cs.LG（2024-01-22）

📊 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) (6) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	P2DT: Mitigating Forgetting in task-incremental Learning with progressive prompt Decision Transformer	提出P2DT以解决任务增量学习中的遗忘问题	reinforcement learning offline reinforcement learning decision transformer
2	WARM: On the Benefits of Weight Averaged Reward Models	提出WARM以解决奖励模型中的奖励黑客问题	reinforcement learning RLHF large language model
3	Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning	提出新算法以解决模型误设定下的协变量偏移问题	reinforcement learning
4	Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization	提出ABC-RL以优化布尔电路最小化问题	reinforcement learning
5	Knowledge Distillation on Spatial-Temporal Graph Convolutional Network for Traffic Prediction	提出知识蒸馏方法以提升时空图卷积网络的交通预测效率	distillation
6	Differentiable Tree Search Network	提出可微分树搜索网络以解决有限训练数据下的决策问题	offline RL world model world models

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

#	题目	一句话要点	标签	🔗	⭐
7	Benchmarking Large Multimodal Models against Common Corruptions	提出MMCBench以评估大规模多模态模型在常见干扰下的自一致性	multimodal	✅
8	Multimodal Deep Learning of Word-of-Mouth Text and Demographics to Predict Customer Rating: Handling Consumer Heterogeneity in Marketing	提出多模态深度学习模型以解决消费者异质性问题	multimodal
9	Next Visit Diagnosis Prediction via Medical Code-Centric Multimodal Contrastive EHR Modelling with Hierarchical Regularisation	提出NECHO框架以解决电子健康记录中的诊断预测问题	multimodal
10	"Which LLM should I use?": Evaluating LLMs for tasks performed by Undergraduate Computer Science Students	评估多种大型语言模型以支持计算机科学本科生任务	large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Scaling Face Interaction Graph Networks to Real World Scenes	提出一种内存高效的图网络模拟器以应对真实场景的复杂性	NeRF

⬅️ 返回 cs.LG 首页 · 🏠 返回主页