cs.AI（2025-09-25）

📊 共 7 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices	NANOMIND：软硬件协同设计，提升电池供电小型设备上多模态推理效率	large language model multimodal
2	A Formal Comparison Between Chain-of-Thought and Latent Thought	形式化分析揭示思维链与潜在思维在计算效率与问题解决能力上的差异	large language model chain-of-thought	✅
3	Communication Bias in Large Language Models: A Regulatory Perspective	大型语言模型中的通信偏差风险分析与监管框架探讨	large language model
4	VC-Agent: An Interactive Agent for Customized Video Dataset Collection	VC-Agent：用于定制视频数据集收集的交互式智能体	large language model	✅
5	TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them	TrustJudge：提出概率框架，解决LLM评估中不一致性问题	large language model	✅
6	Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems	揭示推理过程对多智能体系统中说服力的影响，提出“说服二元性”概念	large language model

#	题目	一句话要点	标签	🔗	⭐
7	Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns	通过学习多样化思维链模式，提升基础模型推理潜力	reinforcement learning foundation model chain-of-thought