cs.AI（2024-06-13）

📊 共 13 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) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1 🔗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) (9 篇)

#题目一句话要点标签🔗⭐
1 Automated Molecular Concept Generation and Labeling with Large Language Models AutoMolCo：利用大语言模型自动生成和标注分子概念，提升分子性质预测性能。 large language model
2 JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models JailbreakEval：用于评估大语言模型越狱攻击的集成工具包 large language model
3 Hierarchical Compression of Text-Rich Graphs via Large Language Models 提出HiCom，通过层级压缩文本信息，提升LLM在富文本图上的节点分类性能。 large language model
4 ResearchArena: Benchmarking Large Language Models' Ability to Collect and Organize Information as Research Agents ResearchArena：评估大语言模型作为研究代理的信息收集与组织能力 large language model ✅
5 3D Building Generation in Minecraft via Large Language Models 提出T2BM模型，利用大语言模型在Minecraft中生成3D建筑 large language model
6 VLind-Bench: Measuring Language Priors in Large Vision-Language Models VLind-Bench：首个用于评估大型视觉语言模型中语言先验的基准测试。 multimodal
7 ElicitationGPT: Text Elicitation Mechanisms via Language Models ElicitationGPT：利用语言模型进行文本诱导机制设计，实现可证明的文本信息可靠获取。 large language model
8 Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs JailTrickBench：针对防御增强型LLM的越狱攻击基准测试框架 large language model ✅
9 A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices 综述性论文：AI模型组合学习的理论与实验研究 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🔗⭐
10 Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges 音乐情感预测综述：分析数据集、模型及挑战，促进更精准的情感捕捉。 predictive model motion prediction
11 On Softmax Direct Preference Optimization for Recommendation 提出Softmax-DPO以优化推荐系统中的用户偏好排序问题 DPO direct preference optimization ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
12 PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance 构建PianoMotion10M数据集，提出钢琴演奏手部动作生成基准 motion generation ✅

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

#题目一句话要点标签🔗⭐
13 AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis 提出AV-GS模型，利用材质和几何先验实现新视角声学合成 gaussian splatting splatting NeRF

⬅️ 返回 cs.AI 首页 · 🏠 返回主页