cs.AI（2025-12-15）

📊 共 10 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery	提出MASTER框架，利用多智能体LLM加速自主功能材料发现	large language model multimodal
2	Revisiting the Reliability of Language Models in Instruction-Following	提出IFEval++评估LLM在指令跟随中对细微差别的可靠性，揭示现有模型不足。	instruction following	✅
3	CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs	CTIGuardian：一种用于缓解微调LLM中隐私泄露的少样本框架	large language model
4	EvoLattice: Persistent Internal-Population Evolution through Multi-Alternative Quality-Diversity Graph Representations for LLM-Guided Program Discovery	EvoLattice：通过多替代质量多样性图表示实现LLM引导的程序发现	large language model
5	neuralFOMO: Can LLMs Handle Being Second Best? Measuring Envy-Like Preferences in Multi-Agent Settings	探究LLM多智能体交互中的“羡慕”偏好，揭示竞争性倾向的设计与安全考量	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization	M-GRPO：通过动量锚定策略优化稳定大型语言模型的自监督强化学习	reinforcement learning large language model
7	SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning	SpeakRL：强化学习驱动语言模型，提升推理、对话与行动协同能力	reinforcement learning reward design
8	Differentiable Evolutionary Reinforcement Learning	提出可微进化强化学习(DERL)，自动发现复杂任务的最优奖励函数。	reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Cisco Integrated AI Security and Safety Framework Report	思科提出集成AI安全与安全框架，应对多维度AI风险	humanoid manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Towards Unified Co-Speech Gesture Generation via Hierarchical Implicit Periodicity Learning	提出基于分层隐式周期性学习的统一口语手势生成方法	VQ-VAE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页