most citedWhat Makes Multi-modal Learning Better than Single (Provably)

43 citations · 52 across the 6 of their papers we have counts for

collaborators

8 papers

cs.LG20225 cited

Label Encoding for Regression Networks

Deval Shah, Zi Yu Xue, Tor M. Aamodt

Deep neural networks are used for a wide range of regression problems. However, there exists a significant gap in accuracy between specialized approaches and generic direct regress…

cs.CV2022

Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularization

Zhengqi Gao, Sucheng Ren, Zihui Xue +2

Multimodal fusion emerges as an appealing technique to improve model performances on many tasks. Nevertheless, the robustness of such fusion methods is rarely involved in the prese…

cs.LG20221 cited

SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning

Zihui Xue, Yuedong Yang, Mengtian Yang +1

Graph Neural Networks (GNNs) have demonstrated a great potential in a variety of graph-based applications, such as recommender systems, drug discovery, and object recognition. Neve…

cs.AR20211 cited

Characterizing and Improving the Resilience of Accelerators in Autonomous Robots

Deval Shah, Zi Yu Xue, Karthik Pattabiraman +1

Motion planning is a computationally intensive and well-studied problem in autonomous robots. However, motion planning hardware accelerators (MPA) must be soft-error resilient for…

cs.CV20212 cited

Co-advise: Cross Inductive Bias Distillation

Sucheng Ren, Zhengqi Gao, Tianyu Hua +4

Transformers recently are adapted from the community of natural language processing as a promising substitute of convolution-based neural networks for visual learning tasks. Howeve…

cs.LG202143 cited

What Makes Multi-modal Learning Better than Single (Provably)

Yu Huang, Chenzhuang Du, Zihui Xue +3

The world provides us with data of multiple modalities. Intuitively, models fusing data from different modalities outperform their uni-modal counterparts, since more information is…