most citedPixMIM: Rethinking Pixel Reconstruction in Masked Image Modeling

13 citations · 26 across the 7 of their papers we have counts for

collaborators

7 papers

cs.IT20241 cited

Leveraging Self-Supervised Learning for MIMO-OFDM Channel Representation and Generation

Zongxi Liu, Jiacheng Chen, Yunting Xu +4

In communications theory, the capacity of multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems is fundamentally determined by wireless chan…

cs.NE2024

Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning

Zeyuan Ma, Jiacheng Chen, Hongshu Guo +2

Evolutionary computation (EC) algorithms, renowned as powerful black-box optimizers, leverage a group of individuals to cooperatively search for the optimum. The exploration-exploi…

cs.NE20242 cited

Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution

Hongshu Guo, Yining Ma, Zeyuan Ma +5

Evolutionary algorithms, such as Differential Evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across dif…

cs.LG20241 cited

Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning

Jiacheng Chen, Zeyuan Ma, Hongshu Guo +3

Recent Meta-learning for Black-Box Optimization (MetaBBO) methods harness neural networks to meta-learn configurations of traditional black-box optimizers. Despite their success, t…

cs.LG20235 cited

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning

Zeyuan Ma, Hongshu Guo, Jiacheng Chen +5

Recently, Meta-Black-Box Optimization with Reinforcement Learning (MetaBBO-RL) has showcased the power of leveraging RL at the meta-level to mitigate manual fine-tuning of low-leve…

cs.CV20234 cited

Improving Pixel-based MIM by Reducing Wasted Modeling Capability

Yuan Liu, Songyang Zhang, Jiacheng Chen +3

There has been significant progress in Masked Image Modeling (MIM). Existing MIM methods can be broadly categorized into two groups based on the reconstruction target: pixel-based…