cs.AI(2024-09-20)
📊 共 10 篇论文
🎯 兴趣领域导航
支柱九:具身大模型 (Embodied Foundation Models) (6)
支柱二:RL算法与架构 (RL & Architecture) (2)
支柱八:物理动画 (Physics-based Animation) (1)
支柱三:空间感知与语义 (Perception & Semantics) (1)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Differentially Private Multimodal Laplacian Dropout (DP-MLD) for EEG Representative Learning | 提出差分隐私多模态拉普拉斯Dropout(DP-MLD)方案,用于脑电图代表性学习,提升帕金森病步态冻结检测精度。 | multimodal | ||
| 2 | Failures in Perspective-taking of Multimodal AI Systems | 评估GPT-4o的视角理解能力,揭示多模态AI在空间认知上的局限性 | multimodal | ||
| 3 | Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation | 研究指令调优代码语言模型利用辅助函数进行代码生成的能力 | instruction following | ||
| 4 | ChainBuddy: An AI Agent System for Generating LLM Pipelines | ChainBuddy:用于生成LLM流水线的AI Agent系统,解决LLM应用中的“空白页问题”。 | large language model | ||
| 5 | LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench | 评估OpenAI的o1在PlanBench上的规划能力,揭示LLM向LRM的演进及局限性 | large language model | ||
| 6 | Leveraging Knowledge Graphs and LLMs to Support and Monitor Legislative Systems | 利用知识图谱和LLM协同支持和监控立法系统 | large language model |
🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Simple Unsupervised Knowledge Distillation With Space Similarity | 提出基于空间相似性的无监督知识蒸馏方法,提升小模型性能 | distillation | ||
| 8 | Scalable Multi-agent Reinforcement Learning for Factory-wide Dynamic Scheduling | 提出基于领导者-跟随者多智能体强化学习的工厂级动态调度方法 | reinforcement learning |
🔬 支柱八:物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | DS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention | DS2TA:一种具有衰减时空注意力的去噪脉冲Transformer,用于提升视觉任务性能。 | spatiotemporal |
🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 10 | SpaceBlender: Creating Context-Rich Collaborative Spaces Through Generative 3D Scene Blending | SpaceBlender:通过生成式3D场景融合创建富含上下文的协作空间 | depth estimation |