cs.LG（2023-12-06）

📊 共 6 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (2)

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

#题目一句话要点标签🔗⭐
1 FoMo Rewards: Can we cast foundation models as reward functions? 提出基于预训练模型的通用奖励函数，用于强化学习交互任务。 reinforcement learning large language model foundation model
2 Generalized Contrastive Divergence: Joint Training of Energy-Based Model and Diffusion Model through Inverse Reinforcement Learning 提出广义对比散度(GCD)，通过逆强化学习联合训练能量模型和扩散模型 reinforcement learning inverse reinforcement learning
3 Multi-Scale and Multi-Modal Contrastive Learning Network for Biomedical Time Series 提出多尺度多模态对比学习网络MBSL，提升生物医学时间序列表征学习的鲁棒性。 representation learning MAE contrastive learning
4 Pearl: A Production-ready Reinforcement Learning Agent Pearl：一个面向生产环境的强化学习智能体框架，解决实际部署中的多重挑战。 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
5 A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints 提出伪语义损失，解决自回归模型中逻辑约束的难题，并应用于模型解毒。 large language model
6 SmoothQuant+: Accurate and Efficient 4-bit Post-Training WeightQuantization for LLM SmoothQuant+：实现LLM无损精度的高效4比特后训练权重量化 large language model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页