Selected work

Representative Papers

Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study

Oct 07, 2026

This study addresses the risk of erroneous AI recommendations misleading junior physicians in AI-assisted diagnosis by conducting a prospective, multicenter randomized controlled trial comparing dual-model versus single-model AI support for radiographic interpretation. Utilizing the multimodal large language models GPT-5.4, Kimi-K2.6, and Gemini-3.6 Flash, this work provides the first quantitative evaluation of the error-correction capability inherent in a dual-model cross-validation mechanism, with statistical analyses performed using Welch’s ANOVA and HC3 robust linear regression. Results demonstrate that dual-recommendation support significantly mitigates the misleading influence of incorrect AI outputs, improving diagnostic accuracy among radiologists by approximately seven percentage points. Conversely, non-radiologists derived no significant benefit, revealing a pronounced interaction effect driven by specialty background.

0 citationsRead paper

Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy

Sep 15, 2026

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

Apr 22, 2026

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

Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader Study

Oct 07, 2026

This study addresses the risk of erroneous AI recommendations misleading junior physicians in AI-assisted diagnosis by conducting a prospective, multicenter randomized controlled trial comparing dual-model versus single-model AI support for radiographic interpretation. Utilizing the multimodal large language models GPT-5.4, Kimi-K2.6, and Gemini-3.6 Flash, this work provides the first quantitative evaluation of the error-correction capability inherent in a dual-model cross-validation mechanism, with statistical analyses performed using Welch’s ANOVA and HC3 robust linear regression. Results demonstrate that dual-recommendation support significantly mitigates the misleading influence of incorrect AI outputs, improving diagnostic accuracy among radiologists by approximately seven percentage points. Conversely, non-radiologists derived no significant benefit, revealing a pronounced interaction effect driven by specialty background.

0 citationsRead paper

Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy

Sep 15, 2026

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

Apr 22, 2026

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