cs.LG（2024-02-09）

📊 共 22 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) (12 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
1 Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning 提出潜在部分因果模型以解决多模态学习中的DAG局限性 representation learning contrastive learning multimodal
2 Corruption Robust Offline Reinforcement Learning with Human Feedback 提出抗干扰的离线强化学习方法以应对人类反馈数据腐败问题 reinforcement learning offline RL offline reinforcement learning
3 Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement 提出熵正则化的令牌级策略优化以解决语言代理强化学习中的不稳定性问题 reinforcement learning PPO RLHF
4 Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss 提出Premier-TACO以提升少样本策略学习效率 policy learning imitation learning representation learning ✅
5 Towards Fair and Firm Real-Time Scheduling in DNN Multi-Tenant Multi-Accelerator Systems via Reinforcement Learning 提出基于深度强化学习的多租户云服务QoS管理方案 reinforcement learning deep reinforcement learning
6 Jointly Learning Representations for Map Entities via Heterogeneous Graph Contrastive Learning 提出HOME-GCL以解决多类别地图实体表示学习问题 representation learning contrastive learning
7 ExGRG: Explicitly-Generated Relation Graph for Self-Supervised Representation Learning 提出ExGRG以解决图结构数据自监督学习中的关系生成问题 representation learning
8 Deceptive Path Planning via Reinforcement Learning with Graph Neural Networks 提出基于强化学习的图神经网络欺骗路径规划方法 reinforcement learning
9 V-STaR: Training Verifiers for Self-Taught Reasoners 提出V-STaR以提升自我学习推理器的准确性 DPO large language model
10 High-Precision Geosteering via Reinforcement Learning and Particle Filters 提出基于强化学习与粒子滤波的高精度地质导向方法 reinforcement learning
11 Issues with Value-Based Multi-objective Reinforcement Learning: Value Function Interference and Overestimation Sensitivity 探讨价值基础多目标强化学习中的干扰与过估计敏感性问题 reinforcement learning
12 POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition 提出POTEC以解决大动作空间中的离线策略学习问题 policy learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
13 FL-NAS: Towards Fairness of NAS for Resource Constrained Devices via Large Language Models 提出FL-NAS以解决资源受限设备的公平性问题 large language model
14 Multimodal Clinical Trial Outcome Prediction with Large Language Models 提出LIFTED模型以解决临床试验结果预测中的多模态融合问题 large language model multimodal
15 Multimodal Interpretable Data-Driven Models for Early Prediction of Antimicrobial Multidrug Resistance Using Multivariate Time-Series 提出多模态可解释数据驱动模型以预测抗菌多重耐药性 multimodal
16 Forecasting Events in Soccer Matches Through Language 提出基于语言模型的足球比赛事件预测方法 large language model
17 Estimating Player Performance in Different Contexts Using Fine-tuned Large Events Models 提出基于大事件模型的足球运动员表现评估方法 large language model
18 Systematic Assessment of Tabular Data Synthesis 提出系统评估框架以提升表格数据合成算法的有效性 large language model
19 CigaR: Cost-efficient Program Repair with LLMs 提出CigaR以降低LLM程序修复成本 large language model
20 Particle Denoising Diffusion Sampler 提出粒子去噪扩散采样器以解决无规范化概率密度采样问题 multimodal
21 Fight Back Against Jailbreaking via Prompt Adversarial Tuning 提出提示对抗调优以应对监狱破坏攻击问题 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following 提出Diffusion-ES以解决自主驾驶中的非可微优化问题 trajectory optimization multimodal instruction following

⬅️ 返回 cs.LG 首页 · 🏠 返回主页