cs.AI（2024-12-24）

📊 共 29 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (25 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (25 篇)

#题目一句话要点标签🔗⭐
1 Decentralized Intelligence in GameFi: Embodied AI Agents and the Convergence of DeFi and Virtual Ecosystems 提出融合具身AI代理的去中心化GameFi生态系统，提升玩家互动和经济参与度 embodied AI large language model
2 Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation Molar：融合多模态信息与协同过滤对齐的LLM序列推荐框架 large language model multimodal
3 Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models 提出PEIT框架，利用属性增强指令调优提升LLM在多任务分子生成中的性能 large language model multimodal ✅
4 Agents on the Bench: Large Language Model Based Multi Agent Framework for Trustworthy Digital Justice AgentsBench：基于大语言模型的多智能体框架，提升数字司法的可信度。 large language model
5 LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating 提出LongDocURL，一个综合性的多模态长文档基准，用于评估理解、推理和定位能力。 multimodal
6 Research on the Proximity Relationships of Psychosomatic Disease Knowledge Graph Modules Extracted by Large Language Models 利用大语言模型提取的心身疾病知识图谱模块邻近关系研究，为诊疗提供新视角。 large language model
7 An Automatic Graph Construction Framework based on Large Language Models for Recommendation 提出AutoGraph框架以自动化图构建解决推荐系统中的效率问题 large language model
8 scReader: Prompting Large Language Models to Interpret scRNA-seq Data scReader：利用大语言模型解读单细胞RNA测序数据，提升跨物种基因分析能力。 large language model
9 GeneSUM: Large Language Model-based Gene Summary Extraction GeneSUM：提出基于大语言模型的基因摘要提取方法，提升生物医学研究效率。 large language model
10 SlimGPT: Layer-wise Structured Pruning for Large Language Models SlimGPT：面向大语言模型的层级结构化剪枝方法，提升部署效率 large language model
11 Real-world Deployment and Evaluation of PErioperative AI CHatbot (PEACH) -- a Large Language Model Chatbot for Perioperative Medicine PEACH：基于大语言模型的围术期医学AI聊天机器人，提升决策效率与一致性 large language model
12 GUI Testing Arena: A Unified Benchmark for Advancing Autonomous GUI Testing Agent 提出GUI测试竞技场(GTArena)，用于评估和提升自主GUI测试Agent的性能。 large language model multimodal ✅
13 Scaling Capability in Token Space: An Analysis of Large Vision Language Model 提出视觉语言模型的标记空间扩展能力分析 large language model
14 DeepCRCEval: Revisiting the Evaluation of Code Review Comment Generation DeepCRCEval：重新审视代码审查评论生成评估方法，提出更可靠的评估框架。 large language model
15 Tackling the Dynamicity in a Production LLM Serving System with SOTA Optimizations via Hybrid Prefill/Decode/Verify Scheduling on Efficient Meta-kernels XY-Serve：通过混合调度和高效Meta-kernel优化，解决生产LLM服务系统中的动态性问题。 large language model
16 MapExplorer: New Content Generation from Low-Dimensional Visualizations 提出MapExplorer，通过低维可视化坐标生成上下文相关的文本内容，实现知识发现。 large language model
17 Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark 提出 DomainCodeBench 多领域代码生成基准，揭示通用LLM在特定领域表现的不足。 large language model ✅
18 The Thousand Brains Project: A New Paradigm for Sensorimotor Intelligence 提出千脑项目：一种基于新皮层原理的通用传感器运动智能新范式 multimodal ✅
19 Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases 提出一种自适应黑盒攻击方法，用于从RAG系统中提取私有知识库 large language model
20 Annotating References to Mythological Entities in French Literature 利用大型语言模型标注法语文学作品中对希腊罗马神话实体的引用 large language model
21 A Novel Task-Driven Method with Evolvable Interactive Agents Using Event Trees for Enhanced Emergency Decision Support 提出EvoTaskTree，利用可进化交互Agent和事件树增强紧急决策支持，解决复杂系统故障下的决策难题。 large language model
22 VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilities 提出VISION：一个模块化AI助手，用于科学用户设施中的自然人机交互 large language model
23 AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation AutoDroid-V2：通过代码生成提升基于SLM的GUI代理性能 large language model ✅
24 AIGT: AI Generative Table Based on Prompt AIGT：基于提示增强的AI生成表格，利用元数据生成高质量合成表格数据。 large language model
25 EvoPat: A Multi-LLM-based Patents Summarization and Analysis Agent EvoPat：一种基于多LLM的专利摘要与分析Agent，助力科研人员高效理解专利。 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🔗⭐
26 Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization 提出直接优势策略优化(DAPO)，提升大语言模型多步推理能力 reinforcement learning PPO offline RL
27 AutoSculpt: A Pattern-based Model Auto-pruning Framework Using Reinforcement Learning and Graph Learning 提出AutoSculpt框架以解决深度神经网络自动剪枝问题 reinforcement learning deep reinforcement learning DRL
28 Joint Adaptive OFDM and Reinforcement Learning Design for Autonomous Vehicles: Leveraging Age of Updates 提出联合自适应OFDM与强化学习设计以解决自动驾驶车辆通信问题 reinforcement learning PPO

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

#题目一句话要点标签🔗⭐
29 LangYa: Revolutionizing Cross-Spatiotemporal Ocean Forecasting LangYa：革新跨时空海洋预测，实现高精度海气耦合预测 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页