1 citations · 2 across the 5 of their papers we have counts for
6 papers
Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss
Yi Ren, Wenlong Deng, Guanzhe Hong +2
Modern language models are likely to be updated throughout their lifetime rather than trained once and frozen. Each update therefore participates in a recurring cycle: decide which…
Are Human-Aligned Models Models of Humans? A Turing-Test Gap in Preference Alignment
Suqin Yuan, Runqi Lin, Muyang Li +5
Human-feedback alignment has made language models useful assistants and is commonly described as aligning them with humans. However, the responses people prefer from an AI need not…
Why Fine-grained Labels in Pretraining Benefit Generalization?
Guan Zhe Hong, Yin Cui, Ariel Fuxman +2
Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better…
Towards Understanding the Effect of Pretraining Label Granularity
Guan Zhe Hong, Yin Cui, Ariel Fuxman +2
In this paper, we study how the granularity of pretraining labels affects the generalization of deep neural networks in image classification tasks. We focus on the "fine-to-coarse"…
Student-Teacher Learning from Clean Inputs to Noisy Inputs
Guanzhe Hong, Zhiyuan Mao, Xiaojun Lin +1
Feature-based student-teacher learning, a training method that encourages the student's hidden features to mimic those of the teacher network, is empirically successful in transfer…
Rethinking Atmospheric Turbulence Mitigation
Nicholas Chimitt, Zhiyuan Mao, Guanzhe Hong +1
State-of-the-art atmospheric turbulence image restoration methods utilize standard image processing tools such as optical flow, lucky region and blind deconvolution to restore the…