Meta-learning as a Recommendation Problem.
Proceedings of the AAAI Workshop on Meta-Learning and MetaDL Challenge, 2021

Advances in MetaDL: AAAI 2021 Challenge and Workshop.
Proceedings of the AAAI Workshop on Meta-Learning and MetaDL Challenge, 2021

2020
Towards automated computer vision: analysis of the AutoCV challenges 2019.
Pattern Recognit. Lett., 2020

LEAP nets for system identification and application to power systems.
Neurocomputing, 2020

AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data.
CoRR, 2020

Deep Statistical Solvers.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019
Towards Automated Deep Learning: Analysis of the AutoDL challenge series 2019.
Proceedings of the NeurIPS 2019 Competition and Demonstration Track, 2019

LEAP nets for power grid perturbations.
Proceedings of the 27th European Symposium on Artificial Neural Networks, 2019

Analysis of the AutoML Challenge Series 2015-2018.
Proceedings of the Automated Machine Learning - Methods, Systems, Challenges, 2019


  Loading...