Zhongwang Zhang

Orcid: 0009-0006-4202-8556

According to our database1, Zhongwang Zhang authored at least 21 papers between 2020 and 2025.

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

2025
WebSailor: Navigating Super-human Reasoning for Web Agent.
CoRR, July, 2025

Scalable Complexity Control Facilitates Reasoning Ability of LLMs.
CoRR, May, 2025

An Analysis for Reasoning Bias of Language Models with Small Initialization.
CoRR, February, 2025

Reasoning Bias of Next Token Prediction Training.
CoRR, February, 2025

Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers.
CoRR, January, 2025

2024
Implicit Regularization of Dropout.
IEEE Trans. Pattern Anal. Mach. Intell., June, 2024

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization.
CoRR, 2024

Towards Understanding How Transformer Perform Multi-step Reasoning with Matching Operation.
CoRR, 2024

Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing.
CoRR, 2024

Loss Jump During Loss Switch in Solving PDEs with Neural Networks.
CoRR, 2024

Anchor function: a type of benchmark functions for studying language models.
CoRR, 2024

Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Stochastic Modified Equations and Dynamics of Dropout Algorithm.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Optimistic Estimate Uncovers the Potential of Nonlinear Models.
CoRR, 2023

Loss Spike in Training Neural Networks.
CoRR, 2023

2022
Linear Stability Hypothesis and Rank Stratification for Nonlinear Models.
CoRR, 2022

RETSR: An Effective Review-Enhanced and Time-Aware Sequential Recommendation Framework.
Proceedings of the 34th IEEE International Conference on Tools with Artificial Intelligence, 2022

2021
Embedding Principle: a hierarchical structure of loss landscape of deep neural networks.
CoRR, 2021

A variance principle explains why dropout finds flatter minima.
CoRR, 2021

Embedding Principle of Loss Landscape of Deep Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
A Distributed Reservation and Contention Combined TDMA Protocol for Wireless Avionics Intra-communication Networks.
Proceedings of the IoT as a Service - 6th EAI International Conference, 2020


  Loading...