cs.AI（2024-12-13）

📊 共 17 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 MANGO: Multimodal Acuity traNsformer for intelliGent ICU Outcomes MANGO：多模态 Acuity Transformer 用于智能 ICU 预后 multimodal
2 Do Large Language Models Show Biases in Causal Learning? 研究表明大型语言模型在因果学习中表现出因果错觉偏差 large language model
3 Harnessing Large Language Models for Mental Health: Opportunities, Challenges, and Ethical Considerations 利用大型语言模型改善心理健康：机遇、挑战与伦理考量 large language model
4 NetOrchLLM: Mastering Wireless Network Orchestration with Large Language Models 提出NetOrchLLM，利用大语言模型实现无线网络编排与优化。 large language model
5 Enhancing Automated Loop Invariant Generation for Complex Programs with Large Language Models ACInv：结合静态分析与大语言模型，提升复杂程序循环不变式自动生成 large language model
6 No Free Lunch for Defending Against Prefilling Attack by In-Context Learning 利用上下文学习防御预填充攻击并非易事：对抗性结构虽有效但存在过度防御问题 large language model
7 Cultural Evolution of Cooperation among LLM Agents 研究LLM智能体文化演进，揭示合作行为差异及社会规范形成 large language model
8 Does Multiple Choice Have a Future in the Age of Generative AI? A Posttest-only RCT 对比选择题与开放式问题在生成式AI时代下的教学效果，发现选择题效率更高。 large language model
9 You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects 提出ExecutionAgent，利用LLM自主执行任意项目的测试，提升测试执行成功率。 large language model
10 Large Action Models: From Inception to Implementation 提出大型动作模型（LAM）的开发框架，实现从语言理解到实际动作执行的转变。 large language model ✅
11 AI and the Future of Digital Public Squares 利用大型语言模型重塑数字公共空间，应对挑战并促进对话 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🔗⭐
12 CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models CosyVoice 2：基于大语言模型的可扩展流式语音合成，实现人声自然度对等。 flow matching large language model ✅
13 Physics Instrument Design with Reinforcement Learning 提出基于强化学习的物理仪器设计方法，克服传统梯度优化局限性 reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
14 Tipping Points, Pulse Elasticity and Tonal Tension: An Empirical Study on What Generates Tipping Points 量化音乐转折点：基于时序与音调张力分析肖邦玛祖卡中的关键转折 PULSE
15 Deep Learning for Spectrum Prediction in Cognitive Radio Networks: State-of-the-Art, New Opportunities, and Challenges 提出ViTransLSTM框架，利用深度学习解决认知无线电网络中频谱预测难题。 spatiotemporal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 CSL-L2M: Controllable Song-Level Lyric-to-Melody Generation Based on Conditional Transformer with Fine-Grained Lyric and Musical Controls CSL-L2M：提出一种可控的歌词到旋律生成方法，通过细粒度的歌词和音乐控制生成高质量旋律。 VQ-VAE ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity Panacea：基于精度保持的非对称量化和节能位片稀疏性的新型DNN加速器 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页