cs.AI（2026-01-02）

📊 共 6 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	A Vision-and-Knowledge Enhanced Large Language Model for Generalizable Pedestrian Crossing Behavior Inference	提出PedX-LLM，通过视觉知识增强LLM，提升行人过马路行为推断的泛化性。	large language model foundation model
2	QSLM: A Performance- and Memory-aware Quantization Framework with Tiered Search Strategy for Spike-driven Language Models	QSLM：面向Spike驱动语言模型的性能与内存感知分层搜索量化框架	large language model
3	Improving Scientific Document Retrieval with Academic Concept Index	提出学术概念索引，提升科学文档检索的查询生成和上下文增强效果	large language model
4	Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?	评估LLM在物联网安全漏洞检测中的能力，揭示其在结构推理方面的局限性。	large language model

#	题目	一句话要点	标签	🔗	⭐
5	DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations	DA-DPO：通过难度感知偏好优化降低多模态大语言模型的幻觉	DPO direct preference optimization large language model	✅
6	Parametrized Sharing for Multi-Agent Hybrid DRL for Multiple Multi-Functional RISs-Aided Downlink NOMA Networks	提出参数化共享多智能体混合DRL，解决多功能RIS辅助NOMA网络能效优化问题	reinforcement learning deep reinforcement learning DRL