cs.AI（2025-02-27）

📊 共 25 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy	Optimus-2：提出基于目标-观察-动作条件策略的多模态Minecraft智能体	large language model multimodal	✅
2	LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis	提出基于token间时间间隔和网络流量分析的LLM指纹识别方法，提升模型安全与可信度。	large language model
3	Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models	Meta-Reasoner：动态引导大语言模型优化推理时推理	large language model
4	ACE, Action and Control via Explanations: A Proposal for LLMs to Provide Human-Centered Explainability for Multimodal AI Assistants	提出ACE框架，利用LLM解释实现人机协作，提升多模态AI助手在制造业中的性能	multimodal
5	LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory	提出基于行为博弈论的LLM战略推理评估框架，揭示模型决策机制与偏见。	large language model chain-of-thought
6	An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs	评估LLM在PDDL理解与生成中的能力，揭示其在自动规划任务中的潜力和局限	large language model chain-of-thought
7	Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts	COMET：面向混合专家模型，实现细粒度计算-通信重叠优化。	large language model
8	Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers	提出多Agent验证（MAV），通过扩展验证器数量提升LLM测试时性能。	large language model
9	EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants	提出EAIRA方法，用于全面评估AI模型作为科研助手的能力	large language model
10	Evaluating Human Trust in LLM-Based Planners: A Preliminary Study	初步研究：评估人类对基于LLM规划器的信任度	large language model
11	AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions	研究浪漫AI伴侣中的隐性偏见，揭示性别化角色对LLM响应的刻板影响	large language model
12	Will AI replace Software Engineers? Do not hold your breath	AI能否取代软件工程师？短期内不会，软件维护能力是关键壁垒	large language model
13	Societal Alignment Frameworks Can Improve LLM Alignment	引入社会对齐框架以提升大型语言模型的对齐效果	large language model
14	DiffCSS: Diverse and Expressive Conversational Speech Synthesis with Diffusion Models	DiffCSS：利用扩散模型实现多样且富有表现力的对话语音合成	multimodal
15	LLM-driven Effective Knowledge Tracing by Integrating Dual-channel Difficulty	提出DDKT框架，利用LLM和RAG提升知识追踪的准确性和可解释性。	large language model
16	ConvCodeWorld: Benchmarking Conversational Code Generation in Reproducible Feedback Environments	提出CONVCODEWORLD以解决多轮交互代码生成评估问题	large language model	✅
17	HALO: Hardware-aware quantization with low critical-path-delay weights for LLM acceleration	HALO：一种硬件感知的低关键路径延迟权重量化方法，用于加速LLM推理。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
18	SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning	提出SuPreME框架，利用监督预训练提升多模态心电图表征学习，实现零样本分类。	representation learning large language model multimodal
19	Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning	提出基于指数拓扑的ExpoComm通信协议，解决大规模MARL中的可扩展通信问题。	reinforcement learning zero-shot transfer	✅
20	AutoBS: Autonomous Base Station Deployment with Reinforcement Learning and Digital Network Twins	AutoBS：基于强化学习和数字网络孪生的基站自主部署	reinforcement learning PPO
21	SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning	提出SoRFT，通过子任务强化微调提升LLM的问题解决能力	reinforcement learning PPO chain-of-thought
22	Developmental Support Approach to AI's Autonomous Growth: Toward the Realization of a Mutually Beneficial Stage Through Experiential Learning	提出AI发展支持方法，通过经验学习实现AI伦理道德的自主增长。	DPO direct preference optimization large language model
23	Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models	揭示小型语言模型越狱攻击的安全威胁，填补安全研究空白。	distillation large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
24	DeePen: Penetration Testing for Audio Deepfake Detection	提出DeePen：一种针对音频深度伪造检测模型的渗透测试方法	manipulation penetration
25	Personas Evolved: Designing Ethical LLM-Based Conversational Agent Personalities	设计伦理的LLM对话Agent人格：弥合CUI与AI社区的差距	manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页