Search Results for author:
Found 9 papers, 2 papers with code
AutoCV: Empowering Reasoning with Automated Process Labeling via Confidence Variation
We experimentally validate that the confidence variations learned by the verification model trained on the final answer correctness can effectively identify errors in the reasoning steps.
The Future of Large Language Model Pre-training is Federated
Generative pre-trained large language models (LLMs) have demonstrated impressive performance over a wide range of tasks, thanks to the unprecedented amount of data they have been trained on.
EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation
We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation.
Corn Yield Prediction based on Remotely Sensed Variables Using Variational Autoencoder and Multiple Instance Regression
Only a few works have addressed the mixed pixels problem in large-scale crop yield prediction.
TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer
We further demonstrate the generalizability of our method on hand mesh recovery.
Vertical Federated Linear Contextual Bandits
In this paper, we investigate a novel problem of building contextual bandits in the vertical federated setting, i. e., contextual information is vertically distributed over different departments.
Physics-informed MTA-UNet: Prediction of Thermal Stress and Thermal Deformation of Satellites
The rapid analysis of thermal stress and deformation plays a pivotal role in the thermal control measures and optimization of the structural design of satellites.
Cross-View-Prediction: Exploring Contrastive Feature for Hyperspectral Image Classification
This paper presents a self-supervised feature learning method for hyperspectral image classification.
Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification
We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to design an unsupervised feature learning network for hyperspectral classification.
