cs.AI（2024-09-25）

📊 共 16 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) (8) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗4) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Empirical Asset Pricing with Large Language Model Agents 提出基于大语言模型代理的资产定价模型，提升投资组合优化和资产定价精度。 large language model
2 VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models VPTQ：面向大语言模型的极低比特向量后训练量化方法 large language model
3 Harnessing Diversity for Important Data Selection in Pretraining Large Language Models 提出Quad方法，通过数据影响力和多样性选择提升大语言模型预训练效果 large language model
4 A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms 综述低比特大语言模型：基础、系统与算法，助力高效部署。 large language model
5 Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning 提出Proof of Thought框架，提升LLM推理的可靠性与可解释性 large language model multimodal
6 AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents AXIS：基于API优先的大语言模型智能体实现高效人机交互 large language model multimodal
7 Sociotechnical Approach to Enterprise Generative Artificial Intelligence (E-GenAI) 提出企业生成式人工智能的社会技术方法，整合LLM优化企业运营 large language model
8 AXCEL: Automated eXplainable Consistency Evaluation using LLMs 提出AXCEL，利用LLM实现自动化、可解释的一致性评估，无需特定任务提示。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
9 Enhancing Interpretability in Deep Reinforcement Learning through Semantic Clustering 提出一种结合语义聚类的深度强化学习架构，提升策略可解释性。 reinforcement learning deep reinforcement learning DRL ✅
10 Search for Efficient Large Language Models 提出一种免训练架构搜索框架，用于高效压缩和加速大型语言模型。 distillation large language model ✅
11 DRIM: Learning Disentangled Representations from Incomplete Multimodal Healthcare Data DRIM：学习不完整多模态医疗数据中的解耦表征，提升生存预测。 contrastive learning multimodal ✅
12 A Survey for Deep Reinforcement Learning Based Network Intrusion Detection 综述：基于深度强化学习的网络入侵检测方法研究进展与挑战 reinforcement learning deep reinforcement learning DRL
13 Post-hoc Reward Calibration: A Case Study on Length Bias 提出后验奖励校准方法，无需额外数据和训练即可有效缓解奖励模型中的长度偏差。 reinforcement learning RLHF large language model ✅
14 The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification 利用感知度量作为损失函数，提升音乐表征学习在音乐流派分类任务上的性能 representation learning
15 AI-Driven Risk-Aware Scheduling for Active Debris Removal Missions 提出基于深度强化学习的风险感知主动碎片移除任务规划方法 reinforcement learning deep reinforcement learning DRL

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

#题目一句话要点标签🔗⭐
16 SEN12-WATER: A New Dataset for Hydrological Applications and its Benchmarking 提出SEN12-WATER水资源数据集，并构建深度学习框架用于干旱分析和水资源管理。 spatiotemporal multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页