cs.LG（2023-11-16）
📊 共 11 篇论文
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (5)
支柱二：RL算法与架构 (RL & Architecture) (5)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Improving Unimodal Inference with Multimodal Transformers | 提出多模态变换器以提升单模态推理性能 | multimodal | ||
| 2 | Hijacking Large Language Models via Adversarial In-Context Learning | 提出可转移的提示注入攻击以解决大语言模型的安全性问题 | large language model | ||
| 3 | Accommodating Missing Modalities in Time-Continuous Multimodal Emotion Recognition | 提出基于Transformer的架构以解决多模态情感识别中的缺失模态问题 | multimodal | ||
| 4 | GEO: Generative Engine Optimization | 提出生成引擎优化（GEO）以提升内容创作者的可见性 | large language model | ||
| 5 | A Speed Odyssey for Deployable Quantization of LLMs | 提出OdysseyLLM以实现高效的LLM量化部署 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Safety Aware Autonomous Path Planning Using Model Predictive Reinforcement Learning for Inland Waterways | 提出基于模型预测强化学习的安全自主路径规划方法 | reinforcement learning PPO occupancy grid | ||
| 7 | Augmenting Unsupervised Reinforcement Learning with Self-Reference | 提出自引用方法以增强无监督强化学习性能 | reinforcement learning | ||
| 8 | Generalization Bounds for Robust Contrastive Learning: From Theory to Practice | 提出鲁棒对比学习的理论框架以提升特征提取的稳健性 | contrastive learning | ||
| 9 | Online Optimization for Network Resource Allocation and Comparison with Reinforcement Learning Techniques | 提出随机在线算法以解决网络资源分配问题 | reinforcement learning | ||
| 10 | Runtime Verification of Learning Properties for Reinforcement Learning Algorithms | 提出运行时验证技术以提升强化学习算法的学习质量与时效性 | reinforcement learning |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 11 | Modelling daily mobility using mobile data traffic at fine spatiotemporal scale | 利用移动数据流量建模城市日常出行模式 | spatiotemporal |