9 papers
How many integrals should be evaluated at least in two-dimensional hyperinterpolation?
Maolin Che, Congpei An, Yimin Wei +1
This paper introduces a novel approach to approximating continuous functions over high-dimensional hypercubes by integrating matrix CUR decomposition with hyperinterpolation techni…
Agentic Recommender System with Hierarchical Belief-State Memory
Xiang Shen, Yuhang Zhou, Yifan Wu +8
Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with st…
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…