cs.AI（2026-01-14）

📊 共 23 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#	题目	一句话要点	标签	🔗	⭐
1	AviationLMM: A Large Multimodal Foundation Model for Civil Aviation	提出AviationLMM：用于民航领域的多模态大模型，旨在统一异构数据流。	foundation model multimodal
2	Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning	Omni-R1：提出统一生成式多模态推理框架，通过生成中间图像实现多任务泛化。	large language model multimodal
3	Personalized Multimodal Feedback Using Multiple External Representations: Strategy Profiles and Learning in High School Physics	个性化多模态反馈提升高中物理学习效果：策略分析与表征能力影响	large language model multimodal
4	On-Device Large Language Models for Sequential Recommendation	提出OD-LLM，用于序列推荐任务中大语言模型在端侧的高效部署。	large language model
5	M$^3$Searcher: Modular Multimodal Information Seeking Agency with Retrieval-Oriented Reasoning	提出M$^3$Searcher：一种面向检索推理的模块化多模态信息搜索代理	multimodal
6	Coordinated Pandemic Control with Large Language Model Agents as Policymaking Assistants	提出基于大语言模型多智能体的疫情协同控制框架，提升决策效率。	large language model
7	DScheLLM: Enabling Dynamic Scheduling through a Fine-Tuned Dual-System Large language Model	DScheLLM：通过微调的双系统大语言模型实现动态调度	large language model
8	STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Models	提出STaR框架，用于大模型推理过程中敏感轨迹的擦除，保障隐私安全。	large language model chain-of-thought
9	Mikasa: A Character-Driven Emotional AI Companion Inspired by Japanese Oshi Culture	Mikasa：受日本Oshi文化启发的角色驱动型情感AI伴侣设计	large language model multimodal
10	Cluster Workload Allocation: Semantic Soft Affinity Using Natural Language Processing	提出基于自然语言处理的语义软亲和性集群工作负载分配方法	large language model
11	ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation	ShortCoder：通过知识增强的语法优化实现高效代码生成	large language model
12	Automating Supply Chain Disruption Monitoring via an Agentic AI Approach	提出基于Agentic AI的供应链中断监控框架，实现对多层供应商网络的自主风险评估与缓解。	large language model
13	What Do LLM Agents Know About Their World? Task2Quiz: A Paradigm for Studying Environment Understanding	提出Task2Quiz评估范式，用于研究LLM Agent的环境理解能力	large language model
14	Population-Aligned Audio Reproduction With LLM-Based Equalizers	提出基于LLM的音频均衡器，通过自然语言控制实现个性化音效调整	large language model
15	Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments	提出主动式任务导向Agent，解决动态环境中长期意图维护问题	large language model
16	MAXS: Meta-Adaptive Exploration with LLM Agents	提出MAXS框架，通过元自适应探索提升LLM Agent多工具推理的全局有效性和计算效率。	large language model	✅
17	The AI Hippocampus: How Far are We From Human Memory?	综述LLM与MLLM中的记忆机制，构建隐式、显式和Agent式记忆的统一分类体系。	large language model
18	Programming over Thinking: Efficient and Robust Multi-Constraint Planning	SCOPE：解耦推理与执行，高效解决多约束规划问题	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models	提出CoT-Flow，通过概率流推理提升大语言模型的推理效率和性能	reinforcement learning large language model chain-of-thought
20	Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning	提出MATTRL，一种用于多智能体推理的测试时强化学习框架。	reinforcement learning
21	Policy-Based Reinforcement Learning with Action Masking for Dynamic Job Shop Scheduling under Uncertainty: Handling Random Arrivals and Machine Failures	提出基于策略的强化学习框架以解决动态作业车间调度问题	reinforcement learning
22	RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering	提出RISER框架以解决复杂推理中的动态干预问题	reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy	系统性研究差分隐私加持的密码学协同学习，并提出统一框架。	MPC

⬅️ 返回 cs.AI 首页 · 🏠 返回主页