cs.AI（2024-12-07）

📊 共 16 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) (9 🔗2) 支柱一：机器人控制 (Robot Control) (3) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Comprehensive Evaluation of Multimodal AI Models in Medical Imaging Diagnosis: From Data Augmentation to Preference-Based Comparison	提出医学影像诊断多模态AI模型评估框架，Llama 3.2-90B表现超越人类诊断。	multimodal
2	Training-Free Bayesianization for Low-Rank Adapters of Large Language Models	提出免训练贝叶斯化方法TFB，提升低秩适配大语言模型的不确定性估计。	large language model	✅
3	Leveraging Time-Series Foundation Model for Subsurface Well Logs Prediction and Anomaly Detection	利用时间序列基础模型预测井眼测井数据并进行异常检测	foundation model
4	Modern Hopfield Networks Require Chain-of-Thought to Solve $\mathsf{NC}^1$-Hard Problems	通过链式思维提升现代霍普菲尔德网络解决复杂问题的能力	chain-of-thought
5	Fragmented Layer Grouping in GUI Designs Through Graph Learning Based on Multimodal Information	提出基于图学习的多模态GUI碎片化图层分组方法，提升代码可维护性。	multimodal
6	KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models	提出KG-Retriever，用于提升检索增强大语言模型在复杂问答任务中的效率和效果	large language model
7	A Scoping Review of ChatGPT Research in Accounting and Finance	综述ChatGPT在会计与金融领域的研究，探索未来研究方向。	large language model
8	Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoning	对比LLM与神经符号方法在抽象推理中算术关系的学习能力	large language model	✅
9	Investigating social alignment via mirroring in a system of interacting language models	提出基于交互式语言模型的社会对齐研究框架，探索镜像行为对群体行为的影响	large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
10	GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents	GROOT-2：基于弱监督多模态指令跟随Agent	manipulation multimodal instruction following
11	RLZero: Direct Policy Inference from Language Without In-Domain Supervision	提出RLZero以解决无监督语言指令下的强化学习策略推断问题	humanoid reinforcement learning language conditioned
12	From Flexibility to Manipulation: The Slippery Slope of XAI Evaluation	揭示XAI评估中超参数选择的脆弱性，提出基于排序的鲁棒性提升策略	manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
13	WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion Recognition	WavFusion：提出一种基于wav2vec 2.0的多模态语音情感识别框架	representation learning multimodal
14	LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage	提出LeakAgent，一种基于强化学习的LLM隐私泄露红队测试框架	reinforcement learning large language model	✅
15	AI Planning: A Primer and Survey (Preliminary Report)	AI规划入门与综述：弥合AI子领域差距，促进自动化决策。	reinforcement learning foundation model

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

#	题目	一句话要点	标签	🔗	⭐
16	GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models	提出GEE-OPs知识库，提升LLM在Google Earth Engine平台上的代码生成能力	spatiotemporal large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页