Guanzhe Hong

According to our database, Guanzhe Hong authored at least 8 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

D²-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing.

Aoxi Liu, Yupeng Chen, James Oldfield, Guanzhe Hong, Junchi Yu, Baoyuan Wu, Philip Torr, Adel Bibi

CoRR, May, 2026

2025

Latent Concept Disentanglement in Transformer-based Language Models.

Guanzhe Hong, Bhavya Vasudeva, Vatsal Sharan, Cyrus Rashtchian, Prabhakar Raghavan, Rina Panigrahy

CoRR, June, 2025

2024

Why Fine-grained Labels in Pretraining Benefit Generalization?

Guanzhe Hong, Yin Cui, Ariel Fuxman, Stanley H. Chan, Enming Luo

Trans. Mach. Learn. Res., 2024

How Transformers Solve Propositional Logic Problems: A Mechanistic Analysis.

Guanzhe Hong, Nishanth Dikkala, Enming Luo, Cyrus Rashtchian, Xin Wang, Rina Panigrahy

CoRR, 2024

Why Fine-grained Labels in Pretraining Benefit Generalization?

Guanzhe Hong, Yin Cui, Ariel Fuxman, Stanely Chan, Enming Luo

CoRR, 2024

2023

Towards Understanding the Effect of Pretraining Label Granularity.

Guanzhe Hong, Yin Cui, Ariel Fuxman, Stanley H. Chan, Enming Luo

CoRR, 2023

2021

Student-Teacher Learning From Clean Inputs to Noisy Inputs.

Guanzhe Hong, Zhiyuan Mao, Xiaojun Lin, Stanley H. Chan

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

2019

Rethinking Atmospheric Turbulence Mitigation.

Nicholas Chimitt, Zhiyuan Mao, Guanzhe Hong, Stanley H. Chan

CoRR, 2019