128 citations · 724 across the 72 of their papers we have counts for
7 papers · 1 filter
Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection
Yucheng Suo, Fan Ma, Kaixin Shen +2
Visual instructions for long-horizon tasks are crucial as they intuitively clarify complex concepts and enhance retention across extended steps. Directly generating a series of ima…
Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
Xihang Yue, Yi Yang, Linchao Zhu
Recent advances in operator learning have produced two distinct approaches for solving partial differential equations (PDEs): attention-based methods offering point-level adaptabil…
DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
Xihang Yue, Yi Yang, Linchao Zhu
The limited availability of high-quality training data poses a major obstacle in data-driven PDE solving, where expensive data collection and resolution constraints severely impact…
Discriminative Radial Domain Adaptation
Zenan Huang, Jun Wen, Siheng Chen +2
Domain adaptation methods reduce domain shift typically by learning domain-invariant features. Most existing methods are built on distribution matching, e.g., adversarial domain ad…
OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation
Qianyu Feng, Linchao Zhu, Bang Zhang +2
Contemporary data-driven methods are typically fed with full supervision on large-scale datasets which limits their applicability. However, in the actual systems with limitations s…
Faster Meta Update Strategy for Noise-Robust Deep Learning
Youjiang Xu, Linchao Zhu, Lu Jiang +1
It has been shown that deep neural networks are prone to overfitting on biased training data. Towards addressing this issue, meta-learning employs a meta model for correcting the t…
Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
Linchao Zhu, Sercan O. Arik, Yi Yang +1
We propose a novel adaptive transfer learning framework, learning to transfer learn (L2TL), to improve performance on a target dataset by careful extraction of the related informat…