cs.AI（2024-06-06）

📊 共 13 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) (9 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 POEM: Interactive Prompt Optimization for Enhancing Multimodal Reasoning of Large Language Models POEM：交互式提示优化系统，增强大语言模型的多模态推理能力 large language model multimodal
2 AgentGym: Evolving Large Language Model-based Agents across Diverse Environments AgentGym：构建基于大语言模型、可在多样环境中自我进化的通用智能体 generalist agent large language model ✅
3 Stock Movement Prediction with Multimodal Stable Fusion via Gated Cross-Attention Mechanism 提出MSGCA模型，通过门控交叉注意力机制实现多模态稳定融合，提升股票走势预测精度。 multimodal
4 VHDL-Eval: A Framework for Evaluating Large Language Models in VHDL Code Generation VHDL-Eval：构建VHDL代码生成LLM评估框架，揭示现有模型的局限性。 large language model
5 GenAI Arena: An Open Evaluation Platform for Generative Models GenAI Arena：一个用于生成模型开放评估的平台，通过用户反馈提升评估质量。 multimodal instruction following
6 Tool-Planner: Task Planning with Clusters across Multiple Tools Tool-Planner：基于工具簇的任务规划框架，提升LLM工具学习的稳定性和效率 large language model ✅
7 On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing 研究代码库编辑中上下文检索的推理重要性，解耦并分析其性能瓶颈。 large language model ✅
8 ActionReasoningBench: Reasoning about Actions with and without Ramification Constraints 提出ActionReasoningBench基准，评估LLM在具身智能和常识推理中的行动推理能力。 large language model
9 Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning 提出VulLLM，通过多任务指令微调增强代码漏洞检测的泛化能力 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🔗⭐
10 Optimizing Autonomous Driving for Safety: A Human-Centric Approach with LLM-Enhanced RLHF 结合LLM与RLHF，提出一种以人为中心的自动驾驶安全优化方法 reinforcement learning RLHF large language model
11 GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model 提出GenSafe，通过降阶MDP模型提升安全强化学习算法的泛化安全性能 reinforcement learning deep reinforcement learning DRL
12 HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning HackAtari：为强化学习的鲁棒性和持续学习构建Atari环境 reinforcement learning PPO curriculum learning

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
13 Pi-fusion: Physics-informed diffusion model for learning fluid dynamics 提出Pi-fusion：一种物理信息扩散模型，用于学习流体动力学。 physics-informed diffusion

⬅️ 返回 cs.AI 首页 · 🏠 返回主页