Search Results for author:
Found 3 papers, 2 papers with code
Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
Reinforcement Learning from Human Feedback (RLHF) is the prevailing approach to ensure Large Language Models (LLMs) align with human values.
Nearest Neighbor Classifier with Margin Penalty for Active Learning
As a result, informative samples in the margin area can not be discovered and AL performance are damaged.
Adaptive Graph Diffusion Networks
Until the date of submission (Aug 26, 2022), AGDNs achieve top-1 performance on the ogbn-arxiv, ogbn-proteins and ogbl-ddi datasets and top-3 performance on the ogbl-citation2 dataset.
Ranked #1 on
Link Property Prediction
on ogbl-citation2
Cannot find the paper you are looking for? You can
Submit a new open access paper.
