cs.LG（2024-07-03）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 HEMM: Holistic Evaluation of Multimodal Foundation Models HEMM：多模态基础模型的全面评估框架，涵盖基本技能、信息流和实际应用。 foundation model multimodal
2 On Large Language Models in National Security Applications 探讨大语言模型在国家安全应用中的潜力与风险 large language model
3 LoRA-Guard: Parameter-Efficient Guardrail Adaptation for Content Moderation of Large Language Models 提出LoRA-Guard，通过参数高效的Guardrail适配实现大语言模型的内容审核，适用于资源受限设备。 large language model
4 LLMcap: Large Language Model for Unsupervised PCAP Failure Detection 提出LLMcap，利用大语言模型无监督检测PCAP数据中的网络故障 large language model
5 GPTQT: Quantize Large Language Models Twice to Push the Efficiency GPTQT：通过两次量化大型语言模型权重，提升效率并降低存储需求 large language model
6 Universal Length Generalization with Turing Programs 提出基于图灵程序的通用长度泛化方法，解决LLM在算法任务上的外推难题 large language model chain-of-thought
7 DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs DLO：通过动态层操作实现LLM高效垂直扩展 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
8 A Role of Environmental Complexity on Representation Learning in Deep Reinforcement Learning Agents 环境复杂度影响深度强化学习智能体表征学习，揭示导航策略发展规律 reinforcement learning deep reinforcement learning representation learning
9 How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks 通过线性自蒸馏网络隐式偏置，JEPA避免噪声特征干扰 masked autoencoder MAE distillation
10 Differential Encoding for Improved Representation Learning over Graphs 提出差分编码方法，提升图表示学习中节点嵌入的表达能力 representation learning
11 Multi-Task Decision-Making for Multi-User 360 Video Processing over Wireless Networks 提出多任务决策方法以优化无线网络中的360视频处理 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🔗⭐
12 Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions 在高维多模态学习模型中，提出最优阈值和算法以提升推理性能。 AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页