Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy
本文提出了一种基于条件3D校正流的框架，结合优化采样策略，有效解决了超低剂量全身PET成像中的噪声问题，同时保持了重建保真度和计算效率。
0 citationsRead paper
Selected work
Representative Papers
Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
Updating knowledge in large language models is costly, and existing retrieval-augmented approaches exhibit instability in long-context and multi-hop reasoning scenarios. This work proposes “Knowledge Capsules”—structured, non-parametric memory units—and introduces an external Key-Value Injection (KVI) framework that directly integrates external knowledge into the model’s attention mechanism rather than merely appending it as additional context. By elevating knowledge integration from the contextual level to the memory level, this approach enables efficient and stable knowledge injection while keeping the base model parameters frozen. Experimental results demonstrate that the method significantly outperforms both RAG and GraphRAG across multiple question-answering benchmarks, achieving notably higher accuracy and robustness, particularly in tasks involving long contexts and multi-hop reasoning.
0 citationsRead paper
Recent publications
Latest Papers
Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy
本文提出了一种基于条件3D校正流的框架，结合优化采样策略，有效解决了超低剂量全身PET成像中的噪声问题，同时保持了重建保真度和计算效率。
0 citationsRead paper
Knowledge Capsules: Structured Nonparametric Memory Units for LLMs
Updating knowledge in large language models is costly, and existing retrieval-augmented approaches exhibit instability in long-context and multi-hop reasoning scenarios. This work proposes “Knowledge Capsules”—structured, non-parametric memory units—and introduces an external Key-Value Injection (KVI) framework that directly integrates external knowledge into the model’s attention mechanism rather than merely appending it as additional context. By elevating knowledge integration from the contextual level to the memory level, this approach enables efficient and stable knowledge injection while keeping the base model parameters frozen. Experimental results demonstrate that the method significantly outperforms both RAG and GraphRAG across multiple question-answering benchmarks, achieving notably higher accuracy and robustness, particularly in tasks involving long contexts and multi-hop reasoning.
0 citationsRead paper