cs.AI（2024-02-15）

📊 共 26 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) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 BrainWave: A Brain Signal Foundation Model for Clinical Applications 提出BrainWave以解决神经信号模型的多样性问题 foundation model zero-shot transfer
2 ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback 提出ChemReasoner以实现高效催化剂发现 large language model
3 OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models 提出OptiMUS以解决优化问题建模与求解的挑战 large language model
4 Fine-tuning Large Language Model (LLM) Artificial Intelligence Chatbots in Ophthalmology and LLM-based evaluation using GPT-4 基于GPT-4的评估方法提升眼科LLM聊天机器人的临床响应质量 large language model
5 Inadequacies of Large Language Model Benchmarks in the Era of Generative Artificial Intelligence 提出统一评估框架以解决大型语言模型基准不足问题 large language model
6 CodeMind: Evaluating Large Language Models for Code Reasoning 提出CodeMind框架以评估大语言模型的代码推理能力 large language model
7 The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse 揭示模型编辑的蝴蝶效应以应对大语言模型崩溃问题 large language model
8 ProtChatGPT: Towards Understanding Proteins with Large Language Models 提出ProtChatGPT以解决蛋白质结构理解问题 large language model
9 Efficient Prompt Optimization Through the Lens of Best Arm Identification 提出TRIPLE框架以在预算约束下优化提示选择 large language model instruction following
10 MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music 提出MuChin基准以评估音乐领域语言模型的表现 large language model multimodal ✅
11 LoraRetriever: Input-Aware LoRA Retrieval and Composition for Mixed Tasks in the Wild 提出LoraRetriever以解决动态任务下LoRA选择问题 large language model
12 Generative AI in the Construction Industry: A State-of-the-art Analysis 提出生成性人工智能框架以提升建筑行业生产力 large language model
13 Toward a Team of AI-made Scientists for Scientific Discovery from Gene Expression Data 提出AI科学家团队框架以简化基因表达数据分析 large language model
14 Zero-Shot Reasoning: Personalized Content Generation Without the Cold Start Problem 提出个性化内容生成方法以解决冷启动问题 large language model
15 GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving 提出GeoEval基准以评估几何问题求解能力 large language model
16 Chain-of-Planned-Behaviour Workflow Elicits Few-Shot Mobility Generation in LLMs 提出Chain-of-Planned Behaviour以解决人类行为生成问题 large language model
17 Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding 探讨人类与大型语言模型的共创反思机制以提升创意编码 large language model
18 Alpha-GPT 2.0: Human-in-the-Loop AI for Quantitative Investment 提出Alpha-GPT 2.0以提升定量投资中的人机交互效率 large language model
19 X-lifecycle Learning for Cloud Incident Management using LLMs 提出X-lifecycle学习以优化云事件管理 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🔗⭐
20 Aligning Crowd Feedback via Distributional Preference Reward Modeling 提出分布偏好奖励模型以解决人类偏好对齐问题 reinforcement learning deep reinforcement learning large language model
21 Federated Prompt-based Decision Transformer for Customized VR Services in Mobile Edge Computing System 提出联邦提示决策变换器以解决移动边缘计算中的定制VR服务问题 reinforcement learning decision transformer
22 Reinforcement Learning for Solving Stochastic Vehicle Routing Problem with Time Windows 提出强化学习方法以解决随机车辆路径问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
23 LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing 提出LAVE以降低视频编辑的入门门槛 manipulation large language model
24 SwissNYF: Tool Grounded LLM Agents for Black Box Setting 提出SwissNYF以解决黑箱环境下工具规划问题 manipulation large language model ✅

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
25 An advanced data fabric architecture leveraging homomorphic encryption and federated learning 提出一种基于同态加密和联邦学习的安全数据架构以解决医疗图像分析问题 OMOMO

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

#题目一句话要点标签🔗⭐
26 System-level Impact of Non-Ideal Program-Time of Charge Trap Flash (CTF) on Deep Neural Network 提出脉冲列设计补偿技术以解决CTF非理想编程时间问题 PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页