4 papers
Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
Lianlei Shan, Han Chen, Yixuan Wang +2
While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains o…
Organizing Background to Explore Latent Classes for Incremental Few-shot Semantic Segmentation
Lianlei Shan, Wenzhang Zhou, Wei Li +1
The goal of incremental Few-shot Semantic Segmentation (iFSS) is to extend pre-trained segmentation models to new classes via few annotated images without access to old training da…
Lifelong Learning and Selective Forgetting via Contrastive Strategy
Lianlei Shan, Wenzhang Zhou, Wei Li +1
Lifelong learning aims to train a model with good performance for new tasks while retaining the capacity of previous tasks. However, some practical scenarios require the system to…
The Binary Quantized Neural Network for Dense Prediction via Specially Designed Upsampling and Attention
Xingyu Ding, Lianlei Shan, Guiqin Zhao +3
Deep learning-based information processing consumes long time and requires huge computing resources, especially for dense prediction tasks which require an output for each pixel, l…