Search Results for author:
Found 7 papers, 3 papers with code
StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation
Furthermore, although many prompt-based methods have been proposed to accomplish specific tasks, their performance in complex real-world scenarios involving a wide variety of dialog styles further enhancement.
PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion
The growing dependence on Large Language Models (LLMs) for finishing user instructions necessitates a comprehensive understanding of their robustness to complex task completion in real-world situations.
StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis
To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes.
Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics
We empirically evaluate the effectiveness of our compression technique on matrix recovery problems.
PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion
Recent evaluations of Large Language Models (LLMs) have centered around testing their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translate instructions into tool APIs.
ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution
Adapting the Diffusion Probabilistic Model (DPM) for direct image super-resolution is wasteful, given that a simple Convolutional Neural Network (CNN) can recover the main low-frequency content.
LeaF: Learning Frames for 4D Point Cloud Sequence Understanding
With such frames, we can factorize geometry and motion to facilitate a feature-space geometric reconstruction for more effective 4D learning.
