6 papers
Intrinsic Low-Tucker-Rank Theory and Unified Tensor CUR Decomposition for High-Dimensional Hyperinterpolation
Maolin Che, Yimin Wei, Chong Wu
High-dimensional hyperinterpolation is severely hampered by the curse of dimensionality, as its coefficient tensors grow exponentially with the ambient dimension. Existing research…
BFLA: Block-Filtered Long-Context Attention Mechanism
Chong Wu, Zhenan Feng, Renjie Xu +5
This paper proposes Block-Filtered Long-Context Attention (BFLA), a training-free sparse prefill attention mechanism for long-context inference. BFLA adopts a two-stage design. In…
UniFormer: Unified and Efficient Transformer for Reasoning Across General and Custom Computing
Zhuoheng Ran, Chong Wu, Renjie Xu +2
The success of neural networks such as convolutional neural networks (CNNs) has been largely attributed to their effective and widespread deployment on customised computing platfor…
ELFATT: Efficient Linear Fast Attention for Vision Transformers
Chong Wu, Maolin Che, Renjie Xu +2
The attention mechanism is the key to the success of transformers in different machine learning tasks. However, the quadratic complexity with respect to the sequence length of the…
sparseGeoHOPCA: A Geometric Solution to Sparse Higher-Order PCA Without Covariance Estimation
Renjie Xu, Chong Wu, Maolin Che +3
We propose sparseGeoHOPCA, a novel framework for sparse higher-order principal component analysis (SHOPCA) that introduces a geometric perspective to high-dimensional tensor decomp…
Efficient randomized algorithms for the fixed Tucker-rank problem of Tucker decomposition with adaptive shifts
Maolin Che, Yimin Wei, Chong Wu +1
Randomized numerical linear algebra is proved to bridge theoretical advancements to offer scalable solutions for approximating tensor decomposition. This paper introduces fast rand…