SliceWorld: A Predictive and Controllable World-State Model for CT Report Generation
cs.CV, cs.CL
Submitted: 2026-05-23
Updated: 2026-11-06
Code: https://github.com/synlp/SliceWorld
Terminology
Sources
- Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation
- World Models
- Mastering Diverse Domains through World Models
- M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models
- PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
- Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data
- DINOv2: Learning Robust Visual Features without Supervision
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Qwen3 Technical Report
- Ministral 3
- A Systematic Review of Deep Learning-based Research on Radiology Report Generation
- Scaling Self-Supervised and Cross-Modal Pretraining for Volumetric CT Transformers
- BERTScore: Evaluating Text Generation with BERT
- GREEN: Generative Radiology Report Evaluation and Error Notation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs