Search Results for author:
Found 10 papers, 5 papers with code
Optimal Matrix Sketching over Sliding Windows
Matrix sketching, aimed at approximating a matrix $\boldsymbol{A} \in \mathbb{R}^{N\times d}$ consisting of vector streams of length $N$ with a smaller sketching matrix $\boldsymbol{B} \in \mathbb{R}^{\ell\times d}, \ell \ll N$, has garnered increasing attention in fields such as large-scale data analytics and machine learning.
Mozart's Touch: A Lightweight Multi-modal Music Generation Framework Based on Pre-Trained Large Models
In recent years, AI-Generated Content (AIGC) has witnessed rapid advancements, facilitating the generation of music, images, and other forms of artistic expression across various industries.
RecDiffusion: Rectangling for Image Stitching with Diffusion Models
Image stitching from different captures often results in non-rectangular boundaries, which is often considered unappealing.
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions.
PathSAGE: Spatial Graph Attention Neural Networks With Random Path Sampling
To address these problems, we propose a model called PathSAGE, which can learn high-order topological information and improve the model's performance by expanding the receptive field.
Integrating Dependency Tree Into Self-attention for Sentence Representation
Recent progress on parse tree encoder for sentence representation learning is notable.
Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations
Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data.
POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems
We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs).
Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising
To achieve this, we utilize sequence-to-sequence prediction for user clicks, and combine both post-view and post-click attribution patterns together for the final conversion estimation.
Personalizing a Dialogue System with Transfer Reinforcement Learning
One way to solve this problem is to consider a collection of multiple users' data as a source domain and an individual user's data as a target domain, and to perform a transfer learning from the source to the target domain.
