cs.AI（2024-08-16）

📊 共 7 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	A Disease-Specific Foundation Model Using Over 100K Fundus Images: Release and Validation for Abnormality and Multi-Disease Classification on Downstream Tasks	提出眼底特异性预训练模型，提升眼科疾病诊断与异常检测性能	foundation model
2	Trust-Oriented Adaptive Guardrails for Large Language Models	提出面向信任的自适应Guardrail机制，提升LLM在不同用户群体的伦理安全性。	large language model
3	LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression	提出基于大语言模型（LLM）的点云几何压缩方法LLM-PCGC，显著提升压缩性能。	large language model
4	DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts	提出DePrompt框架，用于大语言模型提示词的PII脱敏与有效性评估。	large language model
5	Navigating the sociotechnical labyrinth: Dynamic certification for responsible embodied AI	提出动态认证框架，应对具身AI系统快速发展带来的监管挑战	embodied AI

#	题目	一句话要点	标签	🔗	⭐
6	Detecting Misinformation in Multimedia Content through Cross-Modal Entity Consistency: A Dual Learning Approach	提出MultiMD框架，利用跨模态实体一致性检测多媒体内容中的虚假信息，并采用双重学习提升性能。	representation learning multimodal
7	Evaluating the Evaluator: Measuring LLMs' Adherence to Task Evaluation Instructions	评估评估者：衡量LLM作为评估者对任务评估指令的遵循程度	reinforcement learning RLHF