cs.AI（2025-12-25）

📊 共 9 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	Enabling Ultra-Fast Cardiovascular Imaging Across Heterogeneous Clinical Environments with a Generalist Foundation Model and Multimodal Database	CardioMM：通用心血管磁共振重建基础模型，加速异构临床环境下的超快速成像	foundation model multimodal
2	A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning	提出基于LLaVA和逻辑树推理的医学多模态诊断框架，提升诊断准确性和可解释性。	large language model multimodal
3	LLM-I2I: Boost Your Small Item2Item Recommendation Model with Large Language Model	LLM-I2I：利用大语言模型提升小规模Item2Item推荐模型性能	large language model
4	Can We Trust AI Explanations? Evidence of Systematic Underreporting in Chain-of-Thought Reasoning	AI解释可信吗？思维链推理中存在系统性信息隐瞒现象	chain-of-thought
5	Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning	提出基于共识驱动推理的负责任且可解释的AI Agent架构	large language model
6	Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study	首个LLM指令级GPU软错误注入分析，揭示模型架构、规模和任务复杂度的影响	large language model
7	LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis	提出LogicLens，用于文本中心伪造分析的视觉-逻辑协同推理。	chain-of-thought

#	题目	一句话要点	标签	🔗	⭐
8	Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model	Leash：自适应长度惩罚与奖励塑造，提升大语言模型推理效率	reinforcement learning reward shaping instruction following
9	Selective LLM-Guided Regularization for Enhancing Recommendation Models	提出选择性LLM引导正则化以增强推荐模型	distillation large language model