cs.AI（2024-10-21）

📊 共 35 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (28 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (28 篇)

#题目一句话要点标签🔗⭐
1 Allo-AVA: A Large-Scale Multimodal Conversational AI Dataset for Allocentric Avatar Gesture Animation Allo-AVA：用于第三人称视角头像手势动画的大规模多模态对话AI数据集 multimodal TAMP
2 Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models 提出基于多步推理的大语言模型框架，用于更准确地预测美国总统选举结果 large language model chain-of-thought
3 Multimodal Flare Forecasting with Deep Learning 提出基于深度学习的多模态太阳耀斑预测方法，提升预测精度。 multimodal
4 How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making? 提出CPV数据集与评估框架，诊断并缓解大语言模型在临床决策中的偏见问题 large language model
5 STAR: A Simple Training-free Approach for Recommendations using Large Language Models 提出STAR：一种基于大语言模型的免训练推荐方法，无需微调即可实现高质量推荐。 large language model
6 Comprehensive benchmarking of large language models for RNA secondary structure prediction RNA二级结构预测：大规模语言模型的综合基准测试与性能分析 large language model
7 Large Language Models Powered Multiagent Ensemble for Mitigating Hallucination and Efficient Atrial Fibrillation Annotation of ECG Reports 提出基于大语言模型的多智能体集成方法，用于减少幻觉并高效标注心房颤动心电图报告 large language model
8 Reflection-Bench: Evaluating Epistemic Agency in Large Language Models 提出Reflection-Bench基准，评估大语言模型在认知智能体中的认知能力。 large language model ✅
9 Enabling Energy-Efficient Deployment of Large Language Models on Memristor Crossbar: A Synergy of Large and Small 提出基于忆阻器交叉阵列的新架构，实现大语言模型的高能效部署。 large language model
10 Boosting Jailbreak Transferability for Large Language Models 提出增强转移性的方法以应对大型语言模型的越狱攻击问题 large language model ✅
11 Large Body Language Models 提出大型肢体语言模型LBLM-AVA，用于生成逼真且符合语境的虚拟人物实时手势。 large language model multimodal
12 Long Term Memory: The Foundation of AI Self-Evolution 提出基于长时记忆（LTM）的AI自进化框架，提升模型在推理阶段的认知能力。 large language model foundation model
13 Evaluating the Posterior Sampling Ability of Plug&Play Diffusion Methods in Sparse-View CT 评估Plug&Play扩散模型在稀疏视角CT中的后验采样能力 multimodal
14 A Simple Model of Inference Scaling Laws 提出基于记忆的统计模型，研究多次推理尝试下的LLM性能缩放规律。 large language model
15 Deep Learning and Data Augmentation for Detecting Self-Admitted Technical Debt 提出基于数据增强的深度学习方法，提升自述技术债务检测与分类性能 large language model
16 We Urgently Need Intrinsically Kind Machines 提出一种内生善良机制，通过模拟对话将善良嵌入到基础模型中，以确保与人类价值观对齐。 foundation model
17 Towards a Reliable Offline Personal AI Assistant for Long Duration Spaceflight 针对长时间太空飞行，提出融合GPT、RAG和知识图谱的可靠离线个人AI助手 multimodal
18 PODTILE: Facilitating Podcast Episode Browsing with Auto-generated Chapters PODTILE：提出一种自动生成章节的Transformer模型，用于改善播客浏览体验。 TAMP
19 On-Device LLMs for SMEs: Challenges and Opportunities 针对中小企业，探索端侧大语言模型部署的挑战与机遇 large language model
20 PROMPTHEUS: A Human-Centered Pipeline to Streamline SLRs with LLMs PROMPTHEUS：利用LLM简化系统性文献综述的人工智能驱动流程 large language model ✅
21 Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report 基于PDF的RAG系统开发经验报告：利用LLM增强知识检索与生成 large language model ✅
22 Automated Proof Generation for Rust Code via Self-Evolution SAFE：通过自进化提升LLM在Rust代码形式化验证中的自动证明生成能力 large language model
23 Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation Alchemy：通过符号变异增强定理证明能力 large language model
24 AutoTrain: No-code training for state-of-the-art models AutoTrain：一个无需代码即可训练先进模型的工具 large language model ✅
25 InternLM2.5-StepProver: Advancing Automated Theorem Proving via Critic-Guided Search InternLM2.5-StepProver：通过评论家引导搜索提升自动定理证明能力 large language model ✅
26 NetSafe: Exploring the Topological Safety of Multi-agent Networks NetSafe：探索多智能体网络拓扑安全性，揭示拓扑结构对恶意信息传播的影响 large language model
27 Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration 综述性研究：游戏程序化内容生成（PCG）算法，聚焦LLM融合及其未来方向 large language model
28 OpenMU: Your Swiss Army Knife for Music Understanding OpenMU：用于音乐理解的多功能瑞士军刀型工具与基准测试集 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
29 Improve Vision Language Model Chain-of-thought Reasoning 提出基于GPT-4o蒸馏和强化学习的VLM链式推理优化方法 reinforcement learning direct preference optimization chain-of-thought
30 A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications DPO综述：全面回顾直接偏好优化算法，涵盖数据集、理论、变体与应用 reinforcement learning RLHF DPO ✅
31 VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making 提出VLASCD，解决多模态多任务并行执行中聊天与决策的互斥问题。 reinforcement learning VLA multimodal
32 Patrol Security Game: Defending Against Adversary with Freedom in Attack Timing, Location, and Duration 提出巡逻安全博弈模型，解决攻击者自由选择攻击时间、地点和时长的机器人巡逻问题 reinforcement learning deep reinforcement learning
33 SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks SMAC-R1：基于LLM蒸馏的星际争霸多智能体决策智能涌现 reinforcement learning behavior cloning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
34 Teach Multimodal LLMs to Comprehend Electrocardiographic Images 提出PULSE：一个用于心电图图像理解的多模态大语言模型，并构建ECGInstruct和ECGBench数据集。 PULSE large language model multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
35 Combining Theory of Mind and Kindness for Self-Supervised Human-AI Alignment 结合心智理论与善良原则，实现自监督的人工智能对齐 manipulation reinforcement learning RLHF

⬅️ 返回 cs.AI 首页 · 🏠 返回主页