Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning

no code implementations • 19 Sep 2024 • Peichao Lai, Zhengfeng Zhang, Wentao Zhang, Fangcheng Fu, Bin Cui

Recently, using large language models (LLMs) for data augmentation has led to considerable improvements in unsupervised sentence embedding models.

Contrastive Learning Data Augmentation +7

Hard instance learning for quantum adiabatic prime factorization

no code implementations • 10 Oct 2021 • Jian Lin, Zhengfeng Zhang, Junping Zhang, Xiaopeng Li

Prime factorization is a difficult problem with classical computing, whose exponential hardness is the foundation of Rivest-Shamir-Adleman (RSA) cryptography.

Deep Reinforcement Learning Reinforcement Learning (RL) +1

Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration

no code implementations • 27 Sep 2021 • Zhaorun Chen, Binhao Chen, Shenghan Xie, Liang Gong, Chengliang Liu, Zhengfeng Zhang, Junping Zhang

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions.

Deep Reinforcement Learning MuJoCo +1