cs.LG（2024-07-04）

📊 共 11 篇论文 | 🔗 3 篇有代码

🎯 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) (3 🔗2) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards	探索性研究：剖析大模型排行榜的运作流程与潜在问题（Leaderboard Smells）	large language model foundation model
2	Uncertainty-Guided Likelihood Tree Search	提出不确定性引导的似然树搜索算法，解决序列决策中奖励稀疏问题	large language model
3	A Survey of Controllable Learning: Methods and Applications in Information Retrieval	综述可控学习在信息检索中的应用：方法、挑战与未来方向	large language model
4	A Survey of Data Synthesis Approaches	合成数据技术综述：提升数据质量与模型泛化能力	foundation model
5	QET: Enhancing Quantized LLM Parameters and KV cache Compression through Element Substitution and Residual Clustering	提出QET算法，通过元素替换和残差聚类增强量化LLM参数和KV缓存压缩。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Q-Adapter: Customizing Pre-trained LLMs to New Preferences with Forgetting Mitigation	提出Q-Adapter以解决LLM定制化与遗忘问题	reinforcement learning RLHF large language model	✅
7	ROER: Regularized Optimal Experience Replay	提出ROER：基于正则化最优经验回放的强化学习方法，提升样本利用率。	reinforcement learning SAC	✅
8	Multi-Time Scale Service Caching and Pricing in MEC Systems with Dynamic Program Popularity	提出多时间尺度服务缓存与定价框架，解决MEC系统中动态程序流行度下的资源优化问题	reinforcement learning deep reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
9	Reduced-Order Neural Operators: Learning Lagrangian Dynamics on Highly Sparse Graphs	GIOROM：基于图神经网络的降阶模型，加速拉格朗日动力学仿真。	spatiotemporal	✅
10	Low-latency machine learning FPGA accelerator for multi-qubit-state discrimination	提出低延迟FPGA加速器以解决多量子比特状态判别问题	PULSE

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	A fast neural hybrid Newton solver adapted to implicit methods for nonlinear dynamics	提出一种快速神经混合牛顿求解器，加速非线性动力学隐式方法	structure preservation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页