cs.LG（2024-12-21）

📊 共 11 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Lillama: Large Language Models Compression via Low-Rank Feature Distillation	Lillama：通过低秩特征蒸馏压缩大型语言模型，显著降低参数量并保持性能。	Mamba distillation large language model
2	When Can Proxies Improve the Sample Complexity of Preference Learning?	提出代理反馈以改善偏好学习的样本复杂度	policy learning preference learning large language model
3	MOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights	MOL-Mamba：融合结构与电子信息的分子表征增强框架	Mamba representation learning
4	Spatial-Temporal Knowledge Distillation for Takeaway Recommendation	提出STKDRec模型，利用时空知识蒸馏解决外卖推荐中动态用户偏好建模难题。	distillation
5	Subgoal Discovery Using a Free Energy Paradigm and State Aggregations	提出自由能范式与状态聚合的子目标发现方法以解决强化学习中的样本低效问题	reinforcement learning reward shaping

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Correcting Large Language Model Behavior via Influence Function	提出LANCET，利用影响函数自动修正大语言模型的不良行为。	large language model
7	Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees	提出基于任务树的图神经网络预训练框架GIT，实现跨图任务的泛化。	foundation model	✅
8	The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment	全面综述超对齐技术，应对通用人工智能超越人类智能后的对齐挑战	large language model
9	Has LLM Reached the Scaling Ceiling Yet? Unified Insights into LLM Regularities and Constraints	构建统一理论框架，揭示大语言模型扩展的规律与约束	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference	CBNN：用于定制二值神经网络推理的三方安全框架	MPC distillation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Robust random graph matching in Gaussian models via vector approximate message passing	提出向量近似消息传递算法以解决高斯模型下的随机图匹配问题	AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页