cs.LG（2023-11-14）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱八：物理动画 (Physics-based Animation) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning	提出基础模型蒸馏以提升联邦学习中的轻量客户端性能	distillation foundation model
2	Adversarial Imitation Learning On Aggregated Data	提出对抗模仿学习方法以解决逆强化学习的局限性	reinforcement learning imitation learning inverse reinforcement learning
3	On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling	提出PROPS以解决采样误差导致的低效强化学习问题	reinforcement learning policy learning
4	Purpose in the Machine: Do Traffic Simulators Produce Distributionally Equivalent Outcomes for Reinforcement Learning Applications?	揭示交通模拟器在强化学习中的局限性	reinforcement learning
5	Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees	提出一种新型混合强化学习算法以提升样本效率	policy learning offline RL	✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Finding Inductive Loop Invariants using Large Language Models	利用大型语言模型寻找归纳循环不变式以解决程序验证问题	large language model
7	Plum: Prompt Learning using Metaheuristic	提出基于元启发式的提示学习方法以优化大语言模型	large language model chain-of-thought	✅
8	Towards Evaluating AI Systems for Moral Status Using Self-Reports	提出自我报告方法以评估AI系统的道德状态	large language model
9	DiLoCo: Distributed Low-Communication Training of Language Models	提出DiLoCo以解决低通信环境下语言模型训练问题	large language model
10	Language Models are Better Bug Detector Through Code-Pair Classification	提出代码对分类任务以提升bug检测能力	large language model

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Bayesian Conditional Diffusion Models for Versatile Spatiotemporal Turbulence Generation	提出基于贝叶斯条件扩散模型的多功能时空湍流生成方法	spatiotemporal
12	Mean-field variational inference with the TAP free energy: Geometric and statistical properties in linear models	提出基于TAP自由能的均场变分推断以解决高维贝叶斯线性模型问题	AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页