cs.LG（2024-11-14）
📊 共 15 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) (5)
支柱一：机器人控制 (Robot Control) (2)
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 | Real-time Adapting Routing (RAR): Improving Efficiency Through Continuous Learning in Software Powered by Layered Foundation Models | 提出实时自适应路由方法以提高基础模型的效率 | large language model foundation model | ||
| 2 | Beyond Static Tools: Evaluating Large Language Models for Cryptographic Misuse Detection | 评估大型语言模型在密码学误用检测中的能力，超越传统静态分析工具 | large language model | ||
| 3 | Efficiently learning and sampling multimodal distributions with data-based initialization | 提出数据驱动初始化方法以高效采样多模态分布 | multimodal | ||
| 4 | LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models | LLaMA-Mesh：用语言模型统一3D网格生成 | large language model | ||
| 5 | Learning Parameter Sharing with Tensor Decompositions and Sparsity | FiPS：结合张量分解与稀疏性的细粒度参数共享算法，压缩ViT和LLM。 | large language model | ||
| 6 | Local deployment of large-scale music AI models on commodity hardware | MIDInfinite：在通用硬件上本地部署大规模音乐AI模型，实现实时MIDI生成。 | large language model | ||
| 7 | Communication Compression for Tensor Parallel LLM Inference | 针对张量并行LLM推理，提出通信压缩方法以降低延迟。 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Approximated Variational Bayesian Inverse Reinforcement Learning for Large Language Model Alignment | 提出AVA：基于近似变分贝叶斯逆强化学习的大语言模型对齐方法 | reinforcement learning imitation learning inverse reinforcement learning | ||
| 9 | Edge Caching Optimization with PPO and Transfer Learning for Dynamic Environments | 提出基于PPO和迁移学习的边缘缓存优化策略，应对动态环境挑战 | reinforcement learning deep reinforcement learning DRL | ||
| 10 | Iterative Batch Reinforcement Learning via Safe Diversified Model-based Policy Search | 提出基于安全多样性模型策略搜索的迭代批量强化学习方法，用于工业控制等高风险场景。 | reinforcement learning policy learning offline reinforcement learning | ||
| 11 | Fair Resource Allocation in Weakly Coupled Markov Decision Processes | 针对弱耦合MDP中的公平资源分配，提出基于Gini系数和深度强化学习的优化方法 | reinforcement learning deep reinforcement learning | ||
| 12 | Reinforced Disentanglers on Random Unitary Circuits | 利用强化学习在随机酉电路中寻找高效解缠器 | reinforcement learning PPO |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 13 | RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering | 综述：基于可微渲染的对抗攻击研究，统一目标与任务，促进未来研究。 | manipulation gaussian splatting splatting | ||
| 14 | FluidML: Fast and Memory Efficient Inference Optimization | FluidML：一种快速且内存高效的推理优化框架，提升边缘设备模型性能。 | humanoid humanoid robot |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 15 | Harnessing Machine Learning for Single-Shot Measurement of Free Electron Laser Pulse Power | 利用机器学习单次测量自由电子激光脉冲功率 | PULSE |