cs.AI（2024-05-13）

📊 共 15 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) (10 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Layout Generation Agents with Large Language Models 提出基于GPT-4V的Agent驱动布局生成系统，提升虚拟空间创建效率。 large language model multimodal
2 DoLLM: How Large Language Models Understanding Network Flow Data to Detect Carpet Bombing DDoS 提出DoLLM，利用大语言模型检测地毯式DDoS攻击 large language model
3 DynLLM: When Large Language Models Meet Dynamic Graph Recommendation DynLLM：利用大语言模型解决动态图推荐中的数据稀疏和时序演化问题 large language model
4 PromptLink: Leveraging Large Language Models for Cross-Source Biomedical Concept Linking PromptLink：利用大型语言模型进行跨源生物医学概念链接 large language model ✅
5 Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions 提出基于LLM和OBTEA的两阶段框架，从人类指令生成最优行为树 large language model ✅
6 Silver-Tongued and Sundry: Exploring Intersectional Pronouns with ChatGPT 利用ChatGPT探索日语人称代词与交叉身份认同的模拟 large language model
7 LLM Theory of Mind and Alignment: Opportunities and Risks 探讨LLM心智理论对齐的机遇与风险，为安全人机交互提供理论基础 large language model
8 Synthetic Test Collections for Retrieval Evaluation 利用大型语言模型构建全合成检索评测数据集，实现可靠的检索系统评估。 large language model
9 G-VOILA: Gaze-Facilitated Information Querying in Daily Scenarios 提出G-VOILA，利用眼动追踪辅助日常场景下的信息查询，提升交互直观性。 multimodal
10 SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts SambaNova SN40L：利用数据流和专家组合扩展AI内存墙 large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
11 Quick and Accurate Affordance Learning 提出基于深度学习的主动式可供性学习框架，模拟婴儿环境探索行为。 affordance

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
12 MADRL-Based Rate Adaptation for 360° Video Streaming with Multi-Viewpoint Prediction 提出基于MADRL和多视角预测的360°视频码率自适应方法，提升QoE。 reinforcement learning deep reinforcement learning multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models 提出CrossCert，通过交叉验证的检测方法增强深度学习模型对抗对抗补丁的鲁棒性认证。 manipulation VIP

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
14 Automatic Recognition of Food Ingestion Environment from the AIM-2 Wearable Sensor 提出双阶段训练框架，解决可穿戴传感器食物摄入环境识别中的数据不平衡问题 egocentric

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

#题目一句话要点标签🔗⭐
15 LLAniMAtion: LLAMA Driven Gesture Animation LLAniMAtion：利用LLAMA驱动的文本生成手势动画 character animation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页