cs.AI（2024-05-29）

📊 共 17 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) (11) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions 提出MathChat基准测试，评估LLM在多轮数学推理和指令跟随中的能力 large language model instruction following
2 Gemini & Physical World: Large Language Models Can Estimate the Intensity of Earthquake Shaking from Multi-Modal Social Media Posts 利用Gemini模型从多模态社交媒体推文估计地震烈度 large language model
3 Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models 提出大型知识模型(LKM)，弥补大型语言模型(LLM)在科学工程领域知识深度不足的缺陷。 large language model
4 Participation in the age of foundation models 针对通用大模型，提出多层参与式框架，提升下游应用中边缘群体的话语权和决策能力。 foundation model
5 Optimizing Foundation Model Inference on a Many-tiny-core Open-source RISC-V Platform 在多微核RISC-V平台上优化Transformer基础模型推理 foundation model
6 Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology using Large Language Models -- A Case in Optimizing Intermodal Freight Transportation 利用大语言模型构建科学本体，助力下一代城市决策支持系统。 large language model
7 Calibrating Reasoning in Language Models with Internal Consistency 利用内部一致性校准语言模型推理，提升推理性能 large language model chain-of-thought
8 Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code 训练代码大语言模型，生成高质量Qiskit量子计算代码 large language model
9 SSFF: Investigating LLM Predictive Capabilities for Startup Success through a Multi-Agent Framework with Enhanced Explainability and Performance 提出SSFF框架，通过多Agent协作和增强可解释性预测创业公司成功率。 large language model
10 Language Models Trained to do Arithmetic Predict Human Risky and Intertemporal Choice 提出利用算术训练的语言模型预测人类决策行为 large language model
11 LLMs achieve adult human performance on higher-order theory of mind tasks 提出手写测试套件以评估LLMs的高阶心智理论能力 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🔗⭐
12 LLMs Meet Multimodal Generation and Editing: A Survey 综述LLM在多模态生成与编辑中的应用，涵盖图像、视频、3D和音频等领域。 world model large language model multimodal ✅
13 One-Shot Safety Alignment for Large Language Models via Optimal Dualization 提出基于最优对偶化的大语言模型单样本安全对齐方法，提升安全性和效率。 reinforcement learning RLHF large language model
14 Exploring the impact of traffic signal control and connected and automated vehicles on intersections safety: A deep reinforcement learning approach 提出基于深度强化学习的交通信号控制与自动驾驶协同优化方案，提升交叉口安全性 reinforcement learning deep reinforcement learning
15 Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding Dr-LLaVA：利用符号临床基础进行视觉指令调优，提升医学VLM的临床推理能力 reinforcement learning RLHF multimodal
16 Efficient Learning in Chinese Checkers: Comparing Parameter Sharing in Multi-Agent Reinforcement Learning 在六人跳棋中，全参数共享的多智能体强化学习优于独立和部分共享架构 reinforcement learning ✅
17 Why Reinforcement Learning in Energy Systems Needs Explanations 强调能源系统中强化学习模型可解释性的必要性 reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页