7 citations · 19 across the 7 of their papers we have counts for
7 papers
Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks
Yi Yang, Xiaoke Chen, Jinyang Huang +6
Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few…
StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views
Jia-Chen Zhao, Beiqi Chen, Xinyang Chen +2
We present StructSplat, a feed-forward and generalizable 3D Gaussian reconstruction framework that operates directly on uncalibrated images without requiring camera parameters. Exi…
InRank: Incremental Low-Rank Learning
Jiawei Zhao, Yifei Zhang, Beidi Chen +2
The theory of greedy low-rank learning (GLRL) aims to explain the impressive generalization capabilities of deep learning. It proves that stochastic gradient-based training implici…
Incremental Spatial and Spectral Learning of Neural Operators for Solving Large-Scale PDEs
Robert Joseph George, Jiawei Zhao, Jean Kossaifi +2
Fourier Neural Operators (FNO) offer a principled approach to solving challenging partial differential equations (PDE) such as turbulent flows. At the core of FNO is a spectral lay…
A Knowledge Graph based Approach for Mobile Application Recommendation
Mingwei Zhang, Jiawei Zhao, Hai Dong +2
With the rapid prevalence of mobile devices and the dramatic proliferation of mobile applications (apps), app recommendation becomes an emergent task that would benefit both app us…
Is Depth Really Necessary for Salient Object Detection?
Jiawei Zhao, Yifan Zhao, Jia Li +1
Salient object detection (SOD) is a crucial and preliminary task for many computer vision applications, which have made progress with deep CNNs. Most of the existing methods mainly…
Learning compositional functions via multiplicative weight updates
Jeremy Bernstein, Jiawei Zhao, Markus Meister +3
Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems l…