cs.AI（2024-03-26）

📊 共 19 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Evaluating the Efficacy of Prompt-Engineered Large Multimodal Models Versus Fine-Tuned Vision Transformers in Image-Based Security Applications 比较多模态模型与微调视觉变换器在图像安全中的应用效果 large language model multimodal
2 ALISA: Accelerating Large Language Model Inference via Sparsity-Aware KV Caching 提出ALISA以解决长序列推理中的KV缓存效率问题 large language model
3 Accelerating Radio Spectrum Regulation Workflows with Large Language Models (LLMs) 利用大型语言模型加速无线频谱监管工作流程 large language model
4 KC-GenRe: A Knowledge-constrained Generative Re-ranking Method Based on Large Language Models for Knowledge Graph Completion 提出KC-GenRe以解决知识图谱补全中的重排序问题 large language model
5 Aligning Large Language Models for Enhancing Psychiatric Interviews Through Symptom Delineation and Summarization: Pilot Study 利用大语言模型提升精神病访谈的症状识别与总结 large language model
6 Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization 提出自动形式化方法以验证大型语言模型的定量推理 large language model ✅
7 PerOS: Personalized Self-Adapting Operating Systems in the Cloud 提出PerOS以解决个性化操作系统的智能化问题 large language model
8 MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution 提出MAGIS框架以解决GitHub问题 large language model
9 AgentStudio: A Toolkit for Building General Virtual Agents 提出AgentStudio以解决通用虚拟代理开发与评估问题 multimodal
10 ExpressEdit: Video Editing with Natural Language and Sketching 提出ExpressEdit以解决新手视频编辑困难问题 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
11 Self-Clustering Hierarchical Multi-Agent Reinforcement Learning with Extensible Cooperation Graph 提出层次化合作图学习以解决复杂多智能体问题 reinforcement learning zero-shot transfer
12 LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation 提出学习者感知的监督模仿学习以解决交通模拟中的协变量偏移问题 imitation learning
13 Prioritized League Reinforcement Learning for Large-Scale Heterogeneous Multiagent Systems 提出优先级异构联盟强化学习以解决大规模多智能体系统问题 reinforcement learning
14 Optimization-based Prompt Injection Attack to LLM-as-a-Judge 提出JudgeDeceiver以解决LLM作为评判者的攻击问题 reinforcement learning large language model ✅
15 MA4DIV: Multi-Agent Reinforcement Learning for Search Result Diversification 提出MA4DIV以解决搜索结果多样性问题 reinforcement learning ✅
16 An Open-source End-to-End Logic Optimization Framework for Large-scale Boolean Network with Reinforcement Learning 提出开源端到端逻辑优化框架以解决大规模布尔网络问题 reinforcement learning

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
17 Solution for Emotion Prediction Competition of Workshop on Emotionally and Culturally Intelligent AI 提出单一多模态与情感文化特定提示以解决情感预测问题 motion prediction multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Addressing Social Misattributions of Large Language Models: An HCXAI-based Approach 提出HCXAI框架扩展以解决大型语言模型的社会误归因问题 manipulation 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🔗⭐
19 Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs 提出SYCL实现的多层感知器以提升Intel GPU性能 neural radiance field ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页