ProSG: Using Prompt Synthetic Gradients to Alleviate Prompt Forgetting of RNN-like Language Models

no code implementations • 3 Nov 2023 • Haotian Luo, Kunming Wu, Cheng Dai, Sixian Ding, Xinhao Chen

RNN-like language models are getting renewed attention from NLP researchers in recent years and several models have made significant progress, which demonstrates performance comparable to traditional transformers.

Language Modelling

Unlocking Low-Light-Rainy Image Restoration by Pairwise Degradation Feature Vector Guidance

no code implementations • 6 May 2023 • Xin Lin, Jingtong Yue, Sixian Ding, Chao Ren, Chun-Le Guo, Chongyi Li

P-Net can learn degradation feature vectors on the dark and light areas separately, using contrastive learning to guide the image restoration process.

Autonomous Driving Contrastive Learning +2